all: youtube-dl README.md CONTRIBUTING.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish supportedsites
clean:
- rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish *.dump *.part *.info.json CONTRIBUTING.md.tmp
-
-cleanall: clean
- rm -f youtube-dl youtube-dl.exe
+ rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish *.dump *.part *.info.json *.mp4 *.flv *.mp3 CONTRIBUTING.md.tmp youtube-dl youtube-dl.exe
PREFIX ?= /usr/local
BINDIR ?= $(PREFIX)/bin
## Video Selection:
--playlist-start NUMBER playlist video to start at (default is 1)
--playlist-end NUMBER playlist video to end at (default is last)
+ --playlist-items ITEM_SPEC playlist video items to download. Specify
+ indices of the videos in the playlist
+ seperated by commas like: "--playlist-items
+ 1,2,5,8" if you want to download videos
+ indexed 1, 2, 5, 8 in the playlist. You can
+ specify range: "--playlist-items
+ 1-3,7,10-13", it will download the videos
+ at index 1, 2, 3, 7, 10, 11, 12 and 13.
--match-title REGEX download only matching titles (regex or
caseless sub-string)
--reject-title REGEX skip download for matching titles (regex or
## Download Options:
-r, --rate-limit LIMIT maximum download rate in bytes per second
(e.g. 50K or 4.2M)
- -R, --retries RETRIES number of retries (default is 10)
+ -R, --retries RETRIES number of retries (default is 10), or
+ "infinite".
--buffer-size SIZE size of download buffer (e.g. 1024 or 16K)
(default is 1024)
--no-resize-buffer do not automatically adjust the buffer
automatically resized from an initial value
of SIZE.
--playlist-reverse Download playlist videos in reverse order
+ --xattr-set-filesize (experimental) set file xattribute
+ ytdl.filesize with expected filesize
+ --external-downloader COMMAND (experimental) Use the specified external
+ downloader. Currently supports
+ aria2c,curl,wget
## Filesystem Options:
-a, --batch-file FILE file containing URLs to download ('-' for
--write-info-json write video metadata to a .info.json file
--write-annotations write video annotations to a .annotation
file
- --write-thumbnail write thumbnail image to disk
--load-info FILE json file containing the video information
(created with the "--write-json" option)
--cookies FILE file to read cookies from and dump cookie
--no-cache-dir Disable filesystem caching
--rm-cache-dir Delete all filesystem cache files
+## Thumbnail images:
+ --write-thumbnail write thumbnail image to disk
+ --write-all-thumbnails write all thumbnail image formats to disk
+ --list-thumbnails Simulate and list all available thumbnail
+ formats
+
## Verbosity / Simulation Options:
-q, --quiet activates quiet mode
--no-warnings Ignore warnings
--bidi-workaround Work around terminals that lack
bidirectional text support. Requires bidiv
or fribidi executable in PATH
+ --sleep-interval SECONDS Number of seconds to sleep before each
+ download.
## Video Format Options:
-f, --format FORMAT video format code, specify the order of
by extension for the extensions aac, m4a,
mp3, mp4, ogg, wav, webm. You can also use
the special names "best", "bestvideo",
- "bestaudio", "worst". By default, youtube-
- dl will pick the best quality. Use commas
- to download multiple audio formats, such as
- -f
+ "bestaudio", "worst". You can filter the
+ video results by putting a condition in
+ brackets, as in -f "best[height=720]" (or
+ -f "[filesize>10M]"). This works for
+ filesize, height, width, tbr, abr, vbr, and
+ fps and the comparisons <, <=, >, >=, =, !=
+ . Formats for which the value is not known
+ are excluded unless you put a question mark
+ (?) after the operator. You can combine
+ format filters, so -f "[height <=?
+ 720][tbr>500]" selects up to 720p videos
+ (or videos where the height is not known)
+ with a bitrate of at least 500 KBit/s. By
+ default, youtube-dl will pick the best
+ quality. Use commas to download multiple
+ audio formats, such as -f
136/137/mp4/bestvideo,140/m4a/bestaudio.
You can merge the video and audio of two
formats into a single file using -f <video-
## Authentication Options:
-u, --username USERNAME login with this account ID
- -p, --password PASSWORD account password
+ -p, --password PASSWORD account password. If this option is left
+ out, youtube-dl will ask interactively.
-2, --twofactor TWOFACTOR two-factor auth code
-n, --netrc use .netrc authentication data
--video-password PASSWORD video password (vimeo, smotri)
--add-metadata write metadata to the video file
--xattrs write metadata to the video file's xattrs
(using dublin core and xdg standards)
- --fixup POLICY (experimental) Automatically correct known
- faults of the file. One of never (do
- nothing), warn (only emit a warning),
- detect_or_warn(check whether we can do
- anything about it, warn otherwise
+ --fixup POLICY Automatically correct known faults of the
+ file. One of never (do nothing), warn (only
+ emit a warning), detect_or_warn(the
+ default; fix file if we can, warn
+ otherwise)
--prefer-avconv Prefer avconv over ffmpeg for running the
postprocessors (default)
--prefer-ffmpeg Prefer ffmpeg over avconv for running the
From then on, after restarting your shell, you will be able to access both youtube-dl and ffmpeg (and youtube-dl will be able to find ffmpeg) by simply typing `youtube-dl` or `ffmpeg`, no matter what directory you're in.
+### How do I put downloads into a specific folder?
+
+Use the `-o` to specify an [output template](#output-template), for example `-o "/home/user/videos/%(title)s-%(id)s.%(ext)s"`. If you want this for all of your downloads, put the option into your [configuration file](#configuration).
+
+### How do I download a video starting with a `-` ?
+
+Either prepend `http://www.youtube.com/watch?v=` or separate the ID from the options with `--`:
+
+ youtube-dl -- -wNyEUrxzFU
+ youtube-dl "http://www.youtube.com/watch?v=-wNyEUrxzFU"
+
+### Can you add support for this anime video site, or site which shows current movies for free?
+
+As a matter of policy (as well as legality), youtube-dl does not include support for services that specialize in infringing copyright. As a rule of thumb, if you cannot easily find a video that the service is quite obviously allowed to distribute (i.e. that has been uploaded by the creator, the creator's distributor, or is published under a free license), the service is probably unfit for inclusion to youtube-dl.
+
+A note on the service that they don't host the infringing content, but just link to those who do, is evidence that the service should **not** be included into youtube-dl. The same goes for any DMCA note when the whole front page of the service is filled with videos they are not allowed to distribute. A "fair use" note is equally unconvincing if the service shows copyright-protected videos in full without authorization.
+
+Support requests for services that **do** purchase the rights to distribute their content are perfectly fine though. If in doubt, you can simply include a source that mentions the legitimate purchase of content.
+
### How can I detect whether a given URL is supported by youtube-dl?
-For one, have a look at the [list of supported sites](docs/supportedsites). Note that it can sometimes happen that the site changes its URL scheme (say, from http://example.com/v/1234567 to http://example.com/v/1234567 ) and youtube-dl reports an URL of a service in that list as unsupported. In that case, simply report a bug.
+For one, have a look at the [list of supported sites](docs/supportedsites.md). Note that it can sometimes happen that the site changes its URL scheme (say, from http://example.com/v/1234567 to http://example.com/v/1234567 ) and youtube-dl reports an URL of a service in that list as unsupported. In that case, simply report a bug.
It is *not* possible to detect whether a URL is supported or not. That's because youtube-dl contains a generic extractor which matches **all** URLs. You may be tempted to disable, exclude, or remove the generic extractor, but the generic extractor not only allows users to extract videos from lots of websites that embed a video from another service, but may also be used to extract video from a service that it's hosting itself. Therefore, we neither recommend nor support disabling, excluding, or removing the generic extractor.
5. Add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py).
6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will be then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
7. Have a look at [`youtube_dl/common/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L38). Add tests and code for as many as you want.
-8. If you can, check the code with [pyflakes](https://pypi.python.org/pypi/pyflakes) (a good idea) and [pep8](https://pypi.python.org/pypi/pep8) (optional, ignore E501).
+8. If you can, check the code with [flake8](https://pypi.python.org/pypi/flake8).
9. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this:
$ git add youtube_dl/extractor/__init__.py
### Is anyone going to need the feature?
-Only post features that you (or an incapicated friend you can personally talk to) require. Do not post features because they seem like a good idea. If they are really useful, they will be requested by someone who requires them.
+Only post features that you (or an incapacitated friend you can personally talk to) require. Do not post features because they seem like a good idea. If they are really useful, they will be requested by someone who requires them.
### Is your question about youtube-dl?
--playlist-start NUMBER playlist video to start at (default is 1)
--playlist-end NUMBER playlist video to end at (default is last)
+ --playlist-items ITEM_SPEC playlist video items to download. Specify
+ indices of the videos in the playlist
+ seperated by commas like: "--playlist-items
+ 1,2,5,8" if you want to download videos
+ indexed 1, 2, 5, 8 in the playlist. You can
+ specify range: "--playlist-items
+ 1-3,7,10-13", it will download the videos
+ at index 1, 2, 3, 7, 10, 11, 12 and 13.
--match-title REGEX download only matching titles (regex or
caseless sub-string)
--reject-title REGEX skip download for matching titles (regex or
-r, --rate-limit LIMIT maximum download rate in bytes per second
(e.g. 50K or 4.2M)
- -R, --retries RETRIES number of retries (default is 10)
+ -R, --retries RETRIES number of retries (default is 10), or
+ "infinite".
--buffer-size SIZE size of download buffer (e.g. 1024 or 16K)
(default is 1024)
--no-resize-buffer do not automatically adjust the buffer
automatically resized from an initial value
of SIZE.
--playlist-reverse Download playlist videos in reverse order
+ --xattr-set-filesize (experimental) set file xattribute
+ ytdl.filesize with expected filesize
+ --external-downloader COMMAND (experimental) Use the specified external
+ downloader. Currently supports
+ aria2c,curl,wget
Filesystem Options:
-------------------
--write-info-json write video metadata to a .info.json file
--write-annotations write video annotations to a .annotation
file
- --write-thumbnail write thumbnail image to disk
--load-info FILE json file containing the video information
(created with the "--write-json" option)
--cookies FILE file to read cookies from and dump cookie
--no-cache-dir Disable filesystem caching
--rm-cache-dir Delete all filesystem cache files
+Thumbnail images:
+-----------------
+
+ --write-thumbnail write thumbnail image to disk
+ --write-all-thumbnails write all thumbnail image formats to disk
+ --list-thumbnails Simulate and list all available thumbnail
+ formats
+
Verbosity / Simulation Options:
-------------------------------
--bidi-workaround Work around terminals that lack
bidirectional text support. Requires bidiv
or fribidi executable in PATH
+ --sleep-interval SECONDS Number of seconds to sleep before each
+ download.
Video Format Options:
---------------------
by extension for the extensions aac, m4a,
mp3, mp4, ogg, wav, webm. You can also use
the special names "best", "bestvideo",
- "bestaudio", "worst". By default, youtube-
- dl will pick the best quality. Use commas
- to download multiple audio formats, such as
- -f
+ "bestaudio", "worst". You can filter the
+ video results by putting a condition in
+ brackets, as in -f "best[height=720]" (or
+ -f "[filesize>10M]"). This works for
+ filesize, height, width, tbr, abr, vbr, and
+ fps and the comparisons <, <=, >, >=, =, !=
+ . Formats for which the value is not known
+ are excluded unless you put a question mark
+ (?) after the operator. You can combine
+ format filters, so -f "[height <=?
+ 720][tbr>500]" selects up to 720p videos
+ (or videos where the height is not known)
+ with a bitrate of at least 500 KBit/s. By
+ default, youtube-dl will pick the best
+ quality. Use commas to download multiple
+ audio formats, such as -f
136/137/mp4/bestvideo,140/m4a/bestaudio.
You can merge the video and audio of two
formats into a single file using -f <video-
-----------------------
-u, --username USERNAME login with this account ID
- -p, --password PASSWORD account password
+ -p, --password PASSWORD account password. If this option is left
+ out, youtube-dl will ask interactively.
-2, --twofactor TWOFACTOR two-factor auth code
-n, --netrc use .netrc authentication data
--video-password PASSWORD video password (vimeo, smotri)
--add-metadata write metadata to the video file
--xattrs write metadata to the video file's xattrs
(using dublin core and xdg standards)
- --fixup POLICY (experimental) Automatically correct known
- faults of the file. One of never (do
- nothing), warn (only emit a warning),
- detect_or_warn(check whether we can do
- anything about it, warn otherwise
+ --fixup POLICY Automatically correct known faults of the
+ file. One of never (do nothing), warn (only
+ emit a warning), detect_or_warn(the
+ default; fix file if we can, warn
+ otherwise)
--prefer-avconv Prefer avconv over ffmpeg for running the
postprocessors (default)
--prefer-ffmpeg Prefer ffmpeg over avconv for running the
by simply typing youtube-dl or ffmpeg, no matter what directory you're
in.
+How do I put downloads into a specific folder?
+
+Use the -o to specify an output template, for example
+-o "/home/user/videos/%(title)s-%(id)s.%(ext)s". If you want this for
+all of your downloads, put the option into your configuration file.
+
+How do I download a video starting with a - ?
+
+Either prepend http://www.youtube.com/watch?v= or separate the ID from
+the options with --:
+
+ youtube-dl -- -wNyEUrxzFU
+ youtube-dl "http://www.youtube.com/watch?v=-wNyEUrxzFU"
+
+Can you add support for this anime video site, or site which shows current movies for free?
+
+As a matter of policy (as well as legality), youtube-dl does not include
+support for services that specialize in infringing copyright. As a rule
+of thumb, if you cannot easily find a video that the service is quite
+obviously allowed to distribute (i.e. that has been uploaded by the
+creator, the creator's distributor, or is published under a free
+license), the service is probably unfit for inclusion to youtube-dl.
+
+A note on the service that they don't host the infringing content, but
+just link to those who do, is evidence that the service should not be
+included into youtube-dl. The same goes for any DMCA note when the whole
+front page of the service is filled with videos they are not allowed to
+distribute. A "fair use" note is equally unconvincing if the service
+shows copyright-protected videos in full without authorization.
+
+Support requests for services that do purchase the rights to distribute
+their content are perfectly fine though. If in doubt, you can simply
+include a source that mentions the legitimate purchase of content.
+
How can I detect whether a given URL is supported by youtube-dl?
For one, have a look at the list of supported sites. Note that it can
7. Have a look at youtube_dl/common/extractor/common.py for possible
helper methods and a detailed description of what your extractor
should return. Add tests and code for as many as you want.
-8. If you can, check the code with pyflakes (a good idea) and pep8
- (optional, ignore E501).
+8. If you can, check the code with flake8.
9. When the tests pass, add the new files and commit them and push the
result, like this:
Is anyone going to need the feature?
-Only post features that you (or an incapicated friend you can personally
-talk to) require. Do not post features because they seem like a good
-idea. If they are really useful, they will be requested by someone who
-requires them.
+Only post features that you (or an incapacitated friend you can
+personally talk to) require. Do not post features because they seem like
+a good idea. If they are really useful, they will be requested by
+someone who requires them.
Is your question about youtube-dl?
if [ ! -f "updates_key.pem" ]; then echo 'ERROR: updates_key.pem missing'; exit 1; fi
/bin/echo -e "\n### First of all, testing..."
-make cleanall
+make clean
if $skip_tests ; then
echo 'SKIPPING TESTS'
else
/bin/echo -e "\n### Changing version in version.py..."
sed -i "s/__version__ = '.*'/__version__ = '$version'/" youtube_dl/version.py
-/bin/echo -e "\n### Committing README.md and youtube_dl/version.py..."
-make README.md
-git add README.md youtube_dl/version.py
+/bin/echo -e "\n### Committing documentation and youtube_dl/version.py..."
+make README.md CONTRIBUTING.md supportedsites
+git add README.md CONTRIBUTING.md docs/supportedsites.md youtube_dl/version.py
git commit -m "release $version"
/bin/echo -e "\n### Now tagging, signing and pushing..."
- **8tracks**
- **9gag**
- **abc.net.au**
+ - **Abc7News**
- **AcademicEarth:Course**
- **AddAnime**
- **AdobeTV**
- **Aftonbladet**
- **AlJazeera**
- **Allocine**
+ - **AlphaPorno**
- **anitube.se**
- **AnySex**
- **Aparat**
+ - **AppleDailyAnimationNews**
+ - **AppleDailyRealtimeNews**
- **AppleTrailers**
- **archive.org**: archive.org videos
- **ARD**
- **arte.tv:ddc**
- **arte.tv:embed**
- **arte.tv:future**
+ - **AtresPlayer**
+ - **ATTTechChannel**
- **audiomack**
- - **AUEngine**
+ - **audiomack:album**
- **Azubu**
- **bambuser**
- **bambuser:channel**
- **cmt.com**
- **CNET**
- **CNN**
+ - **CNNArticle**
- **CNNBlogs**
- **CollegeHumor**
+ - **CollegeRama**
- **ComCarCoff**
- **ComedyCentral**
- **ComedyCentralShows**: The Daily Show / The Colbert Report
- **Crunchyroll**
- **crunchyroll:playlist**
- **CSpan**: C-SPAN
+ - **CtsNews**
- **culturebox.francetvinfo.fr**
- **dailymotion**
- **dailymotion:playlist**
- **dailymotion:user**
- **daum.net**
- **DBTV**
+ - **DctpTv**
- **DeezerPlaylist**
- **defense.gouv.fr**
- **Discovery**
- **divxstage**: DivxStage
- **Dotsub**
+ - **DRBonanza**
- **Dropbox**
- **DrTuber**
- **DRTV**
- **Dump**
- **dvtv**: http://video.aktualne.cz/
- **EbaumsWorld**
+ - **EchoMsk**
- **eHow**
- **Einthusan**
- **eitb.tv**
- **EMPFlix**
- **Engadget**
- **Eporner**
+ - **EroProfile**
- **Escapist**
- **EveryonesMixtape**
- **exfm**: ex.fm
- **GDCVault**
- **generic**: Generic downloader that works on some sites
- **GiantBomb**
+ - **Giga**
- **Glide**: Glide mobile video messages (glide.me)
- **Globo**
- **GodTube**
- **Grooveshark**
- **Groupon**
- **Hark**
+ - **HearThisAt**
- **Heise**
+ - **HellPorno**
- **Helsinki**: helsinki.fi
- **HentaiStigma**
+ - **HistoricFilms**
+ - **hitbox**
+ - **hitbox:live**
- **HornBunny**
- **HostingBulk**
- **HotNewHipHop**
- **jpopsuki.tv**
- **Jukebox**
- **Kankan**
+ - **Karaoketv**
- **keek**
- **KeezMovies**
- **KhanAcademy**
- **LiveLeak**
- **livestream**
- **livestream:original**
+ - **LnkGo**
- **lrt.lt**
- **lynda**: lynda.com videos
- **lynda:course**: lynda.com online courses
- **MySpass**
- **myvideo**
- **MyVidster**
+ - **n-tv.de**
- **Naver**
- **NBA**
- **NBC**
- **ndr**: NDR.de - Mediathek
- **NDTV**
- **NerdCubedFeed**
+ - **Nerdist**
+ - **Netzkino**
- **Newgrounds**
- **Newstube**
+ - **NextMedia**
+ - **NextMediaActionNews**
- **nfb**: National Film Board of Canada
- **nfl.com**
- **nhl.com**
+ - **nhl.com:news**: NHL news
- **nhl.com:videocenter**: NHL videocenter category
- **niconico**: ニコニコ動画
- **NiconicoPlaylist**
- **Nowness**
- **nowvideo**: NowVideo
- **npo.nl**
+ - **npo.nl:live**
- **NRK**
- **NRKTV**
- - **NTV**
+ - **ntv.ru**
- **Nuvid**
- **NYTimes**
- **ocw.mit.edu**
- **OktoberfestTV**
- **on.aol.com**
- **Ooyala**
+ - **OpenFilm**
+ - **orf:fm4**: radio FM4
- **orf:oe1**: Radio Österreich 1
- **orf:tvthek**: ORF TVthek
- - **ORFFM4**: radio FM4
- **parliamentlive.tv**: UK parliament videos
- **Patreon**
- **PBS**
- **Pyvideo**
- **QuickVid**
- **radio.de**
+ - **radiobremen**
- **radiofrance**
- **Rai**
- **RBMARadio**
- **RottenTomatoes**
- **Roxwel**
- **RTBF**
+ - **Rte**
+ - **RTL2**
- **RTLnow**
- **rtlxl.nl**
- **RTP**
- **RUHD**
- **rutube**: Rutube videos
- **rutube:channel**: Rutube channels
+ - **rutube:embed**: Rutube embedded videos
- **rutube:movie**: Rutube movies
- **rutube:person**: Rutube person videos
- **RUTV**: RUTV.RU
- **Sport5**
- **SportBox**
- **SportDeutschland**
- - **SRMediathek**: Süddeutscher Rundfunk
+ - **SRMediathek**: Saarländischer Rundfunk
- **stanfordoc**: Stanford Open ClassRoom
- **Steam**
- **streamcloud.eu**
- **StreamCZ**
+ - **StreetVoice**
- **SunPorno**
- **SWRMediathek**
- **Syfy**
- **TeleBruxelles**
- **telecinco.es**
- **TeleMB**
+ - **TeleTask**
- **TenPlay**
+ - **TestTube**
- **TF1**
- **TheOnion**
- **ThePlatform**
- **tv.dfb.de**
- **tvigle**: Интернет-телевидение Tvigle.ru
- **tvp.pl**
+ - **tvp.pl:Series**
- **TVPlay**: TV3Play and related services
- - **Twitch**
+ - **Tweakers**
+ - **twitch:bookmarks**
+ - **twitch:chapter**
+ - **twitch:past_broadcasts**
+ - **twitch:profile**
+ - **twitch:stream**
+ - **twitch:video**
+ - **twitch:vod**
- **Ubu**
- **udemy**
- **udemy:course**
- **videoweed**: VideoWeed
- **Vidme**
- **Vidzi**
+ - **vier**
+ - **vier:videos**
- **viki**
- **vimeo**
- **vimeo:album**
- **WDR**
- **wdr:mobile**
- **WDRMaus**: Sendung mit der Maus
+ - **WebOfStories**
- **Weibo**
- **Wimp**
- **Wistia**
- **WorldStarHipHop**
- **wrzuta.pl**
+ - **WSJ**: Wall Street Journal
- **XBef**
- **XboxClips**
- **XHamster**
- **XNXX**
- **XTube**
- **XTubeUser**: XTube user profile
+ - **Xuite**
- **XVideos**
+ - **XXXYMovies**
- **Yahoo**: Yahoo screen and movies
- **YesJapan**
- **Ynet**
- **youtube:search_url**: YouTube.com search URLs
- **youtube:show**: YouTube.com (multi-season) shows
- **youtube:subscriptions**: YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)
- - **youtube:toplist**: YouTube.com top lists, "yttoplist:{channel}:{list title}" (Example: "yttoplist:music:Top Tracks")
- **youtube:user**: YouTube.com user videos (URL or "ytuser" keyword)
- **youtube:watch_later**: Youtube watch later list, ":ytwatchlater" for short (requires authentication)
- **ZDF**
self.assertTrue(
match_rex.match(got),
'field %s (value: %r) should match %r' % (info_field, got, match_str))
+ elif isinstance(expected, compat_str) and expected.startswith('startswith:'):
+ got = got_dict.get(info_field)
+ start_str = expected[len('startswith:'):]
+ self.assertTrue(
+ isinstance(got, compat_str),
+ 'Expected a %s object, but got %s for field %s' % (
+ compat_str.__name__, type(got).__name__, info_field))
+ self.assertTrue(
+ got.startswith(start_str),
+ 'field %s (value: %r) should start with %r' % (info_field, got, start_str))
elif isinstance(expected, type):
got = got_dict.get(info_field)
self.assertTrue(isinstance(got, expected),
# Are checkable fields missing from the test case definition?
test_info_dict = dict((key, value if not isinstance(value, compat_str) or len(value) < 250 else 'md5:' + md5(value))
for key, value in got_dict.items()
- if value and key in ('title', 'description', 'uploader', 'upload_date', 'timestamp', 'uploader_id', 'location'))
+ if value and key in ('id', 'title', 'description', 'uploader', 'upload_date', 'timestamp', 'uploader_id', 'location'))
missing_keys = set(test_info_dict.keys()) - set(expected_dict.keys())
if missing_keys:
def _repr(v):
return "'%s'" % v.replace('\\', '\\\\').replace("'", "\\'").replace('\n', '\\n')
else:
return repr(v)
- info_dict_str = ''.join(
- ' %s: %s,\n' % (_repr(k), _repr(v))
- for k, v in test_info_dict.items())
+ info_dict_str = ''
+ if len(missing_keys) != len(expected_dict):
+ info_dict_str += ''.join(
+ ' %s: %s,\n' % (_repr(k), _repr(v))
+ for k, v in test_info_dict.items() if k not in missing_keys)
+ info_dict_str += '\n'
+ info_dict_str += ''.join(
+ ' %s: %s,\n' % (_repr(k), _repr(test_info_dict[k]))
+ for k in missing_keys)
write_string(
'\n\'info_dict\': {\n' + info_dict_str + '}\n', out=sys.stderr)
self.assertFalse(
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], f1id)
+ def test_format_filtering(self):
+ formats = [
+ {'format_id': 'A', 'filesize': 500, 'width': 1000},
+ {'format_id': 'B', 'filesize': 1000, 'width': 500},
+ {'format_id': 'C', 'filesize': 1000, 'width': 400},
+ {'format_id': 'D', 'filesize': 2000, 'width': 600},
+ {'format_id': 'E', 'filesize': 3000},
+ {'format_id': 'F'},
+ {'format_id': 'G', 'filesize': 1000000},
+ ]
+ for f in formats:
+ f['url'] = 'http://_/'
+ f['ext'] = 'unknown'
+ info_dict = _make_result(formats)
+
+ ydl = YDL({'format': 'best[filesize<3000]'})
+ ydl.process_ie_result(info_dict)
+ downloaded = ydl.downloaded_info_dicts[0]
+ self.assertEqual(downloaded['format_id'], 'D')
+
+ ydl = YDL({'format': 'best[filesize<=3000]'})
+ ydl.process_ie_result(info_dict)
+ downloaded = ydl.downloaded_info_dicts[0]
+ self.assertEqual(downloaded['format_id'], 'E')
+
+ ydl = YDL({'format': 'best[filesize <= ? 3000]'})
+ ydl.process_ie_result(info_dict)
+ downloaded = ydl.downloaded_info_dicts[0]
+ self.assertEqual(downloaded['format_id'], 'F')
+
+ ydl = YDL({'format': 'best [filesize = 1000] [width>450]'})
+ ydl.process_ie_result(info_dict)
+ downloaded = ydl.downloaded_info_dicts[0]
+ self.assertEqual(downloaded['format_id'], 'B')
+
+ ydl = YDL({'format': 'best [filesize = 1000] [width!=450]'})
+ ydl.process_ie_result(info_dict)
+ downloaded = ydl.downloaded_info_dicts[0]
+ self.assertEqual(downloaded['format_id'], 'C')
+
+ ydl = YDL({'format': '[filesize>?1]'})
+ ydl.process_ie_result(info_dict)
+ downloaded = ydl.downloaded_info_dicts[0]
+ self.assertEqual(downloaded['format_id'], 'G')
+
+ ydl = YDL({'format': '[filesize<1M]'})
+ ydl.process_ie_result(info_dict)
+ downloaded = ydl.downloaded_info_dicts[0]
+ self.assertEqual(downloaded['format_id'], 'E')
+
+ ydl = YDL({'format': '[filesize<1MiB]'})
+ ydl.process_ie_result(info_dict)
+ downloaded = ydl.downloaded_info_dicts[0]
+ self.assertEqual(downloaded['format_id'], 'G')
+
def test_add_extra_info(self):
test_dict = {
'extractor': 'Foo',
from youtube_dl.extractor import (
FacebookIE,
gen_extractors,
- TwitchIE,
YoutubeIE,
)
self.assertMatch('http://www.youtube.com/results?search_query=making+mustard', ['youtube:search_url'])
self.assertMatch('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', ['youtube:search_url'])
- def test_twitch_channelid_matching(self):
- self.assertTrue(TwitchIE.suitable('twitch.tv/vanillatv'))
- self.assertTrue(TwitchIE.suitable('www.twitch.tv/vanillatv'))
- self.assertTrue(TwitchIE.suitable('http://www.twitch.tv/vanillatv'))
- self.assertTrue(TwitchIE.suitable('http://www.twitch.tv/vanillatv/'))
-
- def test_twitch_videoid_matching(self):
- self.assertTrue(TwitchIE.suitable('http://www.twitch.tv/vanillatv/b/328087483'))
-
- def test_twitch_chapterid_matching(self):
- self.assertTrue(TwitchIE.suitable('http://www.twitch.tv/tsm_theoddone/c/2349361'))
-
def test_youtube_extract(self):
assertExtractId = lambda url, id: self.assertEqual(YoutubeIE.extract_id(url), id)
assertExtractId('http://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
self.assertMatch(':ythistory', ['youtube:history'])
self.assertMatch(':thedailyshow', ['ComedyCentralShows'])
self.assertMatch(':tds', ['ComedyCentralShows'])
- self.assertMatch(':colbertreport', ['ComedyCentralShows'])
- self.assertMatch(':cr', ['ComedyCentralShows'])
def test_vimeo_matching(self):
self.assertMatch('http://vimeo.com/channels/tributes', ['vimeo:channel'])
for tc in test_cases:
info_dict = tc.get('info_dict', {})
- if not tc.get('file') and not (info_dict.get('id') and info_dict.get('ext')):
+ if not (info_dict.get('id') and info_dict.get('ext')):
raise Exception('Test definition incorrect. The output file cannot be known. Are both \'id\' and \'ext\' keys present?')
if 'skip' in test_case:
expect_warnings(ydl, test_case.get('expected_warnings', []))
def get_tc_filename(tc):
- return tc.get('file') or ydl.prepare_filename(tc.get('info_dict', {}))
+ return ydl.prepare_filename(tc.get('info_dict', {}))
res_dict = None
--- /dev/null
+#!/usr/bin/env python
+from __future__ import unicode_literals
+
+# Allow direct execution
+import os
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from youtube_dl import YoutubeDL
+from youtube_dl.compat import compat_http_server
+import ssl
+import threading
+
+TEST_DIR = os.path.dirname(os.path.abspath(__file__))
+
+
+class HTTPTestRequestHandler(compat_http_server.BaseHTTPRequestHandler):
+ def log_message(self, format, *args):
+ pass
+
+ def do_GET(self):
+ if self.path == '/video.html':
+ self.send_response(200)
+ self.send_header('Content-Type', 'text/html; charset=utf-8')
+ self.end_headers()
+ self.wfile.write(b'<html><video src="/vid.mp4" /></html>')
+ elif self.path == '/vid.mp4':
+ self.send_response(200)
+ self.send_header('Content-Type', 'video/mp4')
+ self.end_headers()
+ self.wfile.write(b'\x00\x00\x00\x00\x20\x66\x74[video]')
+ else:
+ assert False
+
+
+class FakeLogger(object):
+ def debug(self, msg):
+ pass
+
+ def warning(self, msg):
+ pass
+
+ def error(self, msg):
+ pass
+
+
+class TestHTTP(unittest.TestCase):
+ def setUp(self):
+ certfn = os.path.join(TEST_DIR, 'testcert.pem')
+ self.httpd = compat_http_server.HTTPServer(
+ ('localhost', 0), HTTPTestRequestHandler)
+ self.httpd.socket = ssl.wrap_socket(
+ self.httpd.socket, certfile=certfn, server_side=True)
+ self.port = self.httpd.socket.getsockname()[1]
+ self.server_thread = threading.Thread(target=self.httpd.serve_forever)
+ self.server_thread.daemon = True
+ self.server_thread.start()
+
+ def test_nocheckcertificate(self):
+ if sys.version_info >= (2, 7, 9): # No certificate checking anyways
+ ydl = YoutubeDL({'logger': FakeLogger()})
+ self.assertRaises(
+ Exception,
+ ydl.extract_info, 'https://localhost:%d/video.html' % self.port)
+
+ ydl = YoutubeDL({'logger': FakeLogger(), 'nocheckcertificate': True})
+ r = ydl.extract_info('https://localhost:%d/video.html' % self.port)
+ self.assertEqual(r['url'], 'https://localhost:%d/vid.mp4' % self.port)
+
+if __name__ == '__main__':
+ unittest.main()
--- /dev/null
+#!/usr/bin/env python
+
+from __future__ import unicode_literals
+
+# Allow direct execution
+import os
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from youtube_dl.jsinterp import JSInterpreter
+
+
+class TestJSInterpreter(unittest.TestCase):
+ def test_basic(self):
+ jsi = JSInterpreter('function x(){;}')
+ self.assertEqual(jsi.call_function('x'), None)
+
+ jsi = JSInterpreter('function x3(){return 42;}')
+ self.assertEqual(jsi.call_function('x3'), 42)
+
+ def test_calc(self):
+ jsi = JSInterpreter('function x4(a){return 2*a+1;}')
+ self.assertEqual(jsi.call_function('x4', 3), 7)
+
+ def test_empty_return(self):
+ jsi = JSInterpreter('function f(){return; y()}')
+ self.assertEqual(jsi.call_function('f'), None)
+
+ def test_morespace(self):
+ jsi = JSInterpreter('function x (a) { return 2 * a + 1 ; }')
+ self.assertEqual(jsi.call_function('x', 3), 7)
+
+ jsi = JSInterpreter('function f () { x = 2 ; return x; }')
+ self.assertEqual(jsi.call_function('f'), 2)
+
+ def test_strange_chars(self):
+ jsi = JSInterpreter('function $_xY1 ($_axY1) { var $_axY2 = $_axY1 + 1; return $_axY2; }')
+ self.assertEqual(jsi.call_function('$_xY1', 20), 21)
+
+ def test_operators(self):
+ jsi = JSInterpreter('function f(){return 1 << 5;}')
+ self.assertEqual(jsi.call_function('f'), 32)
+
+ jsi = JSInterpreter('function f(){return 19 & 21;}')
+ self.assertEqual(jsi.call_function('f'), 17)
+
+ jsi = JSInterpreter('function f(){return 11 >> 2;}')
+ self.assertEqual(jsi.call_function('f'), 2)
+
+ def test_array_access(self):
+ jsi = JSInterpreter('function f(){var x = [1,2,3]; x[0] = 4; x[0] = 5; x[2] = 7; return x;}')
+ self.assertEqual(jsi.call_function('f'), [5, 2, 7])
+
+ def test_parens(self):
+ jsi = JSInterpreter('function f(){return (1) + (2) * ((( (( (((((3)))))) )) ));}')
+ self.assertEqual(jsi.call_function('f'), 7)
+
+ jsi = JSInterpreter('function f(){return (1 + 2) * 3;}')
+ self.assertEqual(jsi.call_function('f'), 9)
+
+ def test_assignments(self):
+ jsi = JSInterpreter('function f(){var x = 20; x = 30 + 1; return x;}')
+ self.assertEqual(jsi.call_function('f'), 31)
+
+ jsi = JSInterpreter('function f(){var x = 20; x += 30 + 1; return x;}')
+ self.assertEqual(jsi.call_function('f'), 51)
+
+ jsi = JSInterpreter('function f(){var x = 20; x -= 30 + 1; return x;}')
+ self.assertEqual(jsi.call_function('f'), -11)
+
+ def test_comments(self):
+ jsi = JSInterpreter('''
+ function x() {
+ var x = /* 1 + */ 2;
+ var y = /* 30
+ * 40 */ 50;
+ return x + y;
+ }
+ ''')
+ self.assertEqual(jsi.call_function('x'), 52)
+
+ def test_precedence(self):
+ jsi = JSInterpreter('''
+ function x() {
+ var a = [10, 20, 30, 40, 50];
+ var b = 6;
+ a[0]=a[b%a.length];
+ return a;
+ }''')
+ self.assertEqual(jsi.call_function('x'), [20, 20, 30, 40, 50])
+
+
+if __name__ == '__main__':
+ unittest.main()
fix_xml_ampersands,
InAdvancePagedList,
intlist_to_bytes,
+ is_html,
js_to_json,
limit_length,
OnDemandPagedList,
urlencode_postdata,
version_tuple,
xpath_with_ns,
+ render_table,
)
self.assertEqual(
unified_strdate('11/26/2014 11:30:00 AM PST', day_first=False),
'20141126')
+ self.assertEqual(
+ unified_strdate('2/2/2015 6:47:40 PM', day_first=False),
+ '20150202')
def test_find_xpath_attr(self):
testxml = '''<root>
self.assertEqual(parse_duration('5 s'), 5)
self.assertEqual(parse_duration('3 min'), 180)
self.assertEqual(parse_duration('2.5 hours'), 9000)
+ self.assertEqual(parse_duration('02:03:04'), 7384)
+ self.assertEqual(parse_duration('01:02:03:04'), 93784)
def test_fix_xml_ampersands(self):
self.assertEqual(
on = js_to_json('{"abc": true}')
self.assertEqual(json.loads(on), {'abc': True})
+ # Ignore JavaScript code as well
+ on = js_to_json('''{
+ "x": 1,
+ y: "a",
+ z: some.code
+ }''')
+ d = json.loads(on)
+ self.assertEqual(d['x'], 1)
+ self.assertEqual(d['y'], 'a')
+
def test_clean_html(self):
self.assertEqual(clean_html('a:\nb'), 'a: b')
self.assertEqual(clean_html('a:\n "b"'), 'a: "b"')
self.assertTrue(age_restricted(18, 14))
self.assertFalse(age_restricted(18, 18))
+ def test_is_html(self):
+ self.assertFalse(is_html(b'\x49\x44\x43<html'))
+ self.assertTrue(is_html(b'<!DOCTYPE foo>\xaaa'))
+ self.assertTrue(is_html( # UTF-8 with BOM
+ b'\xef\xbb\xbf<!DOCTYPE foo>\xaaa'))
+ self.assertTrue(is_html( # UTF-16-LE
+ b'\xff\xfe<\x00h\x00t\x00m\x00l\x00>\x00\xe4\x00'
+ ))
+ self.assertTrue(is_html( # UTF-16-BE
+ b'\xfe\xff\x00<\x00h\x00t\x00m\x00l\x00>\x00\xe4'
+ ))
+ self.assertTrue(is_html( # UTF-32-BE
+ b'\x00\x00\xFE\xFF\x00\x00\x00<\x00\x00\x00h\x00\x00\x00t\x00\x00\x00m\x00\x00\x00l\x00\x00\x00>\x00\x00\x00\xe4'))
+ self.assertTrue(is_html( # UTF-32-LE
+ b'\xFF\xFE\x00\x00<\x00\x00\x00h\x00\x00\x00t\x00\x00\x00m\x00\x00\x00l\x00\x00\x00>\x00\x00\x00\xe4\x00\x00\x00'))
+
+ def test_render_table(self):
+ self.assertEqual(
+ render_table(
+ ['a', 'bcd'],
+ [[123, 4], [9999, 51]]),
+ 'a bcd\n'
+ '123 4\n'
+ '9999 51')
+
+
if __name__ == '__main__':
unittest.main()
--- /dev/null
+-----BEGIN PRIVATE KEY-----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+-----END PRIVATE KEY-----
+-----BEGIN CERTIFICATE-----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+-----END CERTIFICATE-----
\f[C]
\-\-playlist\-start\ NUMBER\ \ \ \ \ \ \ \ \ \ playlist\ video\ to\ start\ at\ (default\ is\ 1)
\-\-playlist\-end\ NUMBER\ \ \ \ \ \ \ \ \ \ \ \ playlist\ video\ to\ end\ at\ (default\ is\ last)
+\-\-playlist\-items\ ITEM_SPEC\ \ \ \ \ \ \ playlist\ video\ items\ to\ download.\ Specify
+\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ indices\ of\ the\ videos\ in\ the\ playlist
+\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ seperated\ by\ commas\ like:\ "\-\-playlist\-items
+\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ 1,2,5,8"\ if\ you\ want\ to\ download\ videos
+\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ indexed\ 1,\ 2,\ 5,\ 8\ in\ the\ playlist.\ You\ can
+\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ specify\ range:\ "\-\-playlist\-items
+\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ 1\-3,7,10\-13",\ it\ will\ download\ the\ videos
+\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ at\ index\ 1,\ 2,\ 3,\ 7,\ 10,\ 11,\ 12\ and\ 13.
\-\-match\-title\ REGEX\ \ \ \ \ \ \ \ \ \ \ \ \ \ download\ only\ matching\ titles\ (regex\ or
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ caseless\ sub\-string)
\-\-reject\-title\ REGEX\ \ \ \ \ \ \ \ \ \ \ \ \ skip\ download\ for\ matching\ titles\ (regex\ or
\f[C]
\-r,\ \-\-rate\-limit\ LIMIT\ \ \ \ \ \ \ \ \ \ \ maximum\ download\ rate\ in\ bytes\ per\ second
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ (e.g.\ 50K\ or\ 4.2M)
-\-R,\ \-\-retries\ RETRIES\ \ \ \ \ \ \ \ \ \ \ \ number\ of\ retries\ (default\ is\ 10)
+\-R,\ \-\-retries\ RETRIES\ \ \ \ \ \ \ \ \ \ \ \ number\ of\ retries\ (default\ is\ 10),\ or
+\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ "infinite".
\-\-buffer\-size\ SIZE\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ size\ of\ download\ buffer\ (e.g.\ 1024\ or\ 16K)
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ (default\ is\ 1024)
\-\-no\-resize\-buffer\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ do\ not\ automatically\ adjust\ the\ buffer
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ automatically\ resized\ from\ an\ initial\ value
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ of\ SIZE.
\-\-playlist\-reverse\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Download\ playlist\ videos\ in\ reverse\ order
+\-\-xattr\-set\-filesize\ \ \ \ \ \ \ \ \ \ \ \ \ (experimental)\ set\ file\ xattribute
+\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ ytdl.filesize\ with\ expected\ filesize
+\-\-external\-downloader\ COMMAND\ \ \ \ (experimental)\ Use\ the\ specified\ external
+\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ downloader.\ Currently\ supports
+\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ aria2c,curl,wget
\f[]
.fi
.SS Filesystem Options:
\-\-write\-info\-json\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ write\ video\ metadata\ to\ a\ .info.json\ file
\-\-write\-annotations\ \ \ \ \ \ \ \ \ \ \ \ \ \ write\ video\ annotations\ to\ a\ .annotation
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ file
-\-\-write\-thumbnail\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ write\ thumbnail\ image\ to\ disk
\-\-load\-info\ FILE\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ json\ file\ containing\ the\ video\ information
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ (created\ with\ the\ "\-\-write\-json"\ option)
\-\-cookies\ FILE\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ file\ to\ read\ cookies\ from\ and\ dump\ cookie
\-\-rm\-cache\-dir\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Delete\ all\ filesystem\ cache\ files
\f[]
.fi
+.SS Thumbnail images:
+.IP
+.nf
+\f[C]
+\-\-write\-thumbnail\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ write\ thumbnail\ image\ to\ disk
+\-\-write\-all\-thumbnails\ \ \ \ \ \ \ \ \ \ \ write\ all\ thumbnail\ image\ formats\ to\ disk
+\-\-list\-thumbnails\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Simulate\ and\ list\ all\ available\ thumbnail
+\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ formats
+\f[]
+.fi
.SS Verbosity / Simulation Options:
.IP
.nf
\-\-bidi\-workaround\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Work\ around\ terminals\ that\ lack
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ bidirectional\ text\ support.\ Requires\ bidiv
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ or\ fribidi\ executable\ in\ PATH
+\-\-sleep\-interval\ SECONDS\ \ \ \ \ \ \ \ \ Number\ of\ seconds\ to\ sleep\ before\ each
+\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ download.
\f[]
.fi
.SS Video Format Options:
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ by\ extension\ for\ the\ extensions\ aac,\ m4a,
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ mp3,\ mp4,\ ogg,\ wav,\ webm.\ You\ can\ also\ use
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ the\ special\ names\ "best",\ "bestvideo",
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ "bestaudio",\ "worst".\ \ By\ default,\ youtube\-
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ dl\ will\ pick\ the\ best\ quality.\ Use\ commas
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ to\ download\ multiple\ audio\ formats,\ such\ as
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \-f
+\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ "bestaudio",\ "worst".\ \ You\ can\ filter\ the
+\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ video\ results\ by\ putting\ a\ condition\ in
+\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ brackets,\ as\ in\ \-f\ "best[height=720]"\ (or
+\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \-f\ "[filesize>10M]").\ \ This\ works\ for
+\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ filesize,\ height,\ width,\ tbr,\ abr,\ vbr,\ and
+\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ fps\ and\ the\ comparisons\ <,\ <=,\ >,\ >=,\ =,\ !=
+\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ .\ Formats\ for\ which\ the\ value\ is\ not\ known
+\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ are\ excluded\ unless\ you\ put\ a\ question\ mark
+\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ (?)\ after\ the\ operator.\ You\ can\ combine
+\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ format\ filters,\ so\ \ \-f\ "[height\ <=?
+\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ 720][tbr>500]"\ selects\ up\ to\ 720p\ videos
+\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ (or\ videos\ where\ the\ height\ is\ not\ known)
+\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ with\ a\ bitrate\ of\ at\ least\ 500\ KBit/s.\ By
+\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ default,\ youtube\-dl\ will\ pick\ the\ best
+\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ quality.\ Use\ commas\ to\ download\ multiple
+\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ audio\ formats,\ such\ as\ \-f
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ 136/137/mp4/bestvideo,140/m4a/bestaudio.
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ You\ can\ merge\ the\ video\ and\ audio\ of\ two
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ formats\ into\ a\ single\ file\ using\ \-f\ <video\-
.nf
\f[C]
\-u,\ \-\-username\ USERNAME\ \ \ \ \ \ \ \ \ \ login\ with\ this\ account\ ID
-\-p,\ \-\-password\ PASSWORD\ \ \ \ \ \ \ \ \ \ account\ password
+\-p,\ \-\-password\ PASSWORD\ \ \ \ \ \ \ \ \ \ account\ password.\ If\ this\ option\ is\ left
+\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ out,\ youtube\-dl\ will\ ask\ interactively.
\-2,\ \-\-twofactor\ TWOFACTOR\ \ \ \ \ \ \ \ two\-factor\ auth\ code
\-n,\ \-\-netrc\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ use\ .netrc\ authentication\ data
\-\-video\-password\ PASSWORD\ \ \ \ \ \ \ \ video\ password\ (vimeo,\ smotri)
\-\-add\-metadata\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ write\ metadata\ to\ the\ video\ file
\-\-xattrs\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ write\ metadata\ to\ the\ video\ file\[aq]s\ xattrs
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ (using\ dublin\ core\ and\ xdg\ standards)
-\-\-fixup\ POLICY\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ (experimental)\ Automatically\ correct\ known
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ faults\ of\ the\ file.\ One\ of\ never\ (do
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ nothing),\ warn\ (only\ emit\ a\ warning),
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ detect_or_warn(check\ whether\ we\ can\ do
-\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ anything\ about\ it,\ warn\ otherwise
+\-\-fixup\ POLICY\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Automatically\ correct\ known\ faults\ of\ the
+\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ file.\ One\ of\ never\ (do\ nothing),\ warn\ (only
+\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ emit\ a\ warning),\ detect_or_warn(the
+\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ default;\ fix\ file\ if\ we\ can,\ warn
+\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ otherwise)
\-\-prefer\-avconv\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Prefer\ avconv\ over\ ffmpeg\ for\ running\ the
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ postprocessors\ (default)
\-\-prefer\-ffmpeg\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Prefer\ ffmpeg\ over\ avconv\ for\ running\ the
both youtube\-dl and ffmpeg (and youtube\-dl will be able to find
ffmpeg) by simply typing \f[C]youtube\-dl\f[] or \f[C]ffmpeg\f[], no
matter what directory you\[aq]re in.
+.SS How do I put downloads into a specific folder?
+.PP
+Use the \f[C]\-o\f[] to specify an output template (#output-template),
+for example \f[C]\-o\ "/home/user/videos/%(title)s\-%(id)s.%(ext)s"\f[].
+If you want this for all of your downloads, put the option into your
+configuration file (#configuration).
+.SS How do I download a video starting with a \f[C]\-\f[] ?
+.PP
+Either prepend \f[C]http://www.youtube.com/watch?v=\f[] or separate the
+ID from the options with \f[C]\-\-\f[]:
+.IP
+.nf
+\f[C]
+youtube\-dl\ \-\-\ \-wNyEUrxzFU
+youtube\-dl\ "http://www.youtube.com/watch?v=\-wNyEUrxzFU"
+\f[]
+.fi
+.SS Can you add support for this anime video site, or site which shows
+current movies for free?
+.PP
+As a matter of policy (as well as legality), youtube\-dl does not
+include support for services that specialize in infringing copyright.
+As a rule of thumb, if you cannot easily find a video that the service
+is quite obviously allowed to distribute (i.e.
+that has been uploaded by the creator, the creator\[aq]s distributor, or
+is published under a free license), the service is probably unfit for
+inclusion to youtube\-dl.
+.PP
+A note on the service that they don\[aq]t host the infringing content,
+but just link to those who do, is evidence that the service should
+\f[B]not\f[] be included into youtube\-dl.
+The same goes for any DMCA note when the whole front page of the service
+is filled with videos they are not allowed to distribute.
+A "fair use" note is equally unconvincing if the service shows
+copyright\-protected videos in full without authorization.
+.PP
+Support requests for services that \f[B]do\f[] purchase the rights to
+distribute their content are perfectly fine though.
+If in doubt, you can simply include a source that mentions the
+legitimate purchase of content.
.SS How can I detect whether a given URL is supported by youtube\-dl?
.PP
For one, have a look at the list of supported
-sites (docs/supportedsites).
+sites (docs/supportedsites.md).
Note that it can sometimes happen that the site changes its URL scheme
(say, from http://example.com/v/1234567 to http://example.com/v/1234567
) and youtube\-dl reports an URL of a service in that list as
Add tests and code for as many as you want.
.IP " 8." 4
If you can, check the code with
-pyflakes (https://pypi.python.org/pypi/pyflakes) (a good idea) and
-pep8 (https://pypi.python.org/pypi/pep8) (optional, ignore E501).
+flake8 (https://pypi.python.org/pypi/flake8).
.IP " 9." 4
When the tests pass, add (http://git-scm.com/docs/git-add) the new files
and commit (http://git-scm.com/docs/git-commit) them and
video service.
.SS Is anyone going to need the feature?
.PP
-Only post features that you (or an incapicated friend you can personally
-talk to) require.
+Only post features that you (or an incapacitated friend you can
+personally talk to) require.
Do not post features because they seem like a good idea.
If they are really useful, they will be requested by someone who
requires them.
COMPREPLY=()
cur="${COMP_WORDS[COMP_CWORD]}"
prev="${COMP_WORDS[COMP_CWORD-1]}"
- opts="--help --version --update --ignore-errors --abort-on-error --dump-user-agent --list-extractors --extractor-descriptions --default-search --ignore-config --flat-playlist --proxy --socket-timeout --source-address --force-ipv4 --force-ipv6 --playlist-start --playlist-end --match-title --reject-title --max-downloads --min-filesize --max-filesize --date --datebefore --dateafter --min-views --max-views --no-playlist --age-limit --download-archive --include-ads --rate-limit --retries --buffer-size --no-resize-buffer --test --playlist-reverse --batch-file --id --output --autonumber-size --restrict-filenames --auto-number --title --literal --no-overwrites --continue --no-continue --no-part --no-mtime --write-description --write-info-json --write-annotations --write-thumbnail --load-info --cookies --cache-dir --no-cache-dir --rm-cache-dir --quiet --no-warnings --simulate --skip-download --get-url --get-title --get-id --get-thumbnail --get-description --get-duration --get-filename --get-format --dump-json --dump-single-json --print-json --newline --no-progress --console-title --verbose --dump-intermediate-pages --write-pages --youtube-print-sig-code --print-traffic --call-home --no-call-home --encoding --no-check-certificate --prefer-insecure --user-agent --referer --add-header --bidi-workaround --format --all-formats --prefer-free-formats --max-quality --list-formats --youtube-include-dash-manifest --youtube-skip-dash-manifest --merge-output-format --write-sub --write-auto-sub --all-subs --list-subs --sub-format --sub-lang --username --password --twofactor --netrc --video-password --extract-audio --audio-format --audio-quality --recode-video --keep-video --no-post-overwrites --embed-subs --embed-thumbnail --add-metadata --xattrs --fixup --prefer-avconv --prefer-ffmpeg --exec"
+ opts="--help --version --update --ignore-errors --abort-on-error --dump-user-agent --list-extractors --extractor-descriptions --default-search --ignore-config --flat-playlist --proxy --socket-timeout --source-address --force-ipv4 --force-ipv6 --playlist-start --playlist-end --playlist-items --match-title --reject-title --max-downloads --min-filesize --max-filesize --date --datebefore --dateafter --min-views --max-views --no-playlist --age-limit --download-archive --include-ads --rate-limit --retries --buffer-size --no-resize-buffer --test --playlist-reverse --xattr-set-filesize --external-downloader --batch-file --id --output --autonumber-size --restrict-filenames --auto-number --title --literal --no-overwrites --continue --no-continue --no-part --no-mtime --write-description --write-info-json --write-annotations --load-info --cookies --cache-dir --no-cache-dir --rm-cache-dir --write-thumbnail --write-all-thumbnails --list-thumbnails --quiet --no-warnings --simulate --skip-download --get-url --get-title --get-id --get-thumbnail --get-description --get-duration --get-filename --get-format --dump-json --dump-single-json --print-json --newline --no-progress --console-title --verbose --dump-intermediate-pages --write-pages --youtube-print-sig-code --print-traffic --call-home --no-call-home --encoding --no-check-certificate --prefer-insecure --user-agent --referer --add-header --bidi-workaround --sleep-interval --format --all-formats --prefer-free-formats --max-quality --list-formats --youtube-include-dash-manifest --youtube-skip-dash-manifest --merge-output-format --write-sub --write-auto-sub --all-subs --list-subs --sub-format --sub-lang --username --password --twofactor --netrc --video-password --extract-audio --audio-format --audio-quality --recode-video --keep-video --no-post-overwrites --embed-subs --embed-thumbnail --add-metadata --xattrs --fixup --prefer-avconv --prefer-ffmpeg --exec"
keywords=":ytfavorites :ytrecommended :ytsubscriptions :ytwatchlater :ythistory"
fileopts="-a|--batch-file|--download-archive|--cookies|--load-info"
diropts="--cache-dir"
complete --command youtube-dl --long-option force-ipv6 --short-option 6 --description 'Make all connections via IPv6 (experimental)'
complete --command youtube-dl --long-option playlist-start --description 'playlist video to start at (default is %default)'
complete --command youtube-dl --long-option playlist-end --description 'playlist video to end at (default is last)'
+complete --command youtube-dl --long-option playlist-items --description 'playlist video items to download. Specify indices of the videos in the playlist seperated by commas like: "--playlist-items 1,2,5,8" if you want to download videos indexed 1, 2, 5, 8 in the playlist. You can specify range: "--playlist-items 1-3,7,10-13", it will download the videos at index 1, 2, 3, 7, 10, 11, 12 and 13.'
complete --command youtube-dl --long-option match-title --description 'download only matching titles (regex or caseless sub-string)'
complete --command youtube-dl --long-option reject-title --description 'skip download for matching titles (regex or caseless sub-string)'
complete --command youtube-dl --long-option max-downloads --description 'Abort after downloading NUMBER files'
complete --command youtube-dl --long-option download-archive --description 'Download only videos not listed in the archive file. Record the IDs of all downloaded videos in it.' --require-parameter
complete --command youtube-dl --long-option include-ads --description 'Download advertisements as well (experimental)'
complete --command youtube-dl --long-option rate-limit --short-option r --description 'maximum download rate in bytes per second (e.g. 50K or 4.2M)'
-complete --command youtube-dl --long-option retries --short-option R --description 'number of retries (default is %default)'
+complete --command youtube-dl --long-option retries --short-option R --description 'number of retries (default is %default), or "infinite".'
complete --command youtube-dl --long-option buffer-size --description 'size of download buffer (e.g. 1024 or 16K) (default is %default)'
complete --command youtube-dl --long-option no-resize-buffer --description 'do not automatically adjust the buffer size. By default, the buffer size is automatically resized from an initial value of SIZE.'
complete --command youtube-dl --long-option test
complete --command youtube-dl --long-option playlist-reverse --description 'Download playlist videos in reverse order'
+complete --command youtube-dl --long-option xattr-set-filesize --description '(experimental) set file xattribute ytdl.filesize with expected filesize'
+complete --command youtube-dl --long-option external-downloader --description '(experimental) Use the specified external downloader. Currently supports aria2c,curl,wget'
complete --command youtube-dl --long-option batch-file --short-option a --description 'file containing URLs to download ('"'"'-'"'"' for stdin)' --require-parameter
complete --command youtube-dl --long-option id --description 'use only video ID in file name'
complete --command youtube-dl --long-option output --short-option o --description 'output filename template. Use %(title)s to get the title, %(uploader)s for the uploader name, %(uploader_id)s for the uploader nickname if different, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, %(format)s for the format description (like "22 - 1280x720" or "HD"), %(format_id)s for the unique id of the format (like Youtube'"'"'s itags: "137"), %(upload_date)s for the upload date (YYYYMMDD), %(extractor)s for the provider (youtube, metacafe, etc), %(id)s for the video id, %(playlist_title)s, %(playlist_id)s, or %(playlist)s (=title if present, ID otherwise) for the playlist the video is in, %(playlist_index)s for the position in the playlist. %(height)s and %(width)s for the width and height of the video format. %(resolution)s for a textual description of the resolution of the video format. %% for a literal percent. Use - to output to stdout. Can also be used to download to a different directory, for example with -o '"'"'/my/downloads/%(uploader)s/%(title)s-%(id)s.%(ext)s'"'"' .'
complete --command youtube-dl --long-option write-description --description 'write video description to a .description file'
complete --command youtube-dl --long-option write-info-json --description 'write video metadata to a .info.json file'
complete --command youtube-dl --long-option write-annotations --description 'write video annotations to a .annotation file'
-complete --command youtube-dl --long-option write-thumbnail --description 'write thumbnail image to disk'
complete --command youtube-dl --long-option load-info --description 'json file containing the video information (created with the "--write-json" option)' --require-parameter
complete --command youtube-dl --long-option cookies --description 'file to read cookies from and dump cookie jar in' --require-parameter
complete --command youtube-dl --long-option cache-dir --description 'Location in the filesystem where youtube-dl can store some downloaded information permanently. By default $XDG_CACHE_HOME/youtube-dl or ~/.cache/youtube-dl . At the moment, only YouTube player files (for videos with obfuscated signatures) are cached, but that may change.'
complete --command youtube-dl --long-option no-cache-dir --description 'Disable filesystem caching'
complete --command youtube-dl --long-option rm-cache-dir --description 'Delete all filesystem cache files'
+complete --command youtube-dl --long-option write-thumbnail --description 'write thumbnail image to disk'
+complete --command youtube-dl --long-option write-all-thumbnails --description 'write all thumbnail image formats to disk'
+complete --command youtube-dl --long-option list-thumbnails --description 'Simulate and list all available thumbnail formats'
complete --command youtube-dl --long-option quiet --short-option q --description 'activates quiet mode'
complete --command youtube-dl --long-option no-warnings --description 'Ignore warnings'
complete --command youtube-dl --long-option simulate --short-option s --description 'do not download the video and do not write anything to disk'
complete --command youtube-dl --long-option referer --description 'specify a custom referer, use if the video access is restricted to one domain'
complete --command youtube-dl --long-option add-header --description 'specify a custom HTTP header and its value, separated by a colon '"'"':'"'"'. You can use this option multiple times'
complete --command youtube-dl --long-option bidi-workaround --description 'Work around terminals that lack bidirectional text support. Requires bidiv or fribidi executable in PATH'
-complete --command youtube-dl --long-option format --short-option f --description 'video format code, specify the order of preference using slashes, as in -f 22/17/18 . Instead of format codes, you can select by extension for the extensions aac, m4a, mp3, mp4, ogg, wav, webm. You can also use the special names "best", "bestvideo", "bestaudio", "worst". By default, youtube-dl will pick the best quality. Use commas to download multiple audio formats, such as -f 136/137/mp4/bestvideo,140/m4a/bestaudio. You can merge the video and audio of two formats into a single file using -f <video-format>+<audio-format> (requires ffmpeg or avconv), for example -f bestvideo+bestaudio.'
+complete --command youtube-dl --long-option sleep-interval --description 'Number of seconds to sleep before each download.'
+complete --command youtube-dl --long-option format --short-option f --description 'video format code, specify the order of preference using slashes, as in -f 22/17/18 . Instead of format codes, you can select by extension for the extensions aac, m4a, mp3, mp4, ogg, wav, webm. You can also use the special names "best", "bestvideo", "bestaudio", "worst". You can filter the video results by putting a condition in brackets, as in -f "best[height=720]" (or -f "[filesize>10M]"). This works for filesize, height, width, tbr, abr, vbr, and fps and the comparisons <, <=, >, >=, =, != . Formats for which the value is not known are excluded unless you put a question mark (?) after the operator. You can combine format filters, so -f "[height <=? 720][tbr>500]" selects up to 720p videos (or videos where the height is not known) with a bitrate of at least 500 KBit/s. By default, youtube-dl will pick the best quality. Use commas to download multiple audio formats, such as -f 136/137/mp4/bestvideo,140/m4a/bestaudio. You can merge the video and audio of two formats into a single file using -f <video-format>+<audio-format> (requires ffmpeg or avconv), for example -f bestvideo+bestaudio.'
complete --command youtube-dl --long-option all-formats --description 'download all available video formats'
complete --command youtube-dl --long-option prefer-free-formats --description 'prefer free video formats unless a specific one is requested'
complete --command youtube-dl --long-option max-quality --description 'highest quality format to download'
complete --command youtube-dl --long-option sub-format --description 'subtitle format (default=srt) ([sbv/vtt] youtube only)'
complete --command youtube-dl --long-option sub-lang --description 'languages of the subtitles to download (optional) separated by commas, use IETF language tags like '"'"'en,pt'"'"''
complete --command youtube-dl --long-option username --short-option u --description 'login with this account ID'
-complete --command youtube-dl --long-option password --short-option p --description 'account password'
+complete --command youtube-dl --long-option password --short-option p --description 'account password. If this option is left out, youtube-dl will ask interactively.'
complete --command youtube-dl --long-option twofactor --short-option 2 --description 'two-factor auth code'
complete --command youtube-dl --long-option netrc --short-option n --description 'use .netrc authentication data'
complete --command youtube-dl --long-option video-password --description 'video password (vimeo, smotri)'
complete --command youtube-dl --long-option embed-thumbnail --description 'embed thumbnail in the audio as cover art'
complete --command youtube-dl --long-option add-metadata --description 'write metadata to the video file'
complete --command youtube-dl --long-option xattrs --description 'write metadata to the video file'"'"'s xattrs (using dublin core and xdg standards)'
-complete --command youtube-dl --long-option fixup --description '(experimental) Automatically correct known faults of the file. One of never (do nothing), warn (only emit a warning), detect_or_warn(check whether we can do anything about it, warn otherwise'
+complete --command youtube-dl --long-option fixup --description 'Automatically correct known faults of the file. One of never (do nothing), warn (only emit a warning), detect_or_warn(the default; fix file if we can, warn otherwise)'
complete --command youtube-dl --long-option prefer-avconv --description 'Prefer avconv over ffmpeg for running the postprocessors (default)'
complete --command youtube-dl --long-option prefer-ffmpeg --description 'Prefer ffmpeg over avconv for running the postprocessors'
complete --command youtube-dl --long-option exec --description 'Execute a command on the file after downloading, similar to find'"'"'s -exec syntax. Example: --exec '"'"'adb push {} /sdcard/Music/ && rm {}'"'"''
elif [[ ${prev} == "--recode-video" ]]; then
_arguments '*: :(mp4 flv ogg webm mkv)'
else
- _arguments '*: :(--help --version --update --ignore-errors --abort-on-error --dump-user-agent --list-extractors --extractor-descriptions --default-search --ignore-config --flat-playlist --proxy --socket-timeout --source-address --force-ipv4 --force-ipv6 --playlist-start --playlist-end --match-title --reject-title --max-downloads --min-filesize --max-filesize --date --datebefore --dateafter --min-views --max-views --no-playlist --age-limit --download-archive --include-ads --rate-limit --retries --buffer-size --no-resize-buffer --test --playlist-reverse --batch-file --id --output --autonumber-size --restrict-filenames --auto-number --title --literal --no-overwrites --continue --no-continue --no-part --no-mtime --write-description --write-info-json --write-annotations --write-thumbnail --load-info --cookies --cache-dir --no-cache-dir --rm-cache-dir --quiet --no-warnings --simulate --skip-download --get-url --get-title --get-id --get-thumbnail --get-description --get-duration --get-filename --get-format --dump-json --dump-single-json --print-json --newline --no-progress --console-title --verbose --dump-intermediate-pages --write-pages --youtube-print-sig-code --print-traffic --call-home --no-call-home --encoding --no-check-certificate --prefer-insecure --user-agent --referer --add-header --bidi-workaround --format --all-formats --prefer-free-formats --max-quality --list-formats --youtube-include-dash-manifest --youtube-skip-dash-manifest --merge-output-format --write-sub --write-auto-sub --all-subs --list-subs --sub-format --sub-lang --username --password --twofactor --netrc --video-password --extract-audio --audio-format --audio-quality --recode-video --keep-video --no-post-overwrites --embed-subs --embed-thumbnail --add-metadata --xattrs --fixup --prefer-avconv --prefer-ffmpeg --exec)'
+ _arguments '*: :(--help --version --update --ignore-errors --abort-on-error --dump-user-agent --list-extractors --extractor-descriptions --default-search --ignore-config --flat-playlist --proxy --socket-timeout --source-address --force-ipv4 --force-ipv6 --playlist-start --playlist-end --playlist-items --match-title --reject-title --max-downloads --min-filesize --max-filesize --date --datebefore --dateafter --min-views --max-views --no-playlist --age-limit --download-archive --include-ads --rate-limit --retries --buffer-size --no-resize-buffer --test --playlist-reverse --xattr-set-filesize --external-downloader --batch-file --id --output --autonumber-size --restrict-filenames --auto-number --title --literal --no-overwrites --continue --no-continue --no-part --no-mtime --write-description --write-info-json --write-annotations --load-info --cookies --cache-dir --no-cache-dir --rm-cache-dir --write-thumbnail --write-all-thumbnails --list-thumbnails --quiet --no-warnings --simulate --skip-download --get-url --get-title --get-id --get-thumbnail --get-description --get-duration --get-filename --get-format --dump-json --dump-single-json --print-json --newline --no-progress --console-title --verbose --dump-intermediate-pages --write-pages --youtube-print-sig-code --print-traffic --call-home --no-call-home --encoding --no-check-certificate --prefer-insecure --user-agent --referer --add-header --bidi-workaround --sleep-interval --format --all-formats --prefer-free-formats --max-quality --list-formats --youtube-include-dash-manifest --youtube-skip-dash-manifest --merge-output-format --write-sub --write-auto-sub --all-subs --list-subs --sub-format --sub-lang --username --password --twofactor --netrc --video-password --extract-audio --audio-format --audio-quality --recode-video --keep-video --no-post-overwrites --embed-subs --embed-thumbnail --add-metadata --xattrs --fixup --prefer-avconv --prefer-ffmpeg --exec)'
fi
;;
esac
import itertools
import json
import locale
+import operator
import os
import platform
import re
import ctypes
from .compat import (
+ compat_basestring,
compat_cookiejar,
compat_expanduser,
compat_http_client,
make_HTTPS_handler,
MaxDownloadsReached,
PagedList,
+ parse_filesize,
PostProcessingError,
platform_name,
preferredencoding,
+ render_table,
SameFileError,
sanitize_filename,
+ std_headers,
subtitles_filename,
takewhile_inclusive,
UnavailableVideoError,
from .downloader import get_suitable_downloader
from .downloader.rtmp import rtmpdump_version
from .postprocessor import (
+ FFmpegFixupM4aPP,
FFmpegFixupStretchedPP,
FFmpegMergerPP,
FFmpegPostProcessor,
nooverwrites: Prevent overwriting files.
playliststart: Playlist item to start at.
playlistend: Playlist item to end at.
+ playlist_items: Specific indices of playlist to download.
playlistreverse: Download playlist items in reverse order.
matchtitle: Download only matching titles.
rejecttitle: Reject downloads for matching titles.
writeinfojson: Write the video description to a .info.json file
writeannotations: Write the video annotations to a .annotations.xml file
writethumbnail: Write the thumbnail image to a file
+ write_all_thumbnails: Write all thumbnail formats to files
writesubtitles: Write the video subtitles to a file
writeautomaticsub: Write the automatic subtitles to a file
allsubtitles: Downloads all the subtitles of the video
postprocessor.
progress_hooks: A list of functions that get called on download
progress, with a dictionary with the entries
- * filename: The final filename
- * status: One of "downloading" and "finished"
-
- The dict may also have some of the following entries:
+ * status: One of "downloading" and "finished".
+ Check this first and ignore unknown values.
+ If status is one of "downloading" or "finished", the
+ following properties may also be present:
+ * filename: The final filename (always present)
* downloaded_bytes: Bytes on disk
* total_bytes: Size of the whole file, None if unknown
* tmpfilename: The filename we're currently writing to
- "never": do nothing
- "warn": only emit a warning
- "detect_or_warn": check whether we can do anything
- about it, warn otherwise
+ about it, warn otherwise (default)
source_address: (Experimental) Client-side IP address to bind to.
call_home: Boolean, true iff we are allowed to contact the
youtube-dl servers for debugging.
+ sleep_interval: Number of seconds to sleep before each download.
+ external_downloader: Executable of the external downloader to call.
+ listformats: Print an overview of available video formats and exit.
+ list_thumbnails: Print a table of all thumbnails and exit.
The following parameters are not used by YoutubeDL itself, they are used by
the FileDownloader:
nopart, updatetime, buffersize, ratelimit, min_filesize, max_filesize, test,
- noresizebuffer, retries, continuedl, noprogress, consoletitle
+ noresizebuffer, retries, continuedl, noprogress, consoletitle,
+ xattr_set_filesize.
The following options are used by the post processors:
prefer_ffmpeg: If True, use ffmpeg instead of avconv if both are available,
outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
tmpl = compat_expanduser(outtmpl)
filename = tmpl % template_dict
+ # Temporary fix for #4787
+ # 'Treat' all problem characters by passing filename through preferredencoding
+ # to workaround encoding issues with subprocess on python2 @ Windows
+ if sys.version_info < (3, 0) and sys.platform == 'win32':
+ filename = encodeFilename(filename, True).decode(preferredencoding())
return filename
except ValueError as err:
self.report_error('Error in output template: ' + str(err) + ' (encoding: ' + repr(preferredencoding()) + ')')
if playlistend == -1:
playlistend = None
+ playlistitems_str = self.params.get('playlist_items', None)
+ playlistitems = None
+ if playlistitems_str is not None:
+ def iter_playlistitems(format):
+ for string_segment in format.split(','):
+ if '-' in string_segment:
+ start, end = string_segment.split('-')
+ for item in range(int(start), int(end) + 1):
+ yield int(item)
+ else:
+ yield int(string_segment)
+ playlistitems = iter_playlistitems(playlistitems_str)
+
ie_entries = ie_result['entries']
if isinstance(ie_entries, list):
n_all_entries = len(ie_entries)
- entries = ie_entries[playliststart:playlistend]
+ if playlistitems:
+ entries = [ie_entries[i - 1] for i in playlistitems]
+ else:
+ entries = ie_entries[playliststart:playlistend]
n_entries = len(entries)
self.to_screen(
"[%s] playlist %s: Collected %d video ids (downloading %d of them)" %
(ie_result['extractor'], playlist, n_all_entries, n_entries))
elif isinstance(ie_entries, PagedList):
- entries = ie_entries.getslice(
- playliststart, playlistend)
+ if playlistitems:
+ entries = []
+ for item in playlistitems:
+ entries.extend(ie_entries.getslice(
+ item - 1, item
+ ))
+ else:
+ entries = ie_entries.getslice(
+ playliststart, playlistend)
n_entries = len(entries)
self.to_screen(
"[%s] playlist %s: Downloading %d videos" %
(ie_result['extractor'], playlist, n_entries))
else: # iterable
- entries = list(itertools.islice(
- ie_entries, playliststart, playlistend))
+ if playlistitems:
+ entry_list = list(ie_entries)
+ entries = [entry_list[i - 1] for i in playlistitems]
+ else:
+ entries = list(itertools.islice(
+ ie_entries, playliststart, playlistend))
n_entries = len(entries)
self.to_screen(
"[%s] playlist %s: Downloading %d videos" %
else:
raise Exception('Invalid result type: %s' % result_type)
+ def _apply_format_filter(self, format_spec, available_formats):
+ " Returns a tuple of the remaining format_spec and filtered formats "
+
+ OPERATORS = {
+ '<': operator.lt,
+ '<=': operator.le,
+ '>': operator.gt,
+ '>=': operator.ge,
+ '=': operator.eq,
+ '!=': operator.ne,
+ }
+ operator_rex = re.compile(r'''(?x)\s*\[
+ (?P<key>width|height|tbr|abr|vbr|filesize|fps)
+ \s*(?P<op>%s)(?P<none_inclusive>\s*\?)?\s*
+ (?P<value>[0-9.]+(?:[kKmMgGtTpPeEzZyY]i?[Bb]?)?)
+ \]$
+ ''' % '|'.join(map(re.escape, OPERATORS.keys())))
+ m = operator_rex.search(format_spec)
+ if not m:
+ raise ValueError('Invalid format specification %r' % format_spec)
+
+ try:
+ comparison_value = int(m.group('value'))
+ except ValueError:
+ comparison_value = parse_filesize(m.group('value'))
+ if comparison_value is None:
+ comparison_value = parse_filesize(m.group('value') + 'B')
+ if comparison_value is None:
+ raise ValueError(
+ 'Invalid value %r in format specification %r' % (
+ m.group('value'), format_spec))
+ op = OPERATORS[m.group('op')]
+
+ def _filter(f):
+ actual_value = f.get(m.group('key'))
+ if actual_value is None:
+ return m.group('none_inclusive')
+ return op(actual_value, comparison_value)
+ new_formats = [f for f in available_formats if _filter(f)]
+
+ new_format_spec = format_spec[:-len(m.group(0))]
+ if not new_format_spec:
+ new_format_spec = 'best'
+
+ return (new_format_spec, new_formats)
+
def select_format(self, format_spec, available_formats):
+ while format_spec.endswith(']'):
+ format_spec, available_formats = self._apply_format_filter(
+ format_spec, available_formats)
+ if not available_formats:
+ return None
+
if format_spec == 'best' or format_spec is None:
return available_formats[-1]
elif format_spec == 'worst':
return matches[-1]
return None
+ def _calc_headers(self, info_dict):
+ res = std_headers.copy()
+
+ add_headers = info_dict.get('http_headers')
+ if add_headers:
+ res.update(add_headers)
+
+ cookies = self._calc_cookies(info_dict)
+ if cookies:
+ res['Cookie'] = cookies
+
+ return res
+
+ def _calc_cookies(self, info_dict):
+ class _PseudoRequest(object):
+ def __init__(self, url):
+ self.url = url
+ self.headers = {}
+ self.unverifiable = False
+
+ def add_unredirected_header(self, k, v):
+ self.headers[k] = v
+
+ def get_full_url(self):
+ return self.url
+
+ def is_unverifiable(self):
+ return self.unverifiable
+
+ def has_header(self, h):
+ return h in self.headers
+
+ pr = _PseudoRequest(info_dict['url'])
+ self.cookiejar.add_cookie_header(pr)
+ return pr.headers.get('Cookie')
+
def process_video_result(self, info_dict, download=True):
assert info_dict.get('_type', 'video') == 'video'
info_dict['playlist_index'] = None
thumbnails = info_dict.get('thumbnails')
+ if thumbnails is None:
+ thumbnail = info_dict.get('thumbnail')
+ if thumbnail:
+ info_dict['thumbnails'] = thumbnails = [{'url': thumbnail}]
if thumbnails:
thumbnails.sort(key=lambda t: (
- t.get('width'), t.get('height'), t.get('url')))
- for t in thumbnails:
+ t.get('preference'), t.get('width'), t.get('height'),
+ t.get('id'), t.get('url')))
+ for i, t in enumerate(thumbnails):
if 'width' in t and 'height' in t:
t['resolution'] = '%dx%d' % (t['width'], t['height'])
+ if t.get('id') is None:
+ t['id'] = '%d' % i
if thumbnails and 'thumbnail' not in info_dict:
info_dict['thumbnail'] = thumbnails[-1]['url']
# Automatically determine file extension if missing
if 'ext' not in format:
format['ext'] = determine_ext(format['url']).lower()
+ # Add HTTP headers, so that external programs can use them from the
+ # json output
+ full_format_info = info_dict.copy()
+ full_format_info.update(format)
+ format['http_headers'] = self._calc_headers(full_format_info)
format_limit = self.params.get('format_limit', None)
if format_limit:
# element in the 'formats' field in info_dict is info_dict itself,
# wich can't be exported to json
info_dict['formats'] = formats
- if self.params.get('listformats', None):
+ if self.params.get('listformats'):
self.list_formats(info_dict)
return
+ if self.params.get('list_thumbnails'):
+ self.list_thumbnails(info_dict)
+ return
req_format = self.params.get('format')
if req_format is None:
else self.params['merge_output_format'])
selected_format = {
'requested_formats': formats_info,
- 'format': rf,
- 'ext': formats_info[0]['ext'],
+ 'format': '%s+%s' % (formats_info[0].get('format'),
+ formats_info[1].get('format')),
+ 'format_id': '%s+%s' % (formats_info[0].get('format_id'),
+ formats_info[1].get('format_id')),
'width': formats_info[0].get('width'),
'height': formats_info[0].get('height'),
'resolution': formats_info[0].get('resolution'),
self._num_downloads += 1
- filename = self.prepare_filename(info_dict)
+ info_dict['_filename'] = filename = self.prepare_filename(info_dict)
# Forced printings
if self.params.get('forcetitle', False):
if self.params.get('forceformat', False):
self.to_stdout(info_dict['format'])
if self.params.get('forcejson', False):
- info_dict['_filename'] = filename
self.to_stdout(json.dumps(info_dict))
- if self.params.get('dump_single_json', False):
- info_dict['_filename'] = filename
# Do nothing else if in simulate mode
if self.params.get('simulate', False):
self.report_error('Cannot write metadata to JSON file ' + infofn)
return
- if self.params.get('writethumbnail', False):
- if info_dict.get('thumbnail') is not None:
- thumb_format = determine_ext(info_dict['thumbnail'], 'jpg')
- thumb_filename = os.path.splitext(filename)[0] + '.' + thumb_format
- if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(thumb_filename)):
- self.to_screen('[%s] %s: Thumbnail is already present' %
- (info_dict['extractor'], info_dict['id']))
- else:
- self.to_screen('[%s] %s: Downloading thumbnail ...' %
- (info_dict['extractor'], info_dict['id']))
- try:
- uf = self.urlopen(info_dict['thumbnail'])
- with open(thumb_filename, 'wb') as thumbf:
- shutil.copyfileobj(uf, thumbf)
- self.to_screen('[%s] %s: Writing thumbnail to: %s' %
- (info_dict['extractor'], info_dict['id'], thumb_filename))
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- self.report_warning('Unable to download thumbnail "%s": %s' %
- (info_dict['thumbnail'], compat_str(err)))
+ self._write_thumbnails(info_dict, filename)
if not self.params.get('skip_download', False):
try:
def dl(name, info):
- fd = get_suitable_downloader(info)(self, self.params)
+ fd = get_suitable_downloader(info, self.params)(self, self.params)
for ph in self._progress_hooks:
fd.add_progress_hook(ph)
if self.params.get('verbose'):
self.to_stdout('[debug] Invoking downloader on %r' % info.get('url'))
return fd.download(name, info)
+
if info_dict.get('requested_formats') is not None:
downloaded = []
success = True
if success:
# Fixup content
+ fixup_policy = self.params.get('fixup')
+ if fixup_policy is None:
+ fixup_policy = 'detect_or_warn'
+
stretched_ratio = info_dict.get('stretched_ratio')
if stretched_ratio is not None and stretched_ratio != 1:
- fixup_policy = self.params.get('fixup')
- if fixup_policy is None:
- fixup_policy = 'detect_or_warn'
if fixup_policy == 'warn':
self.report_warning('%s: Non-uniform pixel ratio (%s)' % (
info_dict['id'], stretched_ratio))
'%s: Non-uniform pixel ratio (%s). Install ffmpeg or avconv to fix this automatically.' % (
info_dict['id'], stretched_ratio))
else:
- assert fixup_policy == 'ignore'
+ assert fixup_policy in ('ignore', 'never')
+
+ if info_dict.get('requested_formats') is None and info_dict.get('container') == 'm4a_dash':
+ if fixup_policy == 'warn':
+ self.report_warning('%s: writing DASH m4a. Only some players support this container.' % (
+ info_dict['id']))
+ elif fixup_policy == 'detect_or_warn':
+ fixup_pp = FFmpegFixupM4aPP(self)
+ if fixup_pp.available:
+ info_dict.setdefault('__postprocessors', [])
+ info_dict['__postprocessors'].append(fixup_pp)
+ else:
+ self.report_warning(
+ '%s: writing DASH m4a. Only some players support this container. Install ffmpeg or avconv to fix this automatically.' % (
+ info_dict['id']))
+ else:
+ assert fixup_policy in ('ignore', 'never')
try:
self.post_process(filename, info_dict)
header_line = line({
'format_id': 'format code', 'ext': 'extension',
'resolution': 'resolution', 'format_note': 'note'}, idlen=idlen)
- self.to_screen('[info] Available formats for %s:\n%s\n%s' %
- (info_dict['id'], header_line, '\n'.join(formats_s)))
+ self.to_screen(
+ '[info] Available formats for %s:\n%s\n%s' %
+ (info_dict['id'], header_line, '\n'.join(formats_s)))
+
+ def list_thumbnails(self, info_dict):
+ thumbnails = info_dict.get('thumbnails')
+ if not thumbnails:
+ tn_url = info_dict.get('thumbnail')
+ if tn_url:
+ thumbnails = [{'id': '0', 'url': tn_url}]
+ else:
+ self.to_screen(
+ '[info] No thumbnails present for %s' % info_dict['id'])
+ return
+
+ self.to_screen(
+ '[info] Thumbnails for %s:' % info_dict['id'])
+ self.to_screen(render_table(
+ ['ID', 'width', 'height', 'URL'],
+ [[t['id'], t.get('width', 'unknown'), t.get('height', 'unknown'), t['url']] for t in thumbnails]))
def urlopen(self, req):
""" Start an HTTP download """
# urllib chokes on URLs with non-ASCII characters (see http://bugs.python.org/issue3991)
# To work around aforementioned issue we will replace request's original URL with
# percent-encoded one
- req_is_string = isinstance(req, basestring if sys.version_info < (3, 0) else compat_str)
+ req_is_string = isinstance(req, compat_basestring)
url = req if req_is_string else req.get_full_url()
url_escaped = escape_url(url)
if encoding is None:
encoding = preferredencoding()
return encoding
+
+ def _write_thumbnails(self, info_dict, filename):
+ if self.params.get('writethumbnail', False):
+ thumbnails = info_dict.get('thumbnails')
+ if thumbnails:
+ thumbnails = [thumbnails[-1]]
+ elif self.params.get('write_all_thumbnails', False):
+ thumbnails = info_dict.get('thumbnails')
+ else:
+ return
+
+ if not thumbnails:
+ # No thumbnails present, so return immediately
+ return
+
+ for t in thumbnails:
+ thumb_ext = determine_ext(t['url'], 'jpg')
+ suffix = '_%s' % t['id'] if len(thumbnails) > 1 else ''
+ thumb_display_id = '%s ' % t['id'] if len(thumbnails) > 1 else ''
+ thumb_filename = os.path.splitext(filename)[0] + suffix + '.' + thumb_ext
+
+ if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(thumb_filename)):
+ self.to_screen('[%s] %s: Thumbnail %sis already present' %
+ (info_dict['extractor'], info_dict['id'], thumb_display_id))
+ else:
+ self.to_screen('[%s] %s: Downloading thumbnail %s...' %
+ (info_dict['extractor'], info_dict['id'], thumb_display_id))
+ try:
+ uf = self.urlopen(t['url'])
+ with open(thumb_filename, 'wb') as thumbf:
+ shutil.copyfileobj(uf, thumbf)
+ self.to_screen('[%s] %s: Writing thumbnail %sto: %s' %
+ (info_dict['extractor'], info_dict['id'], thumb_display_id, thumb_filename))
+ except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ self.report_warning('Unable to download thumbnail "%s": %s' %
+ (t['url'], compat_str(err)))
parser.error('invalid max_filesize specified')
opts.max_filesize = numeric_limit
if opts.retries is not None:
- try:
- opts.retries = int(opts.retries)
- except (TypeError, ValueError):
- parser.error('invalid retry count specified')
+ if opts.retries in ('inf', 'infinite'):
+ opts_retries = float('inf')
+ else:
+ try:
+ opts_retries = int(opts.retries)
+ except (TypeError, ValueError):
+ parser.error('invalid retry count specified')
if opts.buffersize is not None:
numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize)
if numeric_buffersize is None:
'verboseOutput': opts.verbose,
'exec_cmd': opts.exec_cmd,
})
+ if opts.xattr_set_filesize:
+ try:
+ import xattr
+ xattr # Confuse flake8
+ except ImportError:
+ parser.error('setting filesize xattr requested but python-xattr is not available')
ydl_opts = {
'usenetrc': opts.usenetrc,
'ignoreerrors': opts.ignoreerrors,
'ratelimit': opts.ratelimit,
'nooverwrites': opts.nooverwrites,
- 'retries': opts.retries,
+ 'retries': opts_retries,
'buffersize': opts.buffersize,
'noresizebuffer': opts.noresizebuffer,
'continuedl': opts.continue_dl,
'writeannotations': opts.writeannotations,
'writeinfojson': opts.writeinfojson,
'writethumbnail': opts.writethumbnail,
+ 'write_all_thumbnails': opts.write_all_thumbnails,
'writesubtitles': opts.writesubtitles,
'writeautomaticsub': opts.writeautomaticsub,
'allsubtitles': opts.allsubtitles,
'fixup': opts.fixup,
'source_address': opts.source_address,
'call_home': opts.call_home,
+ 'sleep_interval': opts.sleep_interval,
+ 'external_downloader': opts.external_downloader,
+ 'list_thumbnails': opts.list_thumbnails,
+ 'playlist_items': opts.playlist_items,
+ 'xattr_set_filesize': opts.xattr_set_filesize,
}
with YoutubeDL(ydl_opts) as ydl:
sys.exit()
ydl.warn_if_short_id(sys.argv[1:] if argv is None else argv)
- parser.error('you must provide at least one URL')
+ parser.error(
+ 'You must provide at least one URL.\n'
+ 'Type youtube-dl --help to see a list of all options.')
try:
if opts.load_info_filename is not None:
except ImportError:
compat_subprocess_get_DEVNULL = lambda: open(os.path.devnull, 'w')
+try:
+ import http.server as compat_http_server
+except ImportError:
+ import BaseHTTPServer as compat_http_server
+
try:
from urllib.parse import unquote as compat_urllib_parse_unquote
except ImportError:
string += pct_sequence.decode(encoding, errors)
return string
+try:
+ compat_str = unicode # Python 2
+except NameError:
+ compat_str = str
+
+try:
+ compat_basestring = basestring # Python 2
+except NameError:
+ compat_basestring = str
+
+try:
+ compat_chr = unichr # Python 2
+except NameError:
+ compat_chr = chr
+
+try:
+ from xml.etree.ElementTree import ParseError as compat_xml_parse_error
+except ImportError: # Python 2.6
+ from xml.parsers.expat import ExpatError as compat_xml_parse_error
+
try:
from urllib.parse import parse_qs as compat_parse_qs
def _parse_qsl(qs, keep_blank_values=False, strict_parsing=False,
encoding='utf-8', errors='replace'):
- qs, _coerce_result = qs, unicode
+ qs, _coerce_result = qs, compat_str
pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')]
r = []
for name_value in pairs:
parsed_result[name] = [value]
return parsed_result
-try:
- compat_str = unicode # Python 2
-except NameError:
- compat_str = str
-
-try:
- compat_chr = unichr # Python 2
-except NameError:
- compat_chr = chr
-
-try:
- from xml.etree.ElementTree import ParseError as compat_xml_parse_error
-except ImportError: # Python 2.6
- from xml.parsers.expat import ExpatError as compat_xml_parse_error
-
try:
from shlex import quote as shlex_quote
except ImportError: # Python < 3.3
__all__ = [
'compat_HTTPError',
+ 'compat_basestring',
'compat_chr',
'compat_cookiejar',
'compat_expanduser',
'compat_html_entities',
'compat_html_parser',
'compat_http_client',
+ 'compat_http_server',
'compat_kwargs',
'compat_ord',
'compat_parse_qs',
from __future__ import unicode_literals
from .common import FileDownloader
+from .external import get_external_downloader
+from .f4m import F4mFD
from .hls import HlsFD
from .hls import NativeHlsFD
from .http import HttpFD
from .mplayer import MplayerFD
from .rtmp import RtmpFD
-from .f4m import F4mFD
from ..utils import (
- determine_ext,
+ determine_protocol,
)
+PROTOCOL_MAP = {
+ 'rtmp': RtmpFD,
+ 'm3u8_native': NativeHlsFD,
+ 'm3u8': HlsFD,
+ 'mms': MplayerFD,
+ 'rtsp': MplayerFD,
+ 'f4m': F4mFD,
+}
+
-def get_suitable_downloader(info_dict):
+def get_suitable_downloader(info_dict, params={}):
"""Get the downloader class that can handle the info dict."""
- url = info_dict['url']
- protocol = info_dict.get('protocol')
-
- if url.startswith('rtmp'):
- return RtmpFD
- if protocol == 'm3u8_native':
- return NativeHlsFD
- if (protocol == 'm3u8') or (protocol is None and determine_ext(url) == 'm3u8'):
- return HlsFD
- if url.startswith('mms') or url.startswith('rtsp'):
- return MplayerFD
- if determine_ext(url) == 'f4m':
- return F4mFD
- else:
- return HttpFD
+ protocol = determine_protocol(info_dict)
+ info_dict['protocol'] = protocol
+
+ external_downloader = params.get('external_downloader')
+ if external_downloader is not None:
+ ed = get_external_downloader(external_downloader)
+ if ed.supports(info_dict):
+ return ed
+
+ return PROTOCOL_MAP.get(protocol, HttpFD)
+
__all__ = [
'get_suitable_downloader',
Available options:
- verbose: Print additional info to stdout.
- quiet: Do not print messages to stdout.
- ratelimit: Download speed limit, in bytes/sec.
- retries: Number of times to retry for HTTP error 5xx
- buffersize: Size of download buffer in bytes.
- noresizebuffer: Do not automatically resize the download buffer.
- continuedl: Try to continue downloads if possible.
- noprogress: Do not print the progress bar.
- logtostderr: Log messages to stderr instead of stdout.
- consoletitle: Display progress in console window's titlebar.
- nopart: Do not use temporary .part files.
- updatetime: Use the Last-modified header to set output file timestamps.
- test: Download only first bytes to test the downloader.
- min_filesize: Skip files smaller than this size
- max_filesize: Skip files larger than this size
+ verbose: Print additional info to stdout.
+ quiet: Do not print messages to stdout.
+ ratelimit: Download speed limit, in bytes/sec.
+ retries: Number of times to retry for HTTP error 5xx
+ buffersize: Size of download buffer in bytes.
+ noresizebuffer: Do not automatically resize the download buffer.
+ continuedl: Try to continue downloads if possible.
+ noprogress: Do not print the progress bar.
+ logtostderr: Log messages to stderr instead of stdout.
+ consoletitle: Display progress in console window's titlebar.
+ nopart: Do not use temporary .part files.
+ updatetime: Use the Last-modified header to set output file timestamps.
+ test: Download only first bytes to test the downloader.
+ min_filesize: Skip files smaller than this size
+ max_filesize: Skip files larger than this size
+ xattr_set_filesize: Set ytdl.filesize user xattribute with expected size.
+ (experimenatal)
Subclasses of this one must re-define the real_download method.
"""
"""Download to a filename using the info from info_dict
Return True on success and False otherwise
"""
+
nooverwrites_and_exists = (
self.params.get('nooverwrites', False)
and os.path.exists(encodeFilename(filename))
})
return True
+ sleep_interval = self.params.get('sleep_interval')
+ if sleep_interval:
+ self.to_screen('[download] Sleeping %s seconds...' % sleep_interval)
+ time.sleep(sleep_interval)
+
return self.real_download(filename, info_dict)
def real_download(self, filename, info_dict):
# See YoutubeDl.py (search for progress_hooks) for a description of
# this interface
self._progress_hooks.append(ph)
+
+ def _debug_cmd(self, args, subprocess_encoding, exe=None):
+ if not self.params.get('verbose', False):
+ return
+
+ if exe is None:
+ exe = os.path.basename(args[0])
+
+ if subprocess_encoding:
+ str_args = [
+ a.decode(subprocess_encoding) if isinstance(a, bytes) else a
+ for a in args]
+ else:
+ str_args = args
+ try:
+ import pipes
+ shell_quote = lambda args: ' '.join(map(pipes.quote, str_args))
+ except ImportError:
+ shell_quote = repr
+ self.to_screen('[debug] %s command line: %s' % (
+ exe, shell_quote(str_args)))
--- /dev/null
+from __future__ import unicode_literals
+
+import os.path
+import subprocess
+import sys
+
+from .common import FileDownloader
+from ..utils import (
+ encodeFilename,
+)
+
+
+class ExternalFD(FileDownloader):
+ def real_download(self, filename, info_dict):
+ self.report_destination(filename)
+ tmpfilename = self.temp_name(filename)
+
+ retval = self._call_downloader(tmpfilename, info_dict)
+ if retval == 0:
+ fsize = os.path.getsize(encodeFilename(tmpfilename))
+ self.to_screen('\r[%s] Downloaded %s bytes' % (self.get_basename(), fsize))
+ self.try_rename(tmpfilename, filename)
+ self._hook_progress({
+ 'downloaded_bytes': fsize,
+ 'total_bytes': fsize,
+ 'filename': filename,
+ 'status': 'finished',
+ })
+ return True
+ else:
+ self.to_stderr('\n')
+ self.report_error('%s exited with code %d' % (
+ self.get_basename(), retval))
+ return False
+
+ @classmethod
+ def get_basename(cls):
+ return cls.__name__[:-2].lower()
+
+ @property
+ def exe(self):
+ return self.params.get('external_downloader')
+
+ @classmethod
+ def supports(cls, info_dict):
+ return info_dict['protocol'] in ('http', 'https', 'ftp', 'ftps')
+
+ def _source_address(self, command_option):
+ source_address = self.params.get('source_address')
+ if source_address is None:
+ return []
+ return [command_option, source_address]
+
+ def _call_downloader(self, tmpfilename, info_dict):
+ """ Either overwrite this or implement _make_cmd """
+ cmd = self._make_cmd(tmpfilename, info_dict)
+
+ if sys.platform == 'win32' and sys.version_info < (3, 0):
+ # Windows subprocess module does not actually support Unicode
+ # on Python 2.x
+ # See http://stackoverflow.com/a/9951851/35070
+ subprocess_encoding = sys.getfilesystemencoding()
+ cmd = [a.encode(subprocess_encoding, 'ignore') for a in cmd]
+ else:
+ subprocess_encoding = None
+ self._debug_cmd(cmd, subprocess_encoding)
+
+ p = subprocess.Popen(
+ cmd, stderr=subprocess.PIPE)
+ _, stderr = p.communicate()
+ if p.returncode != 0:
+ self.to_stderr(stderr)
+ return p.returncode
+
+
+class CurlFD(ExternalFD):
+ def _make_cmd(self, tmpfilename, info_dict):
+ cmd = [self.exe, '-o', tmpfilename]
+ for key, val in info_dict['http_headers'].items():
+ cmd += ['--header', '%s: %s' % (key, val)]
+ cmd += self._source_address('--interface')
+ cmd += ['--', info_dict['url']]
+ return cmd
+
+
+class WgetFD(ExternalFD):
+ def _make_cmd(self, tmpfilename, info_dict):
+ cmd = [self.exe, '-O', tmpfilename, '-nv', '--no-cookies']
+ for key, val in info_dict['http_headers'].items():
+ cmd += ['--header', '%s: %s' % (key, val)]
+ cmd += self._source_address('--bind-address')
+ cmd += ['--', info_dict['url']]
+ return cmd
+
+
+class Aria2cFD(ExternalFD):
+ def _make_cmd(self, tmpfilename, info_dict):
+ cmd = [
+ self.exe, '-c',
+ '--min-split-size', '1M', '--max-connection-per-server', '4']
+ dn = os.path.dirname(tmpfilename)
+ if dn:
+ cmd += ['--dir', dn]
+ cmd += ['--out', os.path.basename(tmpfilename)]
+ for key, val in info_dict['http_headers'].items():
+ cmd += ['--header', '%s: %s' % (key, val)]
+ cmd += self._source_address('--interface')
+ cmd += ['--', info_dict['url']]
+ return cmd
+
+_BY_NAME = dict(
+ (klass.get_basename(), klass)
+ for name, klass in globals().items()
+ if name.endswith('FD') and name != 'ExternalFD'
+)
+
+
+def list_external_downloaders():
+ return sorted(_BY_NAME.keys())
+
+
+def get_external_downloader(external_downloader):
+ """ Given the name of the executable, see whether we support the given
+ downloader . """
+ bn = os.path.basename(external_downloader)
+ return _BY_NAME[bn]
""" Return a list of (segment, fragment) for each fragment in the video """
res = []
segment_run_table = boot_info['segments'][0]
- # I've only found videos with one segment
- segment_run_entry = segment_run_table['segment_run'][0]
- n_frags = segment_run_entry[1]
fragment_run_entry_table = boot_info['fragments'][0]['fragments']
first_frag_number = fragment_run_entry_table[0]['first']
- for (i, frag_number) in zip(range(1, n_frags + 1), itertools.count(first_frag_number)):
- res.append((1, frag_number))
+ fragments_counter = itertools.count(first_frag_number)
+ for segment, fragments_count in segment_run_table['segment_run']:
+ for _ in range(fragments_count):
+ res.append((segment, next(fragments_counter)))
return res
A downloader for f4m manifests or AdobeHDS.
"""
+ def _get_unencrypted_media(self, doc):
+ media = doc.findall(_add_ns('media'))
+ if not media:
+ self.report_error('No media found')
+ for e in (doc.findall(_add_ns('drmAdditionalHeader')) +
+ doc.findall(_add_ns('drmAdditionalHeaderSet'))):
+ # If id attribute is missing it's valid for all media nodes
+ # without drmAdditionalHeaderId or drmAdditionalHeaderSetId attribute
+ if 'id' not in e.attrib:
+ self.report_error('Missing ID in f4m DRM')
+ media = list(filter(lambda e: 'drmAdditionalHeaderId' not in e.attrib and
+ 'drmAdditionalHeaderSetId' not in e.attrib,
+ media))
+ if not media:
+ self.report_error('Unsupported DRM')
+ return media
+
def real_download(self, filename, info_dict):
man_url = info_dict['url']
requested_bitrate = info_dict.get('tbr')
)
doc = etree.fromstring(manifest)
- formats = [(int(f.attrib.get('bitrate', -1)), f) for f in doc.findall(_add_ns('media'))]
+ formats = [(int(f.attrib.get('bitrate', -1)), f)
+ for f in self._get_unencrypted_media(doc)]
if requested_bitrate is None:
# get the best format
formats = sorted(formats, key=lambda f: f[0])
compat_urllib_request,
)
from ..utils import (
+ encodeArgument,
encodeFilename,
)
self.report_destination(filename)
tmpfilename = self.temp_name(filename)
- args = [
- '-y', '-i', url, '-f', 'mp4', '-c', 'copy',
- '-bsf:a', 'aac_adtstoasc',
- encodeFilename(tmpfilename, for_subprocess=True)]
-
ffpp = FFmpegPostProcessor(downloader=self)
program = ffpp._executable
if program is None:
self.report_error('m3u8 download detected but ffmpeg or avconv could not be found. Please install one.')
return False
ffpp.check_version()
- cmd = [program] + args
- retval = subprocess.call(cmd)
+ args = [
+ encodeArgument(opt)
+ for opt in (program, '-y', '-i', url, '-f', 'mp4', '-c', 'copy', '-bsf:a', 'aac_adtstoasc')]
+ args.append(encodeFilename(tmpfilename, True))
+
+ retval = subprocess.call(args)
if retval == 0:
fsize = os.path.getsize(encodeFilename(tmpfilename))
- self.to_screen('\r[%s] %s bytes' % (cmd[0], fsize))
+ self.to_screen('\r[%s] %s bytes' % (args[0], fsize))
self.try_rename(tmpfilename, filename)
self._hook_progress({
'downloaded_bytes': fsize,
import os
import time
+from socket import error as SocketError
+import errno
+
from .common import FileDownloader
from ..compat import (
compat_urllib_request,
# Do not include the Accept-Encoding header
headers = {'Youtubedl-no-compression': 'True'}
- if 'user_agent' in info_dict:
- headers['Youtubedl-user-agent'] = info_dict['user_agent']
- if 'http_referer' in info_dict:
- headers['Referer'] = info_dict['http_referer']
add_headers = info_dict.get('http_headers')
if add_headers:
headers.update(add_headers)
resume_len = 0
open_mode = 'wb'
break
+ except SocketError as e:
+ if e.errno != errno.ECONNRESET:
+ # Connection reset is no problem, just retry
+ raise
+
# Retry
count += 1
if count <= retries:
except (OSError, IOError) as err:
self.report_error('unable to open for writing: %s' % str(err))
return False
+
+ if self.params.get('xattr_set_filesize', False) and data_len is not None:
+ try:
+ import xattr
+ xattr.setxattr(tmpfilename, 'user.ytdl.filesize', str(data_len))
+ except(OSError, IOError, ImportError) as err:
+ self.report_error('unable to set filesize xattr: %s' % str(err))
+
try:
stream.write(data_block)
except (IOError, OSError) as err:
live = info_dict.get('rtmp_live', False)
conn = info_dict.get('rtmp_conn', None)
protocol = info_dict.get('rtmp_protocol', None)
+ real_time = info_dict.get('rtmp_real_time', False)
+ no_resume = info_dict.get('no_resume', False)
+ continue_dl = info_dict.get('continuedl', False)
self.report_destination(filename)
tmpfilename = self.temp_name(filename)
basic_args += ['--conn', conn]
if protocol is not None:
basic_args += ['--protocol', protocol]
- args = basic_args + [[], ['--resume', '--skip', '1']][not live and self.params.get('continuedl', False)]
+ if real_time:
+ basic_args += ['--realtime']
+
+ args = basic_args
+ if not no_resume and continue_dl and not live:
+ args += ['--resume']
+ if not live and continue_dl:
+ args += ['--skip', '1']
if sys.platform == 'win32' and sys.version_info < (3, 0):
# Windows subprocess module does not actually support Unicode
else:
subprocess_encoding = None
- if self.params.get('verbose', False):
- if subprocess_encoding:
- str_args = [
- a.decode(subprocess_encoding) if isinstance(a, bytes) else a
- for a in args]
- else:
- str_args = args
- try:
- import pipes
- shell_quote = lambda args: ' '.join(map(pipes.quote, str_args))
- except ImportError:
- shell_quote = repr
- self.to_screen('[debug] rtmpdump command line: ' + shell_quote(str_args))
+ self._debug_cmd(args, subprocess_encoding, exe='rtmpdump')
RD_SUCCESS = 0
RD_FAILED = 1
from __future__ import unicode_literals
from .abc import ABCIE
+from .abc7news import Abc7NewsIE
from .academicearth import AcademicEarthCourseIE
from .addanime import AddAnimeIE
from .adobetv import AdobeTVIE
from .atresplayer import AtresPlayerIE
from .atttechchannel import ATTTechChannelIE
from .audiomack import AudiomackIE, AudiomackAlbumIE
-from .auengine import AUEngineIE
from .azubu import AzubuIE
from .bambuser import BambuserIE, BambuserChannelIE
from .bandcamp import BandcampIE, BandcampAlbumIE
CrunchyrollShowPlaylistIE
)
from .cspan import CSpanIE
+from .ctsnews import CtsNewsIE
from .dailymotion import (
DailymotionIE,
DailymotionPlaylistIE,
)
from .daum import DaumIE
from .dbtv import DBTVIE
+from .dctp import DctpTvIE
from .deezer import DeezerPlaylistIE
from .dfb import DFBIE
from .dotsub import DotsubIE
from .grooveshark import GroovesharkIE
from .groupon import GrouponIE
from .hark import HarkIE
+from .hearthisat import HearThisAtIE
from .heise import HeiseIE
from .hellporno import HellPornoIE
from .helsinki import HelsinkiIE
from .hentaistigma import HentaiStigmaIE
+from .historicfilms import HistoricFilmsIE
from .hitbox import HitboxIE, HitboxLiveIE
from .hornbunny import HornBunnyIE
from .hostingbulk import HostingBulkIE
from .ndtv import NDTVIE
from .netzkino import NetzkinoIE
from .nerdcubed import NerdCubedFeedIE
+from .nerdist import NerdistIE
from .newgrounds import NewgroundsIE
from .newstube import NewstubeIE
+from .nextmedia import (
+ NextMediaIE,
+ NextMediaActionNewsIE,
+ AppleDailyRealtimeNewsIE,
+ AppleDailyAnimationNewsIE
+)
from .nfb import NFBIE
from .nfl import NFLIE
-from .nhl import NHLIE, NHLVideocenterIE
+from .nhl import (
+ NHLIE,
+ NHLNewsIE,
+ NHLVideocenterIE,
+)
from .niconico import NiconicoIE, NiconicoPlaylistIE
from .ninegag import NineGagIE
from .noco import NocoIE
NRKIE,
NRKTVIE,
)
-from .ntv import NTVIE
+from .ntvde import NTVDeIE
+from .ntvru import NTVRuIE
from .nytimes import NYTimesIE
from .nuvid import NuvidIE
from .oktoberfesttv import OktoberfestTVIE
from .rte import RteIE
from .rtlnl import RtlXlIE
from .rtlnow import RTLnowIE
+from .rtl2 import RTL2IE
from .rtp import RTPIE
from .rts import RTSIE
from .rtve import RTVEALaCartaIE, RTVELiveIE
from .steam import SteamIE
from .streamcloud import StreamcloudIE
from .streamcz import StreamCZIE
+from .streetvoice import StreetVoiceIE
from .sunporno import SunPornoIE
from .swrmediathek import SWRMediathekIE
from .syfy import SyfyIE
from .teletask import TeleTaskIE
from .tenplay import TenPlayIE
from .testurl import TestURLIE
+from .testtube import TestTubeIE
from .tf1 import TF1IE
from .theonion import TheOnionIE
from .theplatform import ThePlatformIE
from .tvigle import TvigleIE
from .tvp import TvpIE, TvpSeriesIE
from .tvplay import TVPlayIE
+from .tweakers import TweakersIE
from .twentyfourvideo import TwentyFourVideoIE
-from .twitch import TwitchIE
+from .twitch import (
+ TwitchVideoIE,
+ TwitchChapterIE,
+ TwitchVodIE,
+ TwitchProfileIE,
+ TwitchPastBroadcastsIE,
+ TwitchBookmarksIE,
+ TwitchStreamIE,
+)
from .ubu import UbuIE
from .udemy import (
UdemyIE,
from .wistia import WistiaIE
from .worldstarhiphop import WorldStarHipHopIE
from .wrzuta import WrzutaIE
+from .wsj import WSJIE
from .xbef import XBefIE
from .xboxclips import XboxClipsIE
from .xhamster import XHamsterIE
from .xnxx import XNXXIE
from .xvideos import XVideosIE
from .xtube import XTubeUserIE, XTubeIE
+from .xuite import XuiteIE
from .xxxymovies import XXXYMoviesIE
from .yahoo import (
YahooIE,
--- /dev/null
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import parse_iso8601
+
+
+class Abc7NewsIE(InfoExtractor):
+ _VALID_URL = r'https?://abc7news\.com(?:/[^/]+/(?P<display_id>[^/]+))?/(?P<id>\d+)'
+ _TESTS = [
+ {
+ 'url': 'http://abc7news.com/entertainment/east-bay-museum-celebrates-vintage-synthesizers/472581/',
+ 'info_dict': {
+ 'id': '472581',
+ 'display_id': 'east-bay-museum-celebrates-vintage-synthesizers',
+ 'ext': 'mp4',
+ 'title': 'East Bay museum celebrates history of synthesized music',
+ 'description': 'md5:a4f10fb2f2a02565c1749d4adbab4b10',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'timestamp': 1421123075,
+ 'upload_date': '20150113',
+ 'uploader': 'Jonathan Bloom',
+ },
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
+ },
+ {
+ 'url': 'http://abc7news.com/472581',
+ 'only_matching': True,
+ },
+ ]
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+ display_id = mobj.group('display_id') or video_id
+
+ webpage = self._download_webpage(url, display_id)
+
+ m3u8 = self._html_search_meta(
+ 'contentURL', webpage, 'm3u8 url', fatal=True)
+
+ formats = self._extract_m3u8_formats(m3u8, display_id, 'mp4')
+ self._sort_formats(formats)
+
+ title = self._og_search_title(webpage).strip()
+ description = self._og_search_description(webpage).strip()
+ thumbnail = self._og_search_thumbnail(webpage)
+ timestamp = parse_iso8601(self._search_regex(
+ r'<div class="meta">\s*<time class="timeago" datetime="([^"]+)">',
+ webpage, 'upload date', fatal=False))
+ uploader = self._search_regex(
+ r'rel="author">([^<]+)</a>',
+ webpage, 'uploader', default=None)
+
+ return {
+ 'id': video_id,
+ 'display_id': display_id,
+ 'title': title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'timestamp': timestamp,
+ 'uploader': uploader,
+ 'formats': formats,
+ }
# encoding: utf-8
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
}
def _real_extract(self, url):
- mobj = re.search(self._VALID_URL, url)
-
- video_id = mobj.group('video_id')
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
# find internal video meta data
playlist.append({
'_type': 'video',
'id': video_id,
- 'title': title,
'formats': formats,
'title': title,
'duration': duration,
'thumbnail': thumbnail,
'upload_date': upload_date,
'uploader_id': uploader_id,
- 'user_agent': 'QuickTime compatible (youtube-dl)',
+ 'http_headers': {
+ 'User-Agent': 'QuickTime compatible (youtube-dl)',
+ },
})
return {
_TESTS = [{
'url': 'http://mediathek.daserste.de/sendungen_a-z/328454_anne-will/22429276_vertrauen-ist-gut-spionieren-ist-besser-geht',
- 'file': '22429276.mp4',
- 'md5': '469751912f1de0816a9fc9df8336476c',
- 'info_dict': {
- 'title': 'Vertrauen ist gut, Spionieren ist besser - Geht so deutsch-amerikanische Freundschaft?',
- 'description': 'Das Erste Mediathek [ARD]: Vertrauen ist gut, Spionieren ist besser - Geht so deutsch-amerikanische Freundschaft?, Anne Will, Über die Spionage-Affäre diskutieren Clemens Binninger, Katrin Göring-Eckardt, Georg Mascolo, Andrew B. Denison und Constanze Kurz.. Das Video zur Sendung Anne Will am Mittwoch, 16.07.2014',
- },
- 'skip': 'Blocked outside of Germany',
+ 'only_matching': True,
}, {
'url': 'http://www.ardmediathek.de/tv/Tatort/Das-Wunder-von-Wolbeck-Video-tgl-ab-20/Das-Erste/Video?documentId=22490580&bcastId=602916',
'info_dict': {
import time
import hmac
-from .common import InfoExtractor
+from .subtitles import SubtitlesInfoExtractor
from ..compat import (
compat_str,
compat_urllib_parse,
)
-class AtresPlayerIE(InfoExtractor):
+class AtresPlayerIE(SubtitlesInfoExtractor):
_VALID_URL = r'https?://(?:www\.)?atresplayer\.com/television/[^/]+/[^/]+/[^/]+/(?P<id>.+?)_\d+\.html'
_TESTS = [
{
for fmt in ['windows', 'android_tablet']:
request = compat_urllib_request.Request(
self._URL_VIDEO_TEMPLATE.format(fmt, episode_id, timestamp_shifted, token))
- request.add_header('Youtubedl-user-agent', self._USER_AGENT)
+ request.add_header('User-Agent', self._USER_AGENT)
fmt_json = self._download_json(
request, video_id, 'Downloading %s video JSON' % fmt)
raise ExtractorError(
'%s returned error: %s' % (self.IE_NAME, result), expected=True)
- for _, video_url in fmt_json['resultObject'].items():
+ for format_id, video_url in fmt_json['resultObject'].items():
+ if format_id == 'token' or not video_url.startswith('http'):
+ continue
if video_url.endswith('/Manifest'):
- formats.extend(self._extract_f4m_formats(video_url[:-9] + '/manifest.f4m', video_id))
+ if 'geodeswowsmpra3player' in video_url:
+ f4m_path = video_url.split('smil:', 1)[-1].split('free_', 1)[0]
+ f4m_url = 'http://drg.antena3.com/{0}hds/es/sd.f4m'.format(f4m_path)
+ # this videos are protected by DRM, the f4m downloader doesn't support them
+ continue
+ else:
+ f4m_url = video_url[:-9] + '/manifest.f4m'
+ formats.extend(self._extract_f4m_formats(f4m_url, video_id))
else:
formats.append({
'url': video_url,
- 'format_id': 'android',
+ 'format_id': 'android-%s' % format_id,
'preference': 1,
})
self._sort_formats(formats)
description = xpath_text(art, './description', 'description')
thumbnail = xpath_text(episode, './media/asset/files/background', 'thumbnail')
+ subtitles = {}
+ subtitle = xpath_text(episode, './media/asset/files/subtitle', 'subtitle')
+ if subtitle:
+ subtitles['es'] = subtitle
+
+ if self._downloader.params.get('listsubtitles', False):
+ self._list_available_subtitles(video_id, subtitles)
+ return
+
return {
'id': video_id,
'title': title,
'thumbnail': thumbnail,
'duration': duration,
'formats': formats,
+ 'subtitles': self.extract_subtitles(video_id, subtitles),
}
# Album playlist ripped from fakeshoredrive with no metadata
{
'url': 'http://www.audiomack.com/album/fakeshoredrive/ppp-pistol-p-project',
+ 'info_dict': {
+ 'title': 'PPP (Pistol P Project)',
+ 'id': '837572',
+ },
'playlist': [{
'info_dict': {
- 'title': '9.-heaven-or-hell-chimaca-ft-zuse-prod-by-dj-fu',
- 'id': '9.-heaven-or-hell-chimaca-ft-zuse-prod-by-dj-fu',
+ 'title': 'PPP (Pistol P Project) - 9. Heaven or Hell (CHIMACA) ft Zuse (prod by DJ FU)',
+ 'id': '837577',
'ext': 'mp3',
+ 'uploader': 'Lil Herb a.k.a. G Herbo',
}
}],
'params': {
- 'playliststart': 8,
- 'playlistend': 8,
+ 'playliststart': 9,
+ 'playlistend': 9,
}
}
]
+++ /dev/null
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..compat import compat_urllib_parse
-from ..utils import (
- determine_ext,
- ExtractorError,
- remove_end,
-)
-
-
-class AUEngineIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?auengine\.com/embed\.php\?.*?file=(?P<id>[^&]+).*?'
-
- _TEST = {
- 'url': 'http://auengine.com/embed.php?file=lfvlytY6&w=650&h=370',
- 'md5': '48972bdbcf1a3a2f5533e62425b41d4f',
- 'info_dict': {
- 'id': 'lfvlytY6',
- 'ext': 'mp4',
- 'title': '[Commie]The Legend of the Legendary Heroes - 03 - Replication Eye (Alpha Stigma)[F9410F5A]'
- }
- }
-
- def _real_extract(self, url):
- video_id = self._match_id(url)
-
- webpage = self._download_webpage(url, video_id)
- title = self._html_search_regex(
- r'<title>\s*(?P<title>.+?)\s*</title>', webpage, 'title')
- video_urls = re.findall(r'http://\w+.auengine.com/vod/.*[^\W]', webpage)
- video_url = compat_urllib_parse.unquote(video_urls[0])
- thumbnails = re.findall(r'http://\w+.auengine.com/thumb/.*[^\W]', webpage)
- thumbnail = compat_urllib_parse.unquote(thumbnails[0])
-
- if not video_url:
- raise ExtractorError('Could not find video URL')
-
- ext = '.' + determine_ext(video_url)
- title = remove_end(title, ext)
-
- return {
- 'id': video_id,
- 'url': video_url,
- 'title': title,
- 'thumbnail': thumbnail,
- 'http_referer': 'http://www.auengine.com/flowplayer/flowplayer.commercial-3.2.14.swf',
- }
class BBCCoUkIE(SubtitlesInfoExtractor):
IE_NAME = 'bbc.co.uk'
IE_DESC = 'BBC iPlayer'
- _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer/(?:episode|playlist))/)|music/clips[/#])(?P<id>[\da-z]{8})'
+ _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer(?:/[^/]+)?/(?:episode|playlist))/)|music/clips[/#])(?P<id>[\da-z]{8})'
_TESTS = [
{
}, {
'url': 'http://www.bbc.co.uk/music/clips#p02frcc3',
'only_matching': True,
+ }, {
+ 'url': 'http://www.bbc.co.uk/iplayer/cbeebies/episode/b0480276/bing-14-atchoo',
+ 'only_matching': True,
}
]
# For some weird reason, blip.tv serves a video instead of subtitles
# when we request with a common UA
req = compat_urllib_request.Request(url)
- req.add_header('Youtubedl-user-agent', 'youtube-dl')
+ req.add_header('User-Agent', 'youtube-dl')
return self._download_webpage(req, None, note=False)
"""
# Fix up some stupid HTML, see https://github.com/rg3/youtube-dl/issues/1553
- object_str = re.sub(r'(<param name="[^"]+" value="[^"]+")>',
+ object_str = re.sub(r'(<param(?:\s+[a-zA-Z0-9_]+="[^"]*")*)>',
lambda m: m.group(1) + '/>', object_str)
# Fix up some stupid XML, see https://github.com/rg3/youtube-dl/issues/1608
object_str = object_str.replace('<--', '<!--')
item, './{http://developer.longtailvideo.com/trac/}date')
upload_date = unified_strdate(date_str, day_first=False)
# duration is present but wrong
- formats = []
- formats.append({
+ formats = [{
'format_id': 'main',
- 'url': item.find(
- './{http://search.yahoo.com/mrss/}content').attrib['url'],
- })
+ 'url': item.find('./{http://search.yahoo.com/mrss/}content').attrib['url'],
+ }]
backup_url = xpath_text(
item, './{http://developer.longtailvideo.com/trac/}backupContent')
if backup_url:
from __future__ import unicode_literals
-import json
-import re
-
from .common import InfoExtractor
+from ..utils import determine_ext
_translation_table = {
'''
_TEST = {
'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo',
- 'md5': 'a2ba71eebf523859fe527a61018f723e',
+ 'md5': 'b7c9bbd4eb3a226ab91093714dcaa480',
'info_dict': {
'id': '1012420',
- 'ext': 'mp4',
+ 'ext': 'flv',
'title': 'Fun Jynx Maze solo',
'thumbnail': 're:^https?://.*\.jpg$',
'age_limit': 18,
video_title = self._search_regex(
r'mediaTitle = "([^"]+)"', webpage, 'title')
- pl_fiji = self._search_regex(
- r'pl_fiji = \'([^\']+)\'', webpage, 'video data')
- pl_c_qual = self._search_regex(
- r'pl_c_qual = "(.)"', webpage, 'video quality')
- video_url = _decode(pl_fiji)
- formats = [{
- 'url': video_url,
- 'format_id': 'default-%s' % pl_c_qual,
- }]
-
- qualities_json = self._search_regex(
- r'var pl_qualities\s*=\s*(.*?);\n', webpage, 'quality info')
- qualities_data = json.loads(qualities_json)
-
- for i, t in enumerate(
- re.findall(r"pl_fiji_([a-z0-9]+)\s*=\s*'([^']+')", webpage)):
- quality_id, crypted_url = t
- video_url = _decode(crypted_url)
+ fmts = {}
+ for fmt in ('mp4', 'flv'):
+ fmt_list = self._parse_json(self._search_regex(
+ r'var %sjson\s*=\s*(\[.*?\]);' % fmt, webpage, '%s formats' % fmt), video_id)
+ for f in fmt_list:
+ fmts[f['fname']] = _decode(f['sUrl'])
+
+ qualities = self._parse_json(self._search_regex(
+ r'var player_btns\s*=\s*(.*?);\n', webpage, 'quality info'), video_id)
+
+ formats = []
+ for fname, url in fmts.items():
f = {
- 'format_id': quality_id,
- 'url': video_url,
- 'quality': i,
+ 'url': url,
}
- if quality_id in qualities_data:
- qd = qualities_data[quality_id]
- m = re.match(
- r'''(?x)<b>(?P<width>[0-9]+)x(?P<height>[0-9]+)<\\/b>
- \s*\(\s*(?P<tbr>[0-9]+)\s*kb\\/s''', qd)
- if m:
- f['width'] = int(m.group('width'))
- f['height'] = int(m.group('height'))
- f['tbr'] = int(m.group('tbr'))
+ if fname in qualities:
+ qual = qualities[fname]
+ f.update({
+ 'format_id': '%s_%sp' % (determine_ext(url), qual['h']),
+ 'width': qual['w'],
+ 'height': qual['h'],
+ 'tbr': qual['br'],
+ })
formats.append(f)
+
self._sort_formats(formats)
thumbnail = self._search_regex(
mobj = re.match(self._VALID_URL, url)
path = mobj.group('path')
page_title = mobj.group('title')
- info_url = 'http://cnn.com/video/data/3.0/%s/index.xml' % path
+ info_url = 'http://edition.cnn.com/video/data/3.0/%s/index.xml' % path
info = self._download_xml(info_url, page_title)
formats = []
_VALID_URL = r'https?://(?:(?:edition|www)\.)?cnn\.com/(?!video/)'
_TEST = {
'url': 'http://www.cnn.com/2014/12/21/politics/obama-north-koreas-hack-not-war-but-cyber-vandalism/',
- 'md5': '275b326f85d80dff7592a9820f5dc887',
+ 'md5': '689034c2a3d9c6dc4aa72d65a81efd01',
'info_dict': {
- 'id': 'bestoftv/2014/12/21/sotu-crowley-president-obama-north-korea-not-going-to-be-intimidated.cnn',
+ 'id': 'bestoftv/2014/12/21/ip-north-korea-obama.cnn',
'ext': 'mp4',
- 'title': 'Obama: We\'re not going to be intimidated',
- 'description': 'md5:e735586f3dc936075fa654a4d91b21f9',
- 'upload_date': '20141220',
+ 'title': 'Obama: Cyberattack not an act of war',
+ 'description': 'md5:51ce6750450603795cad0cdfbd7d05c5',
+ 'upload_date': '20141221',
},
'add_ie': ['CNN'],
}
class ComedyCentralShowsIE(MTVServicesInfoExtractor):
IE_DESC = 'The Daily Show / The Colbert Report'
- # urls can be abbreviations like :thedailyshow or :colbert
+ # urls can be abbreviations like :thedailyshow
# urls for episodes like:
# or urls for clips like: http://www.thedailyshow.com/watch/mon-december-10-2012/any-given-gun-day
# or: http://www.colbertnation.com/the-colbert-report-videos/421667/november-29-2012/moon-shattering-news
# or: http://www.colbertnation.com/the-colbert-report-collections/422008/festival-of-lights/79524
- _VALID_URL = r'''(?x)^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport)
+ _VALID_URL = r'''(?x)^(:(?P<shortname>tds|thedailyshow)
|https?://(:www\.)?
(?P<showname>thedailyshow|thecolbertreport)\.(?:cc\.)?com/
((?:full-)?episodes/(?:[0-9a-z]{6}/)?(?P<episode>.*)|
|(watch/(?P<date>[^/]*)/(?P<tdstitle>.*))
)|
(?P<interview>
- extended-interviews/(?P<interID>[0-9a-z]+)/(?:playlist_tds_extended_)?(?P<interview_title>.*?)(/.*?)?)))
+ extended-interviews/(?P<interID>[0-9a-z]+)/
+ (?:playlist_tds_extended_)?(?P<interview_title>[^/?#]*?)
+ (?:/[^/?#]?|[?#]|$))))
'''
_TESTS = [{
'url': 'http://thedailyshow.cc.com/watch/thu-december-13-2012/kristen-stewart',
'uploader': 'thedailyshow',
'title': 'thedailyshow kristen-stewart part 1',
}
+ }, {
+ 'url': 'http://thedailyshow.cc.com/extended-interviews/b6364d/sarah-chayes-extended-interview',
+ 'info_dict': {
+ 'id': 'sarah-chayes-extended-interview',
+ 'description': 'Carnegie Endowment Senior Associate Sarah Chayes discusses how corrupt institutions function throughout the world in her book "Thieves of State: Why Corruption Threatens Global Security."',
+ 'title': 'thedailyshow Sarah Chayes Extended Interview',
+ },
+ 'playlist': [
+ {
+ 'info_dict': {
+ 'id': '0baad492-cbec-4ec1-9e50-ad91c291127f',
+ 'ext': 'mp4',
+ 'upload_date': '20150129',
+ 'description': 'Carnegie Endowment Senior Associate Sarah Chayes discusses how corrupt institutions function throughout the world in her book "Thieves of State: Why Corruption Threatens Global Security."',
+ 'uploader': 'thedailyshow',
+ 'title': 'thedailyshow sarah-chayes-extended-interview part 1',
+ },
+ },
+ {
+ 'info_dict': {
+ 'id': '1e4fb91b-8ce7-4277-bd7c-98c9f1bbd283',
+ 'ext': 'mp4',
+ 'upload_date': '20150129',
+ 'description': 'Carnegie Endowment Senior Associate Sarah Chayes discusses how corrupt institutions function throughout the world in her book "Thieves of State: Why Corruption Threatens Global Security."',
+ 'uploader': 'thedailyshow',
+ 'title': 'thedailyshow sarah-chayes-extended-interview part 2',
+ },
+ },
+ ],
+ 'params': {
+ 'skip_download': True,
+ },
}, {
'url': 'http://thedailyshow.cc.com/extended-interviews/xm3fnq/andrew-napolitano-extended-interview',
'only_matching': True,
return {
'_type': 'playlist',
+ 'id': epTitle,
'entries': entries,
'title': show_name + ' ' + title,
'description': description,
from ..compat import (
compat_cookiejar,
+ compat_HTTPError,
compat_http_client,
compat_urllib_error,
compat_urllib_parse_urlparse,
compiled_regex_type,
ExtractorError,
float_or_none,
+ HEADRequest,
int_or_none,
RegexNotFoundError,
sanitize_filename,
* player_url SWF Player URL (used for rtmpdump).
* protocol The protocol that will be used for the actual
download, lower-case.
- "http", "https", "rtsp", "rtmp", "m3u8" or so.
+ "http", "https", "rtsp", "rtmp", "rtmpe",
+ "m3u8", or "m3u8_native".
* preference Order number of this format. If this field is
present and not None, the formats get sorted
by this field, regardless of all other values.
(quality takes higher priority)
-1 for default (order by other properties),
-2 or smaller for less than default.
- * http_referer HTTP Referer header value to set.
* http_method HTTP method to use for the download.
* http_headers A dictionary of additional HTTP headers
to add to the request.
* http_post_data Additional data to send with a POST
request.
* stretched_ratio If given and not 1, indicates that the
- video's pixels are not square.
- width : height ratio as float.
+ video's pixels are not square.
+ width : height ratio as float.
+ * no_resume The server does not support resuming the
+ (HTTP or RTMP) download. Boolean.
+
url: Final video URL.
ext: Video filename extension.
format: The video format, defaults to ext (used for --get-format)
something like "4234987", title "Dancing naked mole rats",
and display_id "dancing-naked-mole-rats"
thumbnails: A list of dictionaries, with the following entries:
+ * "id" (optional, string) - Thumbnail format ID
* "url"
+ * "preference" (optional, int) - quality of the image
* "width" (optional, int)
* "height" (optional, int)
* "resolution" (optional, string "{width}x{height"},
thumbnail: Full URL to a video thumbnail image.
description: Full video description.
uploader: Full name of the video uploader.
+ creator: The main artist who created the video.
timestamp: UNIX timestamp of the moment the video became available.
upload_date: Video upload date (YYYYMMDD).
If not explicitly set, calculated from timestamp.
preference,
f.get('language_preference') if f.get('language_preference') is not None else -1,
f.get('quality') if f.get('quality') is not None else -1,
- f.get('height') if f.get('height') is not None else -1,
- f.get('width') if f.get('width') is not None else -1,
- ext_preference,
f.get('tbr') if f.get('tbr') is not None else -1,
f.get('vbr') if f.get('vbr') is not None else -1,
+ ext_preference,
+ f.get('height') if f.get('height') is not None else -1,
+ f.get('width') if f.get('width') is not None else -1,
f.get('abr') if f.get('abr') is not None else -1,
audio_ext_preference,
f.get('fps') if f.get('fps') is not None else -1,
)
formats.sort(key=_formats_key)
+ def _check_formats(self, formats, video_id):
+ if formats:
+ formats[:] = filter(
+ lambda f: self._is_valid_url(
+ f['url'], video_id,
+ item='%s video format' % f.get('format_id') if f.get('format_id') else 'video'),
+ formats)
+
+ def _is_valid_url(self, url, video_id, item='video'):
+ try:
+ self._request_webpage(
+ HEADRequest(url), video_id,
+ 'Checking %s URL' % item)
+ return True
+ except ExtractorError as e:
+ if isinstance(e.cause, compat_HTTPError):
+ self.report_warning(
+ '%s URL is invalid, skipping' % item, video_id)
+ return False
+ raise
+
def http_scheme(self):
""" Either "http:" or "https:", depending on the user's preferences """
return (
self.to_screen(msg)
time.sleep(timeout)
- def _extract_f4m_formats(self, manifest_url, video_id):
+ def _extract_f4m_formats(self, manifest_url, video_id, preference=None, f4m_id=None):
manifest = self._download_xml(
manifest_url, video_id, 'Downloading f4m manifest',
'Unable to download f4m manifest')
media_nodes = manifest.findall('{http://ns.adobe.com/f4m/2.0}media')
for i, media_el in enumerate(media_nodes):
if manifest_version == '2.0':
- manifest_url = '/'.join(manifest_url.split('/')[:-1]) + '/' + media_el.attrib.get('href')
+ manifest_url = ('/'.join(manifest_url.split('/')[:-1]) + '/'
+ + (media_el.attrib.get('href') or media_el.attrib.get('url')))
tbr = int_or_none(media_el.attrib.get('bitrate'))
- format_id = 'f4m-%d' % (i if tbr is None else tbr)
formats.append({
- 'format_id': format_id,
+ 'format_id': '-'.join(filter(None, [f4m_id, 'f4m-%d' % (i if tbr is None else tbr)])),
'url': manifest_url,
'ext': 'flv',
'tbr': tbr,
'width': int_or_none(media_el.attrib.get('width')),
'height': int_or_none(media_el.attrib.get('height')),
+ 'preference': preference,
})
self._sort_formats(formats)
return formats
def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None,
- entry_protocol='m3u8', preference=None):
+ entry_protocol='m3u8', preference=None,
+ m3u8_id=None):
formats = [{
- 'format_id': 'm3u8-meta',
+ 'format_id': '-'.join(filter(None, [m3u8_id, 'm3u8-meta'])),
'url': m3u8_url,
'ext': ext,
'protocol': 'm3u8',
formats.append({'url': format_url(line)})
continue
tbr = int_or_none(last_info.get('BANDWIDTH'), scale=1000)
-
f = {
- 'format_id': 'm3u8-%d' % (tbr if tbr else len(formats)),
+ 'format_id': '-'.join(filter(None, [m3u8_id, 'm3u8-%d' % (tbr if tbr else len(formats))])),
'url': format_url(line.strip()),
'tbr': tbr,
'ext': ext,
return formats
# TODO: improve extraction
- def _extract_smil_formats(self, smil_url, video_id):
+ def _extract_smil_formats(self, smil_url, video_id, fatal=True):
smil = self._download_xml(
smil_url, video_id, 'Downloading SMIL file',
- 'Unable to download SMIL file')
+ 'Unable to download SMIL file', fatal=fatal)
+ if smil is False:
+ assert not fatal
+ return []
base = smil.find('./head/meta').get('base')
--- /dev/null
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import parse_iso8601, ExtractorError
+
+
+class CtsNewsIE(InfoExtractor):
+ # https connection failed (Connection reset)
+ _VALID_URL = r'http://news\.cts\.com\.tw/[a-z]+/[a-z]+/\d+/(?P<id>\d+)\.html'
+ _TESTS = [{
+ 'url': 'http://news.cts.com.tw/cts/international/201501/201501291578109.html',
+ 'md5': 'a9875cb790252b08431186d741beaabe',
+ 'info_dict': {
+ 'id': '201501291578109',
+ 'ext': 'mp4',
+ 'title': '以色列.真主黨交火 3人死亡',
+ 'description': 'md5:95e9b295c898b7ff294f09d450178d7d',
+ 'timestamp': 1422528540,
+ 'upload_date': '20150129',
+ }
+ }, {
+ # News count not appear on page but still available in database
+ 'url': 'http://news.cts.com.tw/cts/international/201309/201309031304098.html',
+ 'md5': '3aee7e0df7cdff94e43581f54c22619e',
+ 'info_dict': {
+ 'id': '201309031304098',
+ 'ext': 'mp4',
+ 'title': '韓國31歲童顏男 貌如十多歲小孩',
+ 'description': 'md5:f183feeba3752b683827aab71adad584',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'timestamp': 1378205880,
+ 'upload_date': '20130903',
+ }
+ }, {
+ # With Youtube embedded video
+ 'url': 'http://news.cts.com.tw/cts/money/201501/201501291578003.html',
+ 'md5': '1d842c771dc94c8c3bca5af2cc1db9c5',
+ 'add_ie': ['Youtube'],
+ 'info_dict': {
+ 'id': 'OVbfO7d0_hQ',
+ 'ext': 'mp4',
+ 'title': 'iPhone6熱銷 蘋果財報亮眼',
+ 'description': 'md5:f395d4f485487bb0f992ed2c4b07aa7d',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'upload_date': '20150128',
+ 'uploader_id': 'TBSCTS',
+ 'uploader': '中華電視公司',
+ }
+ }]
+
+ def _real_extract(self, url):
+ news_id = self._match_id(url)
+ page = self._download_webpage(url, news_id)
+
+ if self._search_regex(r'(CTSPlayer2)', page, 'CTSPlayer2 identifier', default=None):
+ feed_url = self._html_search_regex(
+ r'(http://news\.cts\.com\.tw/action/mp4feed\.php\?news_id=\d+)',
+ page, 'feed url')
+ video_url = self._download_webpage(
+ feed_url, news_id, note='Fetching feed')
+ else:
+ self.to_screen('Not CTSPlayer video, trying Youtube...')
+ youtube_url = self._search_regex(
+ r'src="(//www\.youtube\.com/embed/[^"]+)"', page, 'youtube url',
+ default=None)
+ if not youtube_url:
+ raise ExtractorError('The news includes no videos!', expected=True)
+
+ return {
+ '_type': 'url',
+ 'url': youtube_url,
+ 'ie_key': 'Youtube',
+ }
+
+ description = self._html_search_meta('description', page)
+ title = self._html_search_meta('title', page)
+ thumbnail = self._html_search_meta('image', page)
+
+ datetime_str = self._html_search_regex(
+ r'(\d{4}/\d{2}/\d{2} \d{2}:\d{2})', page, 'date and time')
+ # Transform into ISO 8601 format with timezone info
+ datetime_str = datetime_str.replace('/', '-') + ':00+0800'
+ timestamp = parse_iso8601(datetime_str, delimiter=' ')
+
+ return {
+ 'id': news_id,
+ 'url': video_url,
+ 'title': title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'timestamp': timestamp,
+ }
--- /dev/null
+# encoding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_str
+
+
+class DctpTvIE(InfoExtractor):
+ _VALID_URL = r'http://www.dctp.tv/(#/)?filme/(?P<id>.+?)/$'
+ _TEST = {
+ 'url': 'http://www.dctp.tv/filme/videoinstallation-fuer-eine-kaufhausfassade/',
+ 'info_dict': {
+ 'id': '1324',
+ 'display_id': 'videoinstallation-fuer-eine-kaufhausfassade',
+ 'ext': 'flv',
+ 'title': 'Videoinstallation für eine Kaufhausfassade'
+ }
+ }
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ base_url = 'http://dctp-ivms2-restapi.s3.amazonaws.com/'
+ version_json = self._download_json(
+ base_url + 'version.json',
+ video_id, note='Determining file version')
+ version = version_json['version_name']
+ info_json = self._download_json(
+ '{0}{1}/restapi/slugs/{2}.json'.format(base_url, version, video_id),
+ video_id, note='Fetching object ID')
+ object_id = compat_str(info_json['object_id'])
+ meta_json = self._download_json(
+ '{0}{1}/restapi/media/{2}.json'.format(base_url, version, object_id),
+ video_id, note='Downloading metadata')
+ uuid = meta_json['uuid']
+ title = meta_json['title']
+ wide = meta_json['is_wide']
+ if wide:
+ ratio = '16x9'
+ else:
+ ratio = '4x3'
+ play_path = 'mp4:{0}_dctp_0500_{1}.m4v'.format(uuid, ratio)
+
+ servers_json = self._download_json(
+ 'http://www.dctp.tv/streaming_servers/',
+ video_id, note='Downloading server list')
+ url = servers_json[0]['endpoint']
+
+ return {
+ 'id': object_id,
+ 'title': title,
+ 'format': 'rtmp',
+ 'url': url,
+ 'play_path': play_path,
+ 'rtmp_real_time': True,
+ 'ext': 'flv',
+ 'display_id': video_id
+ }
from __future__ import unicode_literals
-import re
-import json
-
from .common import InfoExtractor
class DefenseGouvFrIE(InfoExtractor):
IE_NAME = 'defense.gouv.fr'
- _VALID_URL = (r'http://.*?\.defense\.gouv\.fr/layout/set/'
- r'ligthboxvideo/base-de-medias/webtv/(.*)')
+ _VALID_URL = r'http://.*?\.defense\.gouv\.fr/layout/set/ligthboxvideo/base-de-medias/webtv/(?P<id>[^/?#]*)'
_TEST = {
'url': 'http://www.defense.gouv.fr/layout/set/ligthboxvideo/base-de-medias/webtv/attaque-chimique-syrienne-du-21-aout-2013-1',
- 'file': '11213.mp4',
'md5': '75bba6124da7e63d2d60b5244ec9430c',
- "info_dict": {
- "title": "attaque-chimique-syrienne-du-21-aout-2013-1"
+ 'info_dict': {
+ 'id': '11213',
+ 'ext': 'mp4',
+ 'title': 'attaque-chimique-syrienne-du-21-aout-2013-1'
}
}
def _real_extract(self, url):
- title = re.match(self._VALID_URL, url).group(1)
+ title = self._match_id(url)
webpage = self._download_webpage(url, title)
+
video_id = self._search_regex(
r"flashvars.pvg_id=\"(\d+)\";",
webpage, 'ID')
json_url = ('http://static.videos.gouv.fr/brightcovehub/export/json/'
+ video_id)
- info = self._download_webpage(json_url, title,
- 'Downloading JSON config')
- video_url = json.loads(info)['renditions'][0]['url']
-
- return {'id': video_id,
- 'ext': 'mp4',
- 'url': video_url,
- 'title': title,
- }
+ info = self._download_json(json_url, title, 'Downloading JSON config')
+ video_url = info['renditions'][0]['url']
+
+ return {
+ 'id': video_id,
+ 'ext': 'mp4',
+ 'url': video_url,
+ 'title': title,
+ }
class DRTVIE(SubtitlesInfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?dr\.dk/tv/se/(?:[^/]+/)+(?P<id>[\da-z-]+)(?:[/#?]|$)'
+ _VALID_URL = r'https?://(?:www\.)?dr\.dk/tv/se/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
_TEST = {
'url': 'http://www.dr.dk/tv/se/partiets-mand/partiets-mand-7-8',
def _real_extract(self, url):
video_id = self._match_id(url)
- programcard = self._download_json(
- 'http://www.dr.dk/mu/programcard/expanded/%s' % video_id, video_id, 'Downloading video JSON')
+ webpage = self._download_webpage(url, video_id)
+
+ video_id = self._search_regex(
+ r'data-(?:material-identifier|episode-slug)="([^"]+)"',
+ webpage, 'video id')
+ programcard = self._download_json(
+ 'http://www.dr.dk/mu/programcard/expanded/%s' % video_id,
+ video_id, 'Downloading video JSON')
data = programcard['Data'][0]
title = data['Title']
elif asset['Kind'] == 'VideoResource':
duration = asset['DurationInMilliseconds'] / 1000.0
restricted_to_denmark = asset['RestrictedToDenmark']
+ spoken_subtitles = asset['Target'] == 'SpokenSubtitles'
for link in asset['Links']:
target = link['Target']
uri = link['Uri']
+ format_id = target
+ preference = -1 if target == 'HDS' else -2
+ if spoken_subtitles:
+ preference -= 2
+ format_id += '-spoken-subtitles'
formats.append({
'url': uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43' if target == 'HDS' else uri,
- 'format_id': target,
+ 'format_id': format_id,
'ext': link['FileFormat'],
- 'preference': -1 if target == 'HDS' else -2,
+ 'preference': preference,
})
subtitles_list = asset.get('SubtitlesList')
if isinstance(subtitles_list, list):
from .common import InfoExtractor
from ..compat import (
+ compat_urllib_parse,
compat_urllib_request,
compat_urlparse,
)
class FC2IE(InfoExtractor):
_VALID_URL = r'^http://video\.fc2\.com/(?:[^/]+/)?content/(?P<id>[^/]+)'
IE_NAME = 'fc2'
- _TEST = {
+ _NETRC_MACHINE = 'fc2'
+ _TESTS = [{
'url': 'http://video.fc2.com/en/content/20121103kUan1KHs',
'md5': 'a6ebe8ebe0396518689d963774a54eb7',
'info_dict': {
'ext': 'flv',
'title': 'Boxing again with Puff',
},
- }
+ }, {
+ 'url': 'http://video.fc2.com/en/content/20150125cEva0hDn/',
+ 'info_dict': {
+ 'id': '20150125cEva0hDn',
+ 'ext': 'mp4',
+ },
+ 'params': {
+ 'username': 'ytdl@yt-dl.org',
+ 'password': '(snip)',
+ 'skip': 'requires actual password'
+ }
+ }]
+
+ def _login(self):
+ (username, password) = self._get_login_info()
+ if username is None or password is None:
+ return False
+
+ # Log in
+ login_form_strs = {
+ 'email': username,
+ 'password': password,
+ 'done': 'video',
+ 'Submit': ' Login ',
+ }
+
+ # Convert to UTF-8 *before* urlencode because Python 2.x's urlencode
+ # chokes on unicode
+ login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k, v in login_form_strs.items())
+ login_data = compat_urllib_parse.urlencode(login_form).encode('utf-8')
+ request = compat_urllib_request.Request(
+ 'https://secure.id.fc2.com/index.php?mode=login&switch_language=en', login_data)
+
+ login_results = self._download_webpage(request, None, note='Logging in', errnote='Unable to log in')
+ if 'mode=redirect&login=done' not in login_results:
+ self.report_warning('unable to log in: bad username or password')
+ return False
+
+ # this is also needed
+ login_redir = compat_urllib_request.Request('http://id.fc2.com/?mode=redirect&login=done')
+ self._download_webpage(
+ login_redir, None, note='Login redirect', errnote='Login redirect failed')
+
+ return True
def _real_extract(self, url):
video_id = self._match_id(url)
+ self._login()
webpage = self._download_webpage(url, video_id)
self._downloader.cookiejar.clear_session_cookies() # must clear
+ self._login()
title = self._og_search_title(webpage)
thumbnail = self._og_search_thumbnail(webpage)
info = compat_urlparse.parse_qs(info_webpage)
if 'err_code' in info:
- raise ExtractorError('Error code: %s' % info['err_code'][0])
+ # most of the time we can still download wideo even if err_code is 403 or 602
+ self.report_warning(
+ 'Error code was: %s... but still trying' % info['err_code'][0])
+
+ if 'filepath' not in info:
+ raise ExtractorError('Cannot download file. Are you logged in?')
video_url = info['filepath'][0] + '?mid=' + info['mid'][0]
title_info = info.get('title')
_VALID_URL = r'https?://(?:www\.)?ft\.dk/webtv/video/[^?#]*?\.(?P<id>[0-9]+)\.aspx'
_TEST = {
'url': 'http://www.ft.dk/webtv/video/20141/eru/td.1165642.aspx?as=1#player',
+ 'md5': '6269e8626fa1a891bf5369b386ae996a',
'info_dict': {
'id': '1165642',
'ext': 'mp4',
'upload_date': '20141120',
'duration': 3960,
},
- 'params': {
- 'skip_download': 'rtmpdump required',
- }
}
def _real_extract(self, url):
# coding: utf-8
from __future__ import unicode_literals
-import json
-import re
-
from .common import InfoExtractor
from ..compat import (
- compat_parse_qs,
compat_urlparse,
)
+from ..utils import (
+ determine_ext,
+ int_or_none,
+)
class FranceCultureIE(InfoExtractor):
- _VALID_URL = r'(?P<baseurl>http://(?:www\.)?franceculture\.fr/)player/reecouter\?play=(?P<id>[0-9]+)'
+ _VALID_URL = r'https?://(?:www\.)?franceculture\.fr/player/reecouter\?play=(?P<id>[0-9]+)'
_TEST = {
'url': 'http://www.franceculture.fr/player/reecouter?play=4795174',
'info_dict': {
'id': '4795174',
'ext': 'mp3',
'title': 'Rendez-vous au pays des geeks',
+ 'alt_title': 'Carnet nomade | 13-14',
'vcodec': 'none',
- 'uploader': 'Colette Fellous',
'upload_date': '20140301',
- 'duration': 3601,
'thumbnail': r're:^http://www\.franceculture\.fr/.*/images/player/Carnet-nomade\.jpg$',
- 'description': 'Avec :Jean-Baptiste Péretié pour son documentaire sur Arte "La revanche des « geeks », une enquête menée aux Etats-Unis dans la S ...',
+ 'description': 'startswith:Avec :Jean-Baptiste Péretié pour son documentaire sur Arte "La revanche des « geeks », une enquête menée aux Etats',
+ 'timestamp': 1393700400,
}
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
- baseurl = mobj.group('baseurl')
-
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
- params_code = self._search_regex(
- r"<param name='movie' value='/sites/all/modules/rf/rf_player/swf/loader.swf\?([^']+)' />",
- webpage, 'parameter code')
- params = compat_parse_qs(params_code)
- video_url = compat_urlparse.urljoin(baseurl, params['urlAOD'][0])
+
+ video_path = self._search_regex(
+ r'<a id="player".*?href="([^"]+)"', webpage, 'video path')
+ video_url = compat_urlparse.urljoin(url, video_path)
+ timestamp = int_or_none(self._search_regex(
+ r'<a id="player".*?data-date="([0-9]+)"',
+ webpage, 'upload date', fatal=False))
+ thumbnail = self._search_regex(
+ r'<a id="player".*?>\s+<img src="([^"]+)"',
+ webpage, 'thumbnail', fatal=False)
title = self._html_search_regex(
- r'<h1 class="title[^"]+">(.+?)</h1>', webpage, 'title')
- uploader = self._html_search_regex(
- r'(?s)<div id="emission".*?<span class="author">(.*?)</span>',
- webpage, 'uploader', fatal=False)
- thumbnail_part = self._html_search_regex(
- r'(?s)<div id="emission".*?<img src="([^"]+)"', webpage,
- 'thumbnail', fatal=False)
- if thumbnail_part is None:
- thumbnail = None
- else:
- thumbnail = compat_urlparse.urljoin(baseurl, thumbnail_part)
+ r'<span class="title-diffusion">(.*?)</span>', webpage, 'title')
+ alt_title = self._html_search_regex(
+ r'<span class="title">(.*?)</span>',
+ webpage, 'alt_title', fatal=False)
description = self._html_search_regex(
- r'(?s)<p class="desc">(.*?)</p>', webpage, 'description')
+ r'<span class="description">(.*?)</span>',
+ webpage, 'description', fatal=False)
- info = json.loads(params['infoData'][0])[0]
- duration = info.get('media_length')
- upload_date_candidate = info.get('media_section5')
- upload_date = (
- upload_date_candidate
- if (upload_date_candidate is not None and
- re.match(r'[0-9]{8}$', upload_date_candidate))
- else None)
+ uploader = self._html_search_regex(
+ r'(?s)<div id="emission".*?<span class="author">(.*?)</span>',
+ webpage, 'uploader', default=None)
+ vcodec = 'none' if determine_ext(video_url.lower()) == 'mp3' else None
return {
'id': video_id,
'url': video_url,
- 'vcodec': 'none' if video_url.lower().endswith('.mp3') else None,
- 'duration': duration,
+ 'vcodec': vcodec,
'uploader': uploader,
- 'upload_date': upload_date,
+ 'timestamp': timestamp,
'title': title,
+ 'alt_title': alt_title,
'thumbnail': thumbnail,
'description': description,
}
class GenerationQuoiIE(InfoExtractor):
IE_NAME = 'france2.fr:generation-quoi'
- _VALID_URL = r'https?://generation-quoi\.france2\.fr/portrait/(?P<name>.*)(\?|$)'
+ _VALID_URL = r'https?://generation-quoi\.france2\.fr/portrait/(?P<id>[^/?#]+)'
_TEST = {
'url': 'http://generation-quoi.france2.fr/portrait/garde-a-vous',
- 'file': 'k7FJX8VBcvvLmX4wA5Q.mp4',
'info_dict': {
+ 'id': 'k7FJX8VBcvvLmX4wA5Q',
+ 'ext': 'mp4',
'title': 'Génération Quoi - Garde à Vous',
'uploader': 'Génération Quoi',
},
# It uses Dailymotion
'skip_download': True,
},
- 'skip': 'Only available from France',
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- name = mobj.group('name')
- info_url = compat_urlparse.urljoin(url, '/medias/video/%s.json' % name)
- info_json = self._download_webpage(info_url, name)
+ display_id = self._match_id(url)
+ info_url = compat_urlparse.urljoin(url, '/medias/video/%s.json' % display_id)
+ info_json = self._download_webpage(info_url, display_id)
info = json.loads(info_json)
return self.url_result('http://www.dailymotion.com/video/%s' % info['id'],
ie='Dailymotion')
# coding: utf-8
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
from ..utils import (
int_or_none,
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
-
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
og_title = self._og_search_title(webpage)
ExtractorError,
float_or_none,
HEADRequest,
+ is_html,
orderedSet,
parse_xml,
smuggle_url,
},
'add_ie': ['Ooyala'],
},
+ # multiple ooyala embeds on SBN network websites
+ {
+ 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
+ 'info_dict': {
+ 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
+ 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
+ },
+ 'playlist_mincount': 3,
+ 'params': {
+ 'skip_download': True,
+ },
+ 'add_ie': ['Ooyala'],
+ },
# google redirect
{
'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE',
'info_dict': {
'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
'title': 'Zero Punctuation',
- 'description': 're:'
+ 'description': 're:.*groundbreaking video review series.*'
},
'playlist_mincount': 11,
},
'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
}
},
+ # Cinerama player
+ {
+ 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
+ 'info_dict': {
+ 'id': '730m_DandD_1901_512k',
+ 'ext': 'mp4',
+ 'uploader': 'www.abc.net.au',
+ 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
+ }
+ },
+ # embedded viddler video
+ {
+ 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
+ 'info_dict': {
+ 'id': '4d03aad9',
+ 'ext': 'mp4',
+ 'uploader': 'deadspin',
+ 'title': 'WALL-TO-GORTAT',
+ 'timestamp': 1422285291,
+ 'upload_date': '20150126',
+ },
+ 'add_ie': ['Viddler'],
+ }
]
def report_following_redirect(self, new_url):
# Maybe it's a direct link to a video?
# Be careful not to download the whole thing!
first_bytes = full_response.read(512)
- if not re.match(r'^\s*<', first_bytes.decode('utf-8', 'replace')):
+ if not is_html(first_bytes):
self._downloader.report_warning(
'URL could be a direct video link, returning it as such.')
upload_date = unified_strdate(
if mobj is not None:
return self.url_result(mobj.group('url'))
+ # Look for embedded Viddler player
+ mobj = re.search(
+ r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
+ webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'))
+
# Look for Ooyala videos
- mobj = (re.search(r'player.ooyala.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
- re.search(r'OO.Player.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage))
+ mobj = (re.search(r'player\.ooyala\.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
+ re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
+ re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage))
if mobj is not None:
return OoyalaIE._build_url_result(mobj.group('ec'))
+ # Look for multiple Ooyala embeds on SBN network websites
+ mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
+ if mobj is not None:
+ embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
+ if embeds:
+ return _playlist_from_matches(
+ embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala')
+
# Look for Aparat videos
mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
if mobj is not None:
found = filter_video(re.findall(r'''(?xs)
flowplayer\("[^"]+",\s*
\{[^}]+?\}\s*,
- \s*{[^}]+? ["']?clip["']?\s*:\s*\{\s*
+ \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
["']?url["']?\s*:\s*["']([^"']+)["']
''', webpage))
+ if not found:
+ # Cinerama player
+ found = re.findall(
+ r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
if not found:
# Try to find twitter cards info
found = filter_video(re.findall(
'like_count': int,
}
},
+ {
+ 'url': 'http://globotv.globo.com/canal-brasil/sangue-latino/t/todos-os-videos/v/ator-e-diretor-argentino-ricado-darin-fala-sobre-utopias-e-suas-perdas/3928201/',
+ 'md5': 'c1defca721ce25b2354e927d3e4b3dec',
+ 'info_dict': {
+ 'id': '3928201',
+ 'ext': 'mp4',
+ 'title': 'Ator e diretor argentino, Ricado Darín fala sobre utopias e suas perdas',
+ 'duration': 1472.906,
+ 'uploader': 'Canal Brasil',
+ 'uploader_id': 705,
+ 'like_count': int,
+ }
+ },
]
class MD5():
signed_md5 = self.MD5.b64_md5(received_md5 + compat_str(sign_time) + padding)
signed_hash = hash_code + compat_str(received_time) + received_random + compat_str(sign_time) + padding + signed_md5
- formats.append({
- 'url': '%s?h=%s&k=%s' % (resource['url'], signed_hash, 'flash'),
- 'format_id': resource_id,
- 'height': resource['height']
- })
+ resource_url = resource['url']
+ signed_url = '%s?h=%s&k=%s' % (resource_url, signed_hash, 'flash')
+ if resource_id.endswith('m3u8') or resource_url.endswith('.m3u8'):
+ formats.extend(self._extract_m3u8_formats(signed_url, resource_id, 'mp4'))
+ else:
+ formats.append({
+ 'url': signed_url,
+ 'format_id': resource_id,
+ 'height': resource.get('height'),
+ })
self._sort_formats(formats)
return compat_urlparse.urlunparse((uri.scheme, uri.netloc, obj['attrs']['data'], None, None, None))
def _transform_bootstrap(self, js):
- return re.split('(?m)^\s*try\s*{', js)[0] \
+ return re.split('(?m)^\s*try\s*\{', js)[0] \
.split(' = ', 1)[1].strip().rstrip(';')
def _transform_meta(self, js):
--- /dev/null
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import (
+ compat_urllib_request,
+ compat_urlparse,
+)
+from ..utils import (
+ HEADRequest,
+ str_to_int,
+ urlencode_postdata,
+ urlhandle_detect_ext,
+)
+
+
+class HearThisAtIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?hearthis\.at/(?P<artist>[^/]+)/(?P<title>[A-Za-z0-9\-]+)/?$'
+ _PLAYLIST_URL = 'https://hearthis.at/playlist.php'
+ _TEST = {
+ 'url': 'https://hearthis.at/moofi/dr-kreep',
+ 'md5': 'ab6ec33c8fed6556029337c7885eb4e0',
+ 'info_dict': {
+ 'id': '150939',
+ 'ext': 'wav',
+ 'title': 'Moofi - Dr. Kreep',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'timestamp': 1421564134,
+ 'description': 'Creepy Patch. Mutable Instruments Braids Vowel + Formant Mode.',
+ 'upload_date': '20150118',
+ 'comment_count': int,
+ 'view_count': int,
+ 'like_count': int,
+ 'duration': 71,
+ 'categories': ['Experimental'],
+ }
+ }
+
+ def _real_extract(self, url):
+ m = re.match(self._VALID_URL, url)
+ display_id = '{artist:s} - {title:s}'.format(**m.groupdict())
+
+ webpage = self._download_webpage(url, display_id)
+ track_id = self._search_regex(
+ r'intTrackId\s*=\s*(\d+)', webpage, 'track ID')
+
+ payload = urlencode_postdata({'tracks[]': track_id})
+ req = compat_urllib_request.Request(self._PLAYLIST_URL, payload)
+ req.add_header('Content-type', 'application/x-www-form-urlencoded')
+
+ track = self._download_json(req, track_id, 'Downloading playlist')[0]
+ title = '{artist:s} - {title:s}'.format(**track)
+
+ categories = None
+ if track.get('category'):
+ categories = [track['category']]
+
+ description = self._og_search_description(webpage)
+ thumbnail = self._og_search_thumbnail(webpage)
+
+ meta_span = r'<span[^>]+class="%s".*?</i>([^<]+)</span>'
+ view_count = str_to_int(self._search_regex(
+ meta_span % 'plays_count', webpage, 'view count', fatal=False))
+ like_count = str_to_int(self._search_regex(
+ meta_span % 'likes_count', webpage, 'like count', fatal=False))
+ comment_count = str_to_int(self._search_regex(
+ meta_span % 'comment_count', webpage, 'comment count', fatal=False))
+ duration = str_to_int(self._search_regex(
+ r'data-length="(\d+)', webpage, 'duration', fatal=False))
+ timestamp = str_to_int(self._search_regex(
+ r'<span[^>]+class="calctime"[^>]+data-time="(\d+)', webpage, 'timestamp', fatal=False))
+
+ formats = []
+ mp3_url = self._search_regex(
+ r'(?s)<a class="player-link"\s+(?:[a-zA-Z0-9_:-]+="[^"]+"\s+)*?data-mp3="([^"]+)"',
+ webpage, 'mp3 URL', fatal=False)
+ if mp3_url:
+ formats.append({
+ 'format_id': 'mp3',
+ 'vcodec': 'none',
+ 'acodec': 'mp3',
+ 'url': mp3_url,
+ })
+ download_path = self._search_regex(
+ r'<a class="[^"]*download_fct[^"]*"\s+href="([^"]+)"',
+ webpage, 'download URL', default=None)
+ if download_path:
+ download_url = compat_urlparse.urljoin(url, download_path)
+ ext_req = HEADRequest(download_url)
+ ext_handle = self._request_webpage(
+ ext_req, display_id, note='Determining extension')
+ ext = urlhandle_detect_ext(ext_handle)
+ formats.append({
+ 'format_id': 'download',
+ 'vcodec': 'none',
+ 'ext': ext,
+ 'url': download_url,
+ 'preference': 2, # Usually better quality
+ })
+ self._sort_formats(formats)
+
+ return {
+ 'id': track_id,
+ 'display_id': display_id,
+ 'title': title,
+ 'formats': formats,
+ 'thumbnail': thumbnail,
+ 'description': description,
+ 'duration': duration,
+ 'timestamp': timestamp,
+ 'view_count': view_count,
+ 'comment_count': comment_count,
+ 'like_count': like_count,
+ 'categories': categories,
+ }
--- /dev/null
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import parse_duration
+
+
+class HistoricFilmsIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?historicfilms\.com/(?:tapes/|play)(?P<id>\d+)'
+ _TEST = {
+ 'url': 'http://www.historicfilms.com/tapes/4728',
+ 'md5': 'd4a437aec45d8d796a38a215db064e9a',
+ 'info_dict': {
+ 'id': '4728',
+ 'ext': 'mov',
+ 'title': 'Historic Films: GP-7',
+ 'description': 'md5:1a86a0f3ac54024e419aba97210d959a',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 2096,
+ },
+ }
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, video_id)
+
+ tape_id = self._search_regex(
+ r'class="tapeId">([^<]+)<', webpage, 'tape id')
+
+ title = self._og_search_title(webpage)
+ description = self._og_search_description(webpage)
+ thumbnail = self._html_search_meta(
+ 'thumbnailUrl', webpage, 'thumbnails') or self._og_search_thumbnail(webpage)
+ duration = parse_duration(self._html_search_meta(
+ 'duration', webpage, 'duration'))
+
+ video_url = 'http://www.historicfilms.com/video/%s_%s_web.mov' % (tape_id, video_id)
+
+ return {
+ 'id': video_id,
+ 'url': video_url,
+ 'title': title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'duration': duration,
+ }
class IviIE(InfoExtractor):
IE_DESC = 'ivi.ru'
IE_NAME = 'ivi'
- _VALID_URL = r'https?://(?:www\.)?ivi\.ru/(?:watch/(?:[^/]+/)?|video/player\?.*?videoId=)(?P<videoid>\d+)'
+ _VALID_URL = r'https?://(?:www\.)?ivi\.ru/(?:watch/(?:[^/]+/)?|video/player\?.*?videoId=)(?P<id>\d+)'
_TESTS = [
# Single movie
return int(m.group('commentcount')) if m is not None else 0
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('videoid')
+ video_id = self._match_id(url)
api_url = 'http://api.digitalaccess.ru/api/json/'
- data = {'method': 'da.content.get',
- 'params': [video_id, {'site': 's183',
- 'referrer': 'http://www.ivi.ru/watch/%s' % video_id,
- 'contentid': video_id
- }
- ]
+ data = {
+ 'method': 'da.content.get',
+ 'params': [
+ video_id, {
+ 'site': 's183',
+ 'referrer': 'http://www.ivi.ru/watch/%s' % video_id,
+ 'contentid': video_id
}
+ ]
+ }
request = compat_urllib_request.Request(api_url, json.dumps(data))
- video_json_page = self._download_webpage(request, video_id, 'Downloading video JSON')
+ video_json_page = self._download_webpage(
+ request, video_id, 'Downloading video JSON')
video_json = json.loads(video_json_page)
if 'error' in video_json:
error = video_json['error']
if error['origin'] == 'NoRedisValidData':
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
- raise ExtractorError('Unable to download video %s: %s' % (video_id, error['message']), expected=True)
+ raise ExtractorError(
+ 'Unable to download video %s: %s' % (video_id, error['message']),
+ expected=True)
result = video_json['result']
_TEST = {
'url': 'http://yinyue.kankan.com/vod/48/48863.shtml',
- 'file': '48863.flv',
'md5': '29aca1e47ae68fc28804aca89f29507e',
'info_dict': {
+ 'id': '48863',
+ 'ext': 'flv',
'title': 'Ready To Go',
},
'skip': 'Only available from China',
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._search_regex(r'(?:G_TITLE=|G_MOVIE_TITLE = )[\'"](.+?)[\'"]', webpage, 'video title')
from ..compat import (
compat_urllib_parse_urlparse,
compat_urllib_request,
- compat_urllib_parse,
-)
-from ..aes import (
- aes_decrypt_text
)
_VALID_URL = r'https?://(?:www\.)?keezmovies\.com/video/.+?(?P<id>[0-9]+)(?:[/?&]|$)'
_TEST = {
'url': 'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711',
- 'file': '1214711.mp4',
'md5': '6e297b7e789329923fcf83abb67c9289',
'info_dict': {
+ 'id': '1214711',
+ 'ext': 'mp4',
'title': 'Petite Asian Lady Mai Playing In Bathtub',
'age_limit': 18,
}
embedded_url = mobj.group(1)
return self.url_result(embedded_url)
- video_title = self._html_search_regex(r'<h1 [^>]*>([^<]+)', webpage, 'title')
- video_url = compat_urllib_parse.unquote(self._html_search_regex(r'video_url=(.+?)&', webpage, 'video_url'))
- if 'encrypted=true' in webpage:
- password = self._html_search_regex(r'video_title=(.+?)&', webpage, 'password')
- video_url = aes_decrypt_text(video_url, password, 32).decode('utf-8')
+ video_title = self._html_search_regex(
+ r'<h1 [^>]*>([^<]+)', webpage, 'title')
+ video_url = self._html_search_regex(
+ r'(?s)html5VideoPlayer = .*?src="([^"]+)"', webpage, 'video URL')
path = compat_urllib_parse_urlparse(video_url).path
extension = os.path.splitext(path)[1][1:]
format = path.split('/')[4].split('_')[:2]
from __future__ import unicode_literals
import json
-import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
- unescapeHTML,
+ js_to_json,
)
class KrasViewIE(InfoExtractor):
IE_DESC = 'Красвью'
- _VALID_URL = r'https?://krasview\.ru/video/(?P<id>\d+)'
+ _VALID_URL = r'https?://krasview\.ru/(?:video|embed)/(?P<id>\d+)'
_TEST = {
'url': 'http://krasview.ru/video/512228',
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
- flashvars = json.loads(self._search_regex(
- r'flashvars\s*:\s*({.+?})\s*}\);', webpage, 'flashvars'))
+ flashvars = json.loads(js_to_json(self._search_regex(
+ r'video_Init\(({.+?})', webpage, 'flashvars')))
video_url = flashvars['url']
- title = unescapeHTML(flashvars['title'])
- description = unescapeHTML(flashvars.get('subtitle') or self._og_search_description(webpage, default=None))
- thumbnail = flashvars['image']
- duration = int(flashvars['duration'])
- filesize = int(flashvars['size'])
+ title = self._og_search_title(webpage)
+ description = self._og_search_description(webpage, default=None)
+ thumbnail = flashvars.get('image') or self._og_search_thumbnail(webpage)
+ duration = int_or_none(flashvars.get('duration'))
width = int_or_none(self._og_search_property('video:width', webpage, 'video width'))
height = int_or_none(self._og_search_property('video:height', webpage, 'video height'))
'description': description,
'thumbnail': thumbnail,
'duration': duration,
- 'filesize': filesize,
'width': width,
'height': height,
}
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
from ..utils import (
parse_duration,
_TEST = {
'url': 'http://www.la7.tv/richplayer/?assetid=50355319',
- 'file': '50355319.mp4',
'md5': 'ec7d1f0224d20ba293ab56cf2259651f',
'info_dict': {
+ 'id': '50355319',
+ 'ext': 'mp4',
'title': 'IL DIVO',
'description': 'Un film di Paolo Sorrentino con Toni Servillo, Anna Bonaiuto, Giulio Bosetti e Flavio Bucci',
'duration': 6254,
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
-
+ video_id = self._match_id(url)
xml_url = 'http://www.la7.tv/repliche/content/index.php?contentId=%s' % video_id
doc = self._download_xml(xml_url, video_id)
class LiveLeakIE(InfoExtractor):
- _VALID_URL = r'^(?:http://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)'
+ _VALID_URL = r'https?://(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<id>[\w_]+)(?:.*)'
_TESTS = [{
'url': 'http://www.liveleak.com/view?i=757_1364311680',
- 'md5': '0813c2430bea7a46bf13acf3406992f4',
+ 'md5': '50f79e05ba149149c1b4ea961223d5b3',
'info_dict': {
'id': '757_1364311680',
- 'ext': 'mp4',
+ 'ext': 'flv',
'description': 'extremely bad day for this guy..!',
'uploader': 'ljfriel2',
'title': 'Most unlucky car accident'
}
}, {
'url': 'http://www.liveleak.com/view?i=f93_1390833151',
- 'md5': 'd3f1367d14cc3c15bf24fbfbe04b9abf',
+ 'md5': 'b13a29626183c9d33944e6a04f41aafc',
'info_dict': {
'id': 'f93_1390833151',
'ext': 'mp4',
}]
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('video_id')
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_title = self._og_search_title(webpage).replace('LiveLeak.com -', '').strip()
sources = json.loads(sources_json)
formats = [{
+ 'format_id': '%s' % i,
'format_note': s.get('label'),
'url': s['file'],
- } for s in sources]
+ } for i, s in enumerate(sources)]
+ for i, s in enumerate(sources):
+ orig_url = s['file'].replace('.h264_base.mp4', '')
+ if s['file'] != orig_url:
+ formats.append({
+ 'format_id': 'original-%s' % i,
+ 'format_note': s.get('label'),
+ 'url': orig_url,
+ 'preference': 1,
+ })
self._sort_formats(formats)
return {
from .common import InfoExtractor
from ..utils import (
int_or_none,
- js_to_json,
unified_strdate,
)
class LnkGoIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?lnkgo\.alfa\.lt/visi\-video/(?P<show>[^/]+)/ziurek\-(?P<display_id>[A-Za-z0-9\-]+)'
+ _VALID_URL = r'https?://(?:www\.)?lnkgo\.alfa\.lt/visi-video/(?P<show>[^/]+)/ziurek-(?P<id>[A-Za-z0-9-]+)'
_TESTS = [{
'url': 'http://lnkgo.alfa.lt/visi-video/yra-kaip-yra/ziurek-yra-kaip-yra-162',
'info_dict': {
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- display_id = mobj.group('display_id')
+ display_id = self._match_id(url)
webpage = self._download_webpage(
url, display_id, 'Downloading player webpage')
r'data-ep="([^"]+)"', webpage, 'video ID')
title = self._og_search_title(webpage)
description = self._og_search_description(webpage)
+ upload_date = unified_strdate(self._search_regex(
+ r'class="[^"]*meta-item[^"]*air-time[^"]*">.*?<strong>([^<]+)</strong>', webpage, 'upload date', fatal=False))
thumbnail_w = int_or_none(
self._og_search_property('image:width', webpage, 'thumbnail width', fatal=False))
'height': thumbnail_h,
})
- upload_date = unified_strdate(self._search_regex(
- r'class="meta-item\sair-time">.*?<strong>([^<]+)</strong>', webpage, 'upload date', fatal=False))
- duration = int_or_none(self._search_regex(
- r'VideoDuration = "([^"]+)"', webpage, 'duration', fatal=False))
+ config = self._parse_json(self._search_regex(
+ r'episodePlayer\((\{.*?\}),\s*\{', webpage, 'sources'), video_id)
- pg_rating = self._search_regex(
- r'pgrating="([^"]+)"', webpage, 'PG rating', fatal=False, default='')
- age_limit = self._AGE_LIMITS.get(pg_rating.upper(), 0)
+ if config.get('pGeo'):
+ self.report_warning(
+ 'This content might not be available in your country due to copyright reasons')
- sources_js = self._search_regex(
- r'(?s)sources:\s(\[.*?\]),', webpage, 'sources')
- sources = self._parse_json(
- sources_js, video_id, transform_source=js_to_json)
+ formats = [{
+ 'format_id': 'hls',
+ 'ext': 'mp4',
+ 'url': config['EpisodeVideoLink_HLS'],
+ }]
- formats = []
- for source in sources:
- if source.get('provider') == 'rtmp':
- m = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<play_path>.+)$', source['file'])
- if not m:
- continue
- formats.append({
- 'format_id': 'rtmp',
- 'ext': 'flv',
- 'url': m.group('url'),
- 'play_path': m.group('play_path'),
- 'page_url': url,
- })
- elif source.get('file').endswith('.m3u8'):
- formats.append({
- 'format_id': 'hls',
- 'ext': source.get('type', 'mp4'),
- 'url': source['file'],
- })
+ m = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<play_path>.+)$', config['EpisodeVideoLink'])
+ if m:
+ formats.append({
+ 'format_id': 'rtmp',
+ 'ext': 'flv',
+ 'url': m.group('url'),
+ 'play_path': m.group('play_path'),
+ 'page_url': url,
+ })
self._sort_formats(formats)
'title': title,
'formats': formats,
'thumbnails': [thumbnail],
- 'duration': duration,
+ 'duration': int_or_none(config.get('VideoTime')),
'description': description,
- 'age_limit': age_limit,
+ 'age_limit': self._AGE_LIMITS.get(config.get('PGRating'), 0),
'upload_date': upload_date,
}
} for format_id, video_url in prioritized_streams['0'].items()
])
+ self._check_formats(formats, video_id)
self._sort_formats(formats)
if self._downloader.params.get('listsubtitles', False):
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
from ..utils import ExtractorError
_TEST = {
'url': 'http://www.macgamestore.com/mediaviewer.php?trailer=2450',
- 'file': '2450.m4v',
'md5': '8649b8ea684b6666b4c5be736ecddc61',
'info_dict': {
+ 'id': '2450',
+ 'ext': 'm4v',
'title': 'Crow',
}
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
-
- webpage = self._download_webpage(url, video_id, 'Downloading trailer page')
+ video_id = self._match_id(url)
+ webpage = self._download_webpage(
+ url, video_id, 'Downloading trailer page')
- if re.search(r'>Missing Media<', webpage) is not None:
- raise ExtractorError('Trailer %s does not exist' % video_id, expected=True)
+ if '>Missing Media<' in webpage:
+ raise ExtractorError(
+ 'Trailer %s does not exist' % video_id, expected=True)
video_title = self._html_search_regex(
r'<title>MacGameStore: (.*?) Trailer</title>', webpage, 'title')
from ..utils import (
ExtractorError,
HEADRequest,
- int_or_none,
+ str_to_int,
parse_iso8601,
)
_VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([^/]+)/([^/]+)'
IE_NAME = 'mixcloud'
- _TEST = {
+ _TESTS = [{
'url': 'http://www.mixcloud.com/dholbach/cryptkeeper/',
'info_dict': {
'id': 'dholbach-cryptkeeper',
'view_count': int,
'like_count': int,
},
- }
+ }, {
+ 'url': 'http://www.mixcloud.com/gillespeterson/caribou-7-inch-vinyl-mix-chat/',
+ 'info_dict': {
+ 'id': 'gillespeterson-caribou-7-inch-vinyl-mix-chat',
+ 'ext': 'm4a',
+ 'title': 'Electric Relaxation vol. 3',
+ 'description': 'md5:2b8aec6adce69f9d41724647c65875e8',
+ 'uploader': 'Daniel Drumz',
+ 'uploader_id': 'gillespeterson',
+ 'thumbnail': 're:https?://.*\.jpg',
+ 'view_count': int,
+ 'like_count': int,
+ },
+ }]
def _get_url(self, track_id, template_url):
server_count = 30
webpage = self._download_webpage(url, track_id)
preview_url = self._search_regex(
- r'\s(?:data-preview-url|m-preview)="(.+?)"', webpage, 'preview url')
+ r'\s(?:data-preview-url|m-preview)="([^"]+)"', webpage, 'preview url')
song_url = preview_url.replace('/previews/', '/c/originals/')
template_url = re.sub(r'(stream\d*)', 'stream%d', song_url)
final_song_url = self._get_url(track_id, template_url)
uploader_id = self._search_regex(
r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False)
description = self._og_search_description(webpage)
- like_count = int_or_none(self._search_regex(
- r'<meta itemprop="interactionCount" content="UserLikes:([0-9]+)"',
+ like_count = str_to_int(self._search_regex(
+ [r'<meta itemprop="interactionCount" content="UserLikes:([0-9]+)"',
+ r'/favorites/?">([0-9]+)<'],
webpage, 'like count', fatal=False))
- view_count = int_or_none(self._search_regex(
- r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',
+ view_count = str_to_int(self._search_regex(
+ [r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',
+ r'/listeners/?">([0-9,.]+)</a>'],
webpage, 'play count', fatal=False))
timestamp = parse_iso8601(self._search_regex(
r'<time itemprop="dateCreated" datetime="([^"]+)">',
- webpage, 'upload date'))
+ webpage, 'upload date', default=None))
return {
'id': track_id,
from __future__ import unicode_literals
-import json
-import re
-
from .common import InfoExtractor
from ..utils import int_or_none
class MporaIE(InfoExtractor):
- _VALID_URL = r'^https?://(www\.)?mpora\.(?:com|de)/videos/(?P<id>[^?#/]+)'
+ _VALID_URL = r'https?://(www\.)?mpora\.(?:com|de)/videos/(?P<id>[^?#/]+)'
IE_NAME = 'MPORA'
_TEST = {
'url': 'http://mpora.de/videos/AAdo8okx4wiz/embed?locale=de',
- 'file': 'AAdo8okx4wiz.mp4',
'md5': 'a7a228473eedd3be741397cf452932eb',
'info_dict': {
+ 'id': 'AAdo8okx4wiz',
+ 'ext': 'mp4',
'title': 'Katy Curd - Winter in the Forest',
'duration': 416,
'uploader': 'Peter Newman Media',
}
def _real_extract(self, url):
- m = re.match(self._VALID_URL, url)
- video_id = m.group('id')
-
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
+
data_json = self._search_regex(
r"new FM\.Player\('[^']+',\s*(\{.*?)\).player;", webpage, 'json')
-
- data = json.loads(data_json)
+ data = self._parse_json(data_json, video_id)
uploader = data['info_overlay'].get('username')
duration = data['video']['duration'] // 1000
import re
-from .common import InfoExtractor
+from .subtitles import SubtitlesInfoExtractor
from ..compat import (
compat_urllib_parse,
compat_urllib_request,
+ compat_str,
)
from ..utils import (
ExtractorError,
return '{http://search.yahoo.com/mrss/}%s' % tag
-class MTVServicesInfoExtractor(InfoExtractor):
+class MTVServicesInfoExtractor(SubtitlesInfoExtractor):
_MOBILE_TEMPLATE = None
@staticmethod
webpage_url = self._MOBILE_TEMPLATE % mtvn_id
req = compat_urllib_request.Request(webpage_url)
# Otherwise we get a webpage that would execute some javascript
- req.add_header('Youtubedl-user-agent', 'curl/7')
+ req.add_header('User-Agent', 'curl/7')
webpage = self._download_webpage(req, mtvn_id,
'Downloading mobile page')
metrics_url = unescapeHTML(self._search_regex(r'<a href="(http://metrics.+?)"', webpage, 'url'))
try:
_, _, ext = rendition.attrib['type'].partition('/')
rtmp_video_url = rendition.find('./src').text
- formats.append({'ext': ext,
- 'url': self._transform_rtmp_url(rtmp_video_url),
- 'format_id': rendition.get('bitrate'),
- 'width': int(rendition.get('width')),
- 'height': int(rendition.get('height')),
- })
+ if rtmp_video_url.endswith('siteunavail.png'):
+ continue
+ formats.append({
+ 'ext': ext,
+ 'url': self._transform_rtmp_url(rtmp_video_url),
+ 'format_id': rendition.get('bitrate'),
+ 'width': int(rendition.get('width')),
+ 'height': int(rendition.get('height')),
+ })
except (KeyError, TypeError):
raise ExtractorError('Invalid rendition field.')
self._sort_formats(formats)
return formats
+ def _extract_subtitles(self, mdoc, mtvn_id):
+ subtitles = {}
+ FORMATS = {
+ 'scc': 'cea-608',
+ 'eia-608': 'cea-608',
+ 'xml': 'ttml',
+ }
+ subtitles_format = FORMATS.get(
+ self._downloader.params.get('subtitlesformat'), 'ttml')
+ for transcript in mdoc.findall('.//transcript'):
+ if transcript.get('kind') != 'captions':
+ continue
+ lang = transcript.get('srclang')
+ for typographic in transcript.findall('./typographic'):
+ captions_format = typographic.get('format')
+ if captions_format == subtitles_format:
+ subtitles[lang] = compat_str(typographic.get('src'))
+ break
+ if self._downloader.params.get('listsubtitles', False):
+ self._list_available_subtitles(mtvn_id, subtitles)
+ return self.extract_subtitles(mtvn_id, subtitles)
+
def _get_video_info(self, itemdoc):
uri = itemdoc.find('guid').text
video_id = self._id_from_uri(uri)
return {
'title': title,
'formats': self._extract_video_formats(mediagen_doc, mtvn_id),
+ 'subtitles': self._extract_subtitles(mediagen_doc, mtvn_id),
'id': video_id,
'thumbnail': self._get_thumbnail_url(uri, itemdoc),
'description': description,
mgid = self._search_regex(
[r'data-mgid="(.*?)"', r'swfobject.embedSWF\(".*?(mgid:.*?)"'],
webpage, 'mgid')
- return self._get_videos_info(mgid)
+
+ videos_info = self._get_videos_info(mgid)
+ if self._downloader.params.get('listsubtitles', False):
+ return
+ return videos_info
class MTVServicesEmbeddedIE(MTVServicesInfoExtractor):
_TESTS = [
{
'url': 'http://www.mtv.com/videos/misc/853555/ours-vh1-storytellers.jhtml',
- 'file': '853555.mp4',
'md5': '850f3f143316b1e71fa56a4edfd6e0f8',
'info_dict': {
+ 'id': '853555',
+ 'ext': 'mp4',
'title': 'Taylor Swift - "Ours (VH1 Storytellers)"',
'description': 'Album: Taylor Swift performs "Ours" for VH1 Storytellers at Harvey Mudd College.',
},
},
- {
- 'add_ie': ['Vevo'],
- 'url': 'http://www.mtv.com/videos/taylor-swift/916187/everything-has-changed-ft-ed-sheeran.jhtml',
- 'file': 'USCJY1331283.mp4',
- 'md5': '73b4e7fcadd88929292fe52c3ced8caf',
- 'info_dict': {
- 'title': 'Everything Has Changed',
- 'upload_date': '20130606',
- 'uploader': 'Taylor Swift',
- },
- 'skip': 'VEVO is only available in some countries',
- },
]
def _get_thumbnail_url(self, uri, itemdoc):
webpage = self._download_webpage(url, video_id)
# Some videos come from Vevo.com
- m_vevo = re.search(r'isVevoVideo = true;.*?vevoVideoId = "(.*?)";',
- webpage, re.DOTALL)
+ m_vevo = re.search(
+ r'(?s)isVevoVideo = true;.*?vevoVideoId = "(.*?)";', webpage)
if m_vevo:
vevo_id = m_vevo.group(1)
self.to_screen('Vevo video detected: %s' % vevo_id)
from .common import InfoExtractor
from ..compat import (
compat_str,
+ compat_HTTPError,
)
from ..utils import (
ExtractorError,
},
'add_ie': ['ThePlatform'],
},
+ {
+ 'url': 'http://www.nbcnews.com/feature/dateline-full-episodes/full-episode-family-business-n285156',
+ 'md5': 'fdbf39ab73a72df5896b6234ff98518a',
+ 'info_dict': {
+ 'id': 'Wjf9EDR3A_60',
+ 'ext': 'mp4',
+ 'title': 'FULL EPISODE: Family Business',
+ 'description': 'md5:757988edbaae9d7be1d585eb5d55cc04',
+ },
+ },
]
def _real_extract(self, url):
if not base_url:
continue
playlist_url = base_url + '?form=MPXNBCNewsAPI'
- all_videos = self._download_json(playlist_url, title)['videos']
try:
- info = next(v for v in all_videos if v['mpxId'] == mpxid)
+ all_videos = self._download_json(playlist_url, title)
+ except ExtractorError as ee:
+ if isinstance(ee.cause, compat_HTTPError):
+ continue
+ raise
+
+ if not all_videos or 'videos' not in all_videos:
+ continue
+
+ try:
+ info = next(v for v in all_videos['videos'] if v['mpxId'] == mpxid)
break
except StopIteration:
continue
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
-
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
filename = self._search_regex(
_TEST = {
'url': 'http://www.nerdcubed.co.uk/feed.json',
'info_dict': {
+ 'id': 'nerdcubed-feed',
'title': 'nerdcubed.co.uk feed',
},
'playlist_mincount': 1300,
--- /dev/null
+# encoding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+from ..utils import (
+ determine_ext,
+ parse_iso8601,
+ xpath_text,
+)
+
+
+class NerdistIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?nerdist\.com/vepisode/(?P<id>[^/?#]+)'
+ _TEST = {
+ 'url': 'http://www.nerdist.com/vepisode/exclusive-which-dc-characters-w',
+ 'md5': '3698ed582931b90d9e81e02e26e89f23',
+ 'info_dict': {
+ 'display_id': 'exclusive-which-dc-characters-w',
+ 'id': 'RPHpvJyr',
+ 'ext': 'mp4',
+ 'title': 'Your TEEN TITANS Revealed! Who\'s on the show?',
+ 'thumbnail': 're:^https?://.*/thumbs/.*\.jpg$',
+ 'description': 'Exclusive: Find out which DC Comics superheroes will star in TEEN TITANS Live-Action TV Show on Nerdist News with Jessica Chobot!',
+ 'uploader': 'Eric Diaz',
+ 'upload_date': '20150202',
+ 'timestamp': 1422892808,
+ }
+ }
+
+ def _real_extract(self, url):
+ display_id = self._match_id(url)
+ webpage = self._download_webpage(url, display_id)
+
+ video_id = self._search_regex(
+ r'''(?x)<script\s+(?:type="text/javascript"\s+)?
+ src="https?://content\.nerdist\.com/players/([a-zA-Z0-9_]+)-''',
+ webpage, 'video ID')
+ timestamp = parse_iso8601(self._html_search_meta(
+ 'shareaholic:article_published_time', webpage, 'upload date'))
+ uploader = self._html_search_meta(
+ 'shareaholic:article_author_name', webpage, 'article author')
+
+ doc = self._download_xml(
+ 'http://content.nerdist.com/jw6/%s.xml' % video_id, video_id)
+ video_info = doc.find('.//item')
+ title = xpath_text(video_info, './title', fatal=True)
+ description = xpath_text(video_info, './description')
+ thumbnail = xpath_text(
+ video_info, './{http://rss.jwpcdn.com/}image', 'thumbnail')
+
+ formats = []
+ for source in video_info.findall('./{http://rss.jwpcdn.com/}source'):
+ vurl = source.attrib['file']
+ ext = determine_ext(vurl)
+ if ext == 'm3u8':
+ formats.extend(self._extract_m3u8_formats(
+ vurl, video_id, entry_protocol='m3u8_native', ext='mp4',
+ preference=0))
+ elif ext == 'smil':
+ formats.extend(self._extract_smil_formats(
+ vurl, video_id, fatal=False
+ ))
+ else:
+ formats.append({
+ 'format_id': ext,
+ 'url': vurl,
+ })
+ self._sort_formats(formats)
+
+ return {
+ 'id': video_id,
+ 'display_id': display_id,
+ 'title': title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'timestamp': timestamp,
+ 'formats': formats,
+ 'uploader': uploader,
+ }
--- /dev/null
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import parse_iso8601
+
+
+class NextMediaIE(InfoExtractor):
+ _VALID_URL = r'http://hk.apple.nextmedia.com/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)'
+ _TESTS = [{
+ 'url': 'http://hk.apple.nextmedia.com/realtime/news/20141108/53109199',
+ 'md5': 'dff9fad7009311c421176d1ac90bfe4f',
+ 'info_dict': {
+ 'id': '53109199',
+ 'ext': 'mp4',
+ 'title': '【佔領金鐘】50外國領事議員撐場 讚學生勇敢香港有希望',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'description': 'md5:28222b9912b6665a21011b034c70fcc7',
+ 'timestamp': 1415456273,
+ 'upload_date': '20141108',
+ }
+ }]
+
+ _URL_PATTERN = r'\{ url: \'(.+)\' \}'
+
+ def _real_extract(self, url):
+ news_id = self._match_id(url)
+ page = self._download_webpage(url, news_id)
+ return self._extract_from_nextmedia_page(news_id, url, page)
+
+ def _extract_from_nextmedia_page(self, news_id, url, page):
+ title = self._fetch_title(page)
+ video_url = self._search_regex(self._URL_PATTERN, page, 'video url')
+
+ attrs = {
+ 'id': news_id,
+ 'title': title,
+ 'url': video_url, # ext can be inferred from url
+ 'thumbnail': self._fetch_thumbnail(page),
+ 'description': self._fetch_description(page),
+ }
+
+ timestamp = self._fetch_timestamp(page)
+ if timestamp:
+ attrs['timestamp'] = timestamp
+ else:
+ attrs['upload_date'] = self._fetch_upload_date(url)
+
+ return attrs
+
+ def _fetch_title(self, page):
+ return self._og_search_title(page)
+
+ def _fetch_thumbnail(self, page):
+ return self._og_search_thumbnail(page)
+
+ def _fetch_timestamp(self, page):
+ dateCreated = self._search_regex('"dateCreated":"([^"]+)"', page, 'created time')
+ return parse_iso8601(dateCreated)
+
+ def _fetch_upload_date(self, url):
+ return self._search_regex(self._VALID_URL, url, 'upload date', group='date')
+
+ def _fetch_description(self, page):
+ return self._og_search_property('description', page)
+
+
+class NextMediaActionNewsIE(NextMediaIE):
+ _VALID_URL = r'http://hk.dv.nextmedia.com/actionnews/[^/]+/(?P<date>\d+)/(?P<id>\d+)/\d+'
+ _TESTS = [{
+ 'url': 'http://hk.dv.nextmedia.com/actionnews/hit/20150121/19009428/20061460',
+ 'md5': '05fce8ffeed7a5e00665d4b7cf0f9201',
+ 'info_dict': {
+ 'id': '19009428',
+ 'ext': 'mp4',
+ 'title': '【壹週刊】細10年男友偷食 50歲邵美琪再失戀',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'description': 'md5:cd802fad1f40fd9ea178c1e2af02d659',
+ 'timestamp': 1421791200,
+ 'upload_date': '20150120',
+ }
+ }]
+
+ def _real_extract(self, url):
+ news_id = self._match_id(url)
+ actionnews_page = self._download_webpage(url, news_id)
+ article_url = self._og_search_url(actionnews_page)
+ article_page = self._download_webpage(article_url, news_id)
+ return self._extract_from_nextmedia_page(news_id, url, article_page)
+
+
+class AppleDailyRealtimeNewsIE(NextMediaIE):
+ _VALID_URL = r'http://(www|ent).appledaily.com.tw/(realtimenews|enews)/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
+ _TESTS = [{
+ 'url': 'http://ent.appledaily.com.tw/enews/article/entertainment/20150128/36354694',
+ 'md5': 'a843ab23d150977cc55ef94f1e2c1e4d',
+ 'info_dict': {
+ 'id': '36354694',
+ 'ext': 'mp4',
+ 'title': '周亭羽走過摩鐵陰霾2男陪吃 九把刀孤寒看醫生',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'description': 'md5:b23787119933404ce515c6356a8c355c',
+ 'upload_date': '20150128',
+ }
+ }, {
+ 'url': 'http://www.appledaily.com.tw/realtimenews/article/strange/20150128/550549/%E4%B8%8D%E6%BB%BF%E8%A2%AB%E8%B8%A9%E8%85%B3%E3%80%80%E5%B1%B1%E6%9D%B1%E5%85%A9%E5%A4%A7%E5%AA%BD%E4%B8%80%E8%B7%AF%E6%89%93%E4%B8%8B%E8%BB%8A',
+ 'md5': '86b4e9132d158279c7883822d94ccc49',
+ 'info_dict': {
+ 'id': '550549',
+ 'ext': 'mp4',
+ 'title': '不滿被踩腳 山東兩大媽一路打下車',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'description': 'md5:2648aaf6fc4f401f6de35a91d111aa1d',
+ 'upload_date': '20150128',
+ }
+ }]
+
+ _URL_PATTERN = r'\{url: \'(.+)\'\}'
+
+ def _fetch_title(self, page):
+ return self._html_search_regex(r'<h1 id="h1">([^<>]+)</h1>', page, 'news title')
+
+ def _fetch_thumbnail(self, page):
+ return self._html_search_regex(r"setInitialImage\(\'([^']+)'\)", page, 'video thumbnail', fatal=False)
+
+ def _fetch_timestamp(self, page):
+ return None
+
+
+class AppleDailyAnimationNewsIE(AppleDailyRealtimeNewsIE):
+ _VALID_URL = 'http://www.appledaily.com.tw/animation/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
+ _TESTS = [{
+ 'url': 'http://www.appledaily.com.tw/animation/realtimenews/new/20150128/5003671',
+ 'md5': '03df296d95dedc2d5886debbb80cb43f',
+ 'info_dict': {
+ 'id': '5003671',
+ 'ext': 'mp4',
+ 'title': '20正妹熱舞 《刀龍傳說Online》火辣上市',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'description': 'md5:23c0aac567dc08c9c16a3161a2c2e3cd',
+ 'upload_date': '20150128',
+ }
+ }, {
+ # No thumbnail
+ 'url': 'http://www.appledaily.com.tw/animation/realtimenews/new/20150128/5003673/',
+ 'md5': 'b06182cd386ea7bc6115ec7ff0f72aeb',
+ 'info_dict': {
+ 'id': '5003673',
+ 'ext': 'mp4',
+ 'title': '半夜尿尿 好像會看到___',
+ 'description': 'md5:61d2da7fe117fede148706cdb85ac066',
+ 'upload_date': '20150128',
+ },
+ 'expected_warnings': [
+ 'video thumbnail',
+ ]
+ }]
+
+ def _fetch_title(self, page):
+ return self._html_search_meta('description', page, 'news title')
+
+ def _fetch_description(self, page):
+ return self._html_search_meta('description', page, 'news description')
'timestamp': 1388354455,
'thumbnail': 're:^https?://.*\.jpg$',
}
- }
+ },
+ {
+ 'url': 'http://www.nfl.com/news/story/0ap3000000467586/article/patriots-seahawks-involved-in-lategame-skirmish',
+ 'info_dict': {
+ 'id': '0ap3000000467607',
+ 'ext': 'mp4',
+ 'title': 'Frustrations flare on the field',
+ 'description': 'Emotions ran high at the end of the Super Bowl on both sides of the ball after a dramatic finish.',
+ 'timestamp': 1422850320,
+ 'upload_date': '20150202',
+ },
+ },
]
@staticmethod
webpage = self._download_webpage(url, video_id)
config_url = NFLIE.prepend_host(host, self._search_regex(
- r'(?:config|configURL)\s*:\s*"([^"]+)"', webpage, 'config URL'))
+ r'(?:config|configURL)\s*:\s*"([^"]+)"', webpage, 'config URL',
+ default='static/content/static/config/video/config.json'))
+ # For articles, the id in the url is not the video id
+ video_id = self._search_regex(
+ r'contentId\s*:\s*"([^"]+)"', webpage, 'video id', default=video_id)
config = self._download_json(config_url, video_id,
note='Downloading player config')
url_template = NFLIE.prepend_host(
def _fix_json(json_string):
return json_string.replace('\\\'', '\'')
+ def _real_extract_video(self, video_id):
+ json_url = 'http://video.nhl.com/videocenter/servlets/playlist?ids=%s&format=json' % video_id
+ data = self._download_json(
+ json_url, video_id, transform_source=self._fix_json)
+ return self._extract_video(data[0])
+
def _extract_video(self, info):
video_id = info['id']
self.report_extraction(video_id)
class NHLIE(NHLBaseInfoExtractor):
IE_NAME = 'nhl.com'
- _VALID_URL = r'https?://video(?P<team>\.[^.]*)?\.nhl\.com/videocenter/console(?:\?(?:.*?[?&])?)id=(?P<id>[-0-9a-zA-Z]+)'
+ _VALID_URL = r'https?://video(?P<team>\.[^.]*)?\.nhl\.com/videocenter/(?:console)?(?:\?(?:.*?[?&])?)id=(?P<id>[-0-9a-zA-Z]+)'
_TESTS = [{
'url': 'http://video.canucks.nhl.com/videocenter/console?catid=6?id=453614',
}, {
'url': 'http://video.flames.nhl.com/videocenter/console?id=630616',
'only_matching': True,
+ }, {
+ 'url': 'http://video.nhl.com/videocenter/?id=736722',
+ 'only_matching': True,
}]
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
- json_url = 'http://video.nhl.com/videocenter/servlets/playlist?ids=%s&format=json' % video_id
- data = self._download_json(
- json_url, video_id, transform_source=self._fix_json)
- return self._extract_video(data[0])
+ video_id = self._match_id(url)
+ return self._real_extract_video(video_id)
+
+
+class NHLNewsIE(NHLBaseInfoExtractor):
+ IE_NAME = 'nhl.com:news'
+ IE_DESC = 'NHL news'
+ _VALID_URL = r'https?://(?:www\.)?nhl\.com/ice/news\.html?(?:\?(?:.*?[?&])?)id=(?P<id>[-0-9a-zA-Z]+)'
+
+ _TEST = {
+ 'url': 'http://www.nhl.com/ice/news.htm?id=750727',
+ 'md5': '4b3d1262e177687a3009937bd9ec0be8',
+ 'info_dict': {
+ 'id': '736722',
+ 'ext': 'mp4',
+ 'title': 'Cal Clutterbuck has been fined $2,000',
+ 'description': 'md5:45fe547d30edab88b23e0dd0ab1ed9e6',
+ 'duration': 37,
+ 'upload_date': '20150128',
+ },
+ }
+
+ def _real_extract(self, url):
+ news_id = self._match_id(url)
+ webpage = self._download_webpage(url, news_id)
+ video_id = self._search_regex(
+ [r'pVid(\d+)', r"nlid\s*:\s*'(\d+)'"],
+ webpage, 'video id')
+ return self._real_extract_video(video_id)
class NHLVideocenterIE(NHLBaseInfoExtractor):
# encoding: utf-8
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
from ..utils import (
class NormalbootsIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?normalboots\.com/video/(?P<videoid>[0-9a-z-]*)/?$'
+ _VALID_URL = r'http://(?:www\.)?normalboots\.com/video/(?P<id>[0-9a-z-]*)/?$'
_TEST = {
'url': 'http://normalboots.com/video/home-alone-games-jontron/',
'md5': '8bf6de238915dd501105b44ef5f1e0f6',
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('videoid')
-
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
- video_uploader = self._html_search_regex(r'Posted\sby\s<a\shref="[A-Za-z0-9/]*">(?P<uploader>[A-Za-z]*)\s</a>',
- webpage, 'uploader')
- raw_upload_date = self._html_search_regex('<span style="text-transform:uppercase; font-size:inherit;">[A-Za-z]+, (?P<date>.*)</span>',
- webpage, 'date')
- video_upload_date = unified_strdate(raw_upload_date)
- player_url = self._html_search_regex(r'<iframe\swidth="[0-9]+"\sheight="[0-9]+"\ssrc="(?P<url>[\S]+)"', webpage, 'url')
+ video_uploader = self._html_search_regex(
+ r'Posted\sby\s<a\shref="[A-Za-z0-9/]*">(?P<uploader>[A-Za-z]*)\s</a>',
+ webpage, 'uploader', fatal=False)
+ video_upload_date = unified_strdate(self._html_search_regex(
+ r'<span style="text-transform:uppercase; font-size:inherit;">[A-Za-z]+, (?P<date>.*)</span>',
+ webpage, 'date', fatal=False))
+
+ player_url = self._html_search_regex(
+ r'<iframe\swidth="[0-9]+"\sheight="[0-9]+"\ssrc="(?P<url>[\S]+)"',
+ webpage, 'player url')
player_page = self._download_webpage(player_url, video_id)
- video_url = self._html_search_regex(r"file:\s'(?P<file>[^']+\.mp4)'", player_page, 'file')
+ video_url = self._html_search_regex(
+ r"file:\s'(?P<file>[^']+\.mp4)'", player_page, 'file')
return {
'id': video_id,
from __future__ import unicode_literals
-from .common import InfoExtractor
+from .subtitles import SubtitlesInfoExtractor
from ..utils import (
fix_xml_ampersands,
parse_duration,
)
-class NPOBaseIE(InfoExtractor):
+class NPOBaseIE(SubtitlesInfoExtractor):
def _get_token(self, video_id):
token_page = self._download_webpage(
'http://ida.omroep.nl/npoplayer/i.js',
self._sort_formats(formats)
+ subtitles = {}
+ if metadata.get('tt888') == 'ja':
+ subtitles['nl'] = 'http://e.omroep.nl/tt888/%s' % video_id
+
+ if self._downloader.params.get('listsubtitles', False):
+ self._list_available_subtitles(video_id, subtitles)
+ return
+
+ subtitles = self.extract_subtitles(video_id, subtitles)
+
return {
'id': video_id,
'title': metadata['titel'],
'upload_date': unified_strdate(metadata.get('gidsdatum')),
'duration': parse_duration(metadata.get('tijdsduur')),
'formats': formats,
+ 'subtitles': subtitles,
}
--- /dev/null
+# encoding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+ int_or_none,
+ js_to_json,
+ parse_duration,
+)
+
+
+class NTVDeIE(InfoExtractor):
+ IE_NAME = 'n-tv.de'
+ _VALID_URL = r'https?://(?:www\.)?n-tv\.de/mediathek/videos/[^/?#]+/[^/?#]+-article(?P<id>.+)\.html'
+
+ _TESTS = [{
+ 'url': 'http://www.n-tv.de/mediathek/videos/panorama/Schnee-und-Glaette-fuehren-zu-zahlreichen-Unfaellen-und-Staus-article14438086.html',
+ 'md5': '6ef2514d4b1e8e03ca24b49e2f167153',
+ 'info_dict': {
+ 'id': '14438086',
+ 'ext': 'mp4',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'title': 'Schnee und Glätte führen zu zahlreichen Unfällen und Staus',
+ 'alt_title': 'Winterchaos auf deutschen Straßen',
+ 'description': 'Schnee und Glätte sorgen deutschlandweit für einen chaotischen Start in die Woche: Auf den Straßen kommt es zu kilometerlangen Staus und Dutzenden Glätteunfällen. In Düsseldorf und München wirbelt der Schnee zudem den Flugplan durcheinander. Dutzende Flüge landen zu spät, einige fallen ganz aus.',
+ 'duration': 4020,
+ 'timestamp': 1422892797,
+ 'upload_date': '20150202',
+ },
+ }]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ webpage = self._download_webpage(url, video_id)
+
+ info = self._parse_json(self._search_regex(
+ r'(?s)ntv.pageInfo.article =\s(\{.*?\});', webpage, 'info'),
+ video_id, transform_source=js_to_json)
+ timestamp = int_or_none(info.get('publishedDateAsUnixTimeStamp'))
+ vdata = self._parse_json(self._search_regex(
+ r'(?s)\$\(\s*"\#player"\s*\)\s*\.data\(\s*"player",\s*(\{.*?\})\);',
+ webpage, 'player data'),
+ video_id, transform_source=js_to_json)
+ duration = parse_duration(vdata.get('duration'))
+ formats = [{
+ 'format_id': 'flash',
+ 'url': 'rtmp://fms.n-tv.de/' + vdata['video'],
+ }, {
+ 'format_id': 'mobile',
+ 'url': 'http://video.n-tv.de' + vdata['videoMp4'],
+ 'tbr': 400, # estimation
+ }]
+ m3u8_url = 'http://video.n-tv.de' + vdata['videoM3u8']
+ formats.extend(self._extract_m3u8_formats(
+ m3u8_url, video_id, ext='mp4',
+ entry_protocol='m3u8_native', preference=0))
+ self._sort_formats(formats)
+
+ return {
+ 'id': video_id,
+ 'title': info['headline'],
+ 'description': info.get('intro'),
+ 'alt_title': info.get('kicker'),
+ 'timestamp': timestamp,
+ 'thumbnail': vdata.get('html5VideoPoster'),
+ 'duration': duration,
+ 'formats': formats,
+ }
# encoding: utf-8
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
from ..utils import (
unescapeHTML
)
-class NTVIE(InfoExtractor):
+class NTVRuIE(InfoExtractor):
+ IE_NAME = 'ntv.ru'
_VALID_URL = r'http://(?:www\.)?ntv\.ru/(?P<id>.+)'
_TESTS = [
]
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
-
+ video_id = self._match_id(url)
page = self._download_webpage(url, video_id)
video_id = self._html_search_regex(self._VIDEO_ID_REGEXES, page, 'video id')
compat_urllib_request,
)
from ..utils import (
+ ExtractorError,
str_to_int,
)
from ..aes import (
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id)
+ error_msg = self._html_search_regex(
+ r'(?s)<div class="userMessageSection[^"]*".*?>(.*?)</div>',
+ webpage, 'error message', default=None)
+ if error_msg:
+ error_msg = re.sub(r'\s+', ' ', error_msg)
+ raise ExtractorError(
+ 'PornHub said: %s' % error_msg,
+ expected=True, video_id=video_id)
+
video_title = self._html_search_regex(r'<h1 [^>]+>([^<]+)', webpage, 'title')
video_uploader = self._html_search_regex(
r'(?s)From: .+?<(?:a href="/users/|a href="/channels/|<span class="username)[^>]+>(.+?)<',
class RingTVIE(InfoExtractor):
- _VALID_URL = r'(?:http://)?(?:www\.)?ringtv\.craveonline\.com/(?P<type>news|videos/video)/(?P<id>[^/?#]+)'
+ _VALID_URL = r'http://(?:www\.)?ringtv\.craveonline\.com/(?P<type>news|videos/video)/(?P<id>[^/?#]+)'
_TEST = {
"url": "http://ringtv.craveonline.com/news/310833-luis-collazo-says-victor-ortiz-better-not-quit-on-jan-30",
- "file": "857645.mp4",
"md5": "d25945f5df41cdca2d2587165ac28720",
"info_dict": {
+ 'id': '857645',
+ 'ext': 'mp4',
"title": 'Video: Luis Collazo says Victor Ortiz "better not quit on Jan. 30" - Ring TV',
"description": 'Luis Collazo is excited about his Jan. 30 showdown with fellow former welterweight titleholder Victor Ortiz at Barclays Center in his hometown of Brooklyn. The SuperBowl week fight headlines a Golden Boy Live! card on Fox Sports 1.',
}
_TEST = {
'url': 'http://www.rottentomatoes.com/m/toy_story_3/trailers/11028566/',
- 'file': '613340.mp4',
'info_dict': {
+ 'id': '613340',
+ 'ext': 'mp4',
'title': 'TOY STORY 3',
'description': 'From the creators of the beloved TOY STORY films, comes a story that will reunite the gang in a whole new way.',
},
--- /dev/null
+# encoding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class RTL2IE(InfoExtractor):
+ _VALID_URL = r'http?://(?:www\.)?rtl2\.de/[^?#]*?/(?P<id>[^?#/]*?)(?:$|/(?:$|[?#]))'
+ _TESTS = [{
+ 'url': 'http://www.rtl2.de/sendung/grip-das-motormagazin/folge/folge-203-0',
+ 'md5': 'bfcc179030535b08dc2b36b469b5adc7',
+ 'info_dict': {
+ 'id': 'folge-203-0',
+ 'ext': 'f4v',
+ 'title': 'GRIP sucht den Sommerkönig',
+ 'description': 'Matthias, Det und Helge treten gegeneinander an.'
+ },
+ }, {
+ 'url': 'http://www.rtl2.de/sendung/koeln-50667/video/5512-anna/21040-anna-erwischt-alex/',
+ 'md5': 'ffcd517d2805b57ce11a58a2980c2b02',
+ 'info_dict': {
+ 'id': '21040-anna-erwischt-alex',
+ 'ext': 'mp4',
+ 'title': 'Anna erwischt Alex!',
+ 'description': 'Anna ist Alex\' Tochter bei Köln 50667.'
+ },
+ }]
+
+ def _real_extract(self, url):
+ # Some rtl2 urls have no slash at the end, so append it.
+ if not url.endswith('/'):
+ url += '/'
+
+ video_id = self._match_id(url)
+ webpage = self._download_webpage(url, video_id)
+
+ vico_id = self._html_search_regex(
+ r'vico_id\s*:\s*([0-9]+)', webpage, 'vico_id')
+ vivi_id = self._html_search_regex(
+ r'vivi_id\s*:\s*([0-9]+)', webpage, 'vivi_id')
+ info_url = 'http://www.rtl2.de/video/php/get_video.php?vico_id=' + vico_id + '&vivi_id=' + vivi_id
+ webpage = self._download_webpage(info_url, '')
+
+ info = self._download_json(info_url, video_id)
+ video_info = info['video']
+ title = video_info['titel']
+ description = video_info.get('beschreibung')
+ thumbnail = video_info.get('image')
+
+ download_url = video_info['streamurl']
+ download_url = download_url.replace('\\', '')
+ stream_url = 'mp4:' + self._html_search_regex(r'ondemand/(.*)', download_url, 'stream URL')
+ rtmp_conn = ["S:connect", "O:1", "NS:pageUrl:" + url, "NB:fpad:0", "NN:videoFunction:1", "O:0"]
+
+ formats = [{
+ 'url': download_url,
+ 'play_path': stream_url,
+ 'player_url': 'http://www.rtl2.de/flashplayer/vipo_player.swf',
+ 'page_url': url,
+ 'flash_version': 'LNX 11,2,202,429',
+ 'rtmp_conn': rtmp_conn,
+ 'no_resume': True,
+ }]
+ self._sort_formats(formats)
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'thumbnail': thumbnail,
+ 'description': description,
+ 'formats': formats,
+ }
'ext': ext,
'vcodec': config.get('type') == 'audio' and 'none' or None,
'player_url': 'http://programas.rtp.pt/play/player.swf?v3',
+ 'rtmp_real_time': True,
}]
return {
from .common import InfoExtractor
from ..compat import (
compat_str,
+ compat_urllib_parse_urlparse,
)
from ..utils import (
int_or_none,
parse_duration,
parse_iso8601,
unescapeHTML,
+ xpath_text,
)
return int_or_none(self._search_regex(
r'-([0-9]+)k\.', url, 'bitrate', default=None))
- formats = [{
- 'format_id': fid,
- 'url': furl,
- 'tbr': extract_bitrate(furl),
- } for fid, furl in info['streams'].items()]
+ formats = []
+ for format_id, format_url in info['streams'].items():
+ if format_url.endswith('.f4m'):
+ token = self._download_xml(
+ 'http://tp.srgssr.ch/token/akahd.xml?stream=%s/*' % compat_urllib_parse_urlparse(format_url).path,
+ video_id, 'Downloading %s token' % format_id)
+ auth_params = xpath_text(token, './/authparams', 'auth params')
+ if not auth_params:
+ continue
+ formats.extend(self._extract_f4m_formats(
+ '%s?%s&hdcore=3.4.0&plugin=aasp-3.4.0.132.66' % (format_url, auth_params),
+ video_id, f4m_id=format_id))
+ elif format_url.endswith('.m3u8'):
+ formats.extend(self._extract_m3u8_formats(
+ format_url, video_id, 'mp4', m3u8_id=format_id))
+ else:
+ formats.append({
+ 'format_id': format_id,
+ 'url': format_url,
+ 'tbr': extract_bitrate(format_url),
+ })
if 'media' in info:
formats.extend([{
class RTVEALaCartaIE(InfoExtractor):
IE_NAME = 'rtve.es:alacarta'
IE_DESC = 'RTVE a la carta'
- _VALID_URL = r'http://www\.rtve\.es/alacarta/videos/[^/]+/[^/]+/(?P<id>\d+)'
+ _VALID_URL = r'http://www\.rtve\.es/(m/)?alacarta/videos/[^/]+/[^/]+/(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/',
'id': '1694255',
'ext': 'flv',
'title': 'TODO',
- }
+ },
+ 'skip': 'The f4m manifest can\'t be used yet',
+ }, {
+ 'url': 'http://www.rtve.es/m/alacarta/videos/cuentame-como-paso/cuentame-como-paso-t16-ultimo-minuto-nuestra-vida-capitulo-276/2969138/?media=tve',
+ 'only_matching': True,
}]
def _real_extract(self, url):
png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % video_id
png = self._download_webpage(png_url, video_id, 'Downloading url information')
video_url = _decrypt_url(png)
+ if not video_url.endswith('.f4m'):
+ auth_url = video_url.replace(
+ 'resources/', 'auth/resources/'
+ ).replace('.net.rtve', '.multimedia.cdn.rtve')
+ video_path = self._download_webpage(
+ auth_url, video_id, 'Getting video url')
+ # Use mvod.akcdn instead of flash.akamaihd.multimedia.cdn to get
+ # the right Content-Length header and the mp4 format
+ video_url = (
+ 'http://mvod.akcdn.rtve.es/{0}&v=2.6.8'
+ '&fp=MAC%2016,0,0,296&r=MRUGG&g=OEOJWFXNFGCP'.format(video_path)
+ )
return {
'id': video_id,
'vbr': int(quality),
}
elif transport == 'm3u8':
- fmt = {
- 'url': url,
- 'ext': 'mp4',
- }
+ formats.extend(self._extract_m3u8_formats(url, video_id, 'mp4'))
+ continue
else:
fmt = {
'url': url
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
from ..utils import (
int_or_none,
_TEST = {
'url': 'http://bs.serving-sys.com/BurstingPipe/adServer.bs?cn=is&c=23&pl=VAST&pli=5349193&PluID=0&pos=7135&ord=[timestamp]&cim=1?',
+ 'info_dict': {
+ 'id': '5349193',
+ 'title': 'AdAPPter_Hyundai_demo',
+ },
'playlist': [{
- 'file': '29955898.flv',
'md5': 'baed851342df6846eb8677a60a011a0f',
'info_dict': {
+ 'id': '29955898',
+ 'ext': 'flv',
'title': 'AdAPPter_Hyundai_demo (1)',
'duration': 74,
'tbr': 1378,
'height': 400,
},
}, {
- 'file': '29907998.flv',
'md5': '979b4da2655c4bc2d81aeb915a8c5014',
'info_dict': {
+ 'id': '29907998',
+ 'ext': 'flv',
'title': 'AdAPPter_Hyundai_demo (2)',
'duration': 34,
'width': 854,
'params': {
'playlistend': 2,
},
- 'skip': 'Blocked in the US [sic]',
+ '_skip': 'Blocked in the US [sic]',
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- pl_id = mobj.group('id')
-
+ pl_id = self._match_id(url)
vast_doc = self._download_xml(url, pl_id)
+
title = vast_doc.find('.//AdTitle').text
media = vast_doc.find('.//MediaFile').text
info_url = self._search_regex(r'&adData=([^&]+)&', media, 'info URL')
class SinaIE(InfoExtractor):
- _VALID_URL = r'''https?://(.*?\.)?video\.sina\.com\.cn/
+ _VALID_URL = r'''(?x)https?://(.*?\.)?video\.sina\.com\.cn/
(
(.+?/(((?P<pseudo_id>\d+).html)|(.*?(\#|(vid=)|b/)(?P<id>\d+?)($|&|\-))))
|
_TESTS = [
{
'url': 'http://video.sina.com.cn/news/vlist/zt/chczlj2013/?opsubject_id=top12#110028898',
- 'file': '110028898.flv',
'md5': 'd65dd22ddcf44e38ce2bf58a10c3e71f',
'info_dict': {
+ 'id': '110028898',
+ 'ext': 'flv',
'title': '《中国新闻》 朝鲜要求巴拿马立即释放被扣船员',
}
},
},
]
- @classmethod
- def suitable(cls, url):
- return re.match(cls._VALID_URL, url, flags=re.VERBOSE) is not None
-
def _extract_video(self, video_id):
data = compat_urllib_parse.urlencode({'vid': video_id})
url_doc = self._download_xml('http://v.iask.com/v_play.php?%s' % data,
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE)
+ mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
if mobj.group('token') is not None:
# The video id is in the redirected url
'uploader_id': 'mopeder',
'duration': 71,
'thumbnail': 'http://frame9.loadup.ru/d7/32/2888853.2.3.jpg',
+ 'upload_date': '20150114',
},
},
# swf player
{
'url': 'http://pics.smotri.com/scrubber_custom8.swf?file=v9188090500',
- 'md5': '4d47034979d9390d14acdf59c4935bc2',
+ 'md5': '31099eeb4bc906712c5f40092045108d',
'info_dict': {
'id': 'v9188090500',
'ext': 'mp4',
def _search_meta(self, name, html, display_name=None):
if display_name is None:
display_name = name
- return self._html_search_regex(
- r'<meta itemprop="%s" content="([^"]+)" />' % re.escape(name),
- html, display_name, fatal=False)
return self._html_search_meta(name, html, display_name)
def _real_extract(self, url):
_TESTS = [{
'url': 'https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep',
'info_dict': {
+ 'id': '2284613',
'title': 'The Royal Concept EP',
},
'playlist_mincount': 6,
return {
'_type': 'playlist',
'entries': [self._extract_info_dict(track, secret_token=token) for track in info['tracks']],
- 'id': info['id'],
+ 'id': '%s' % info['id'],
'title': info['title'],
}
import re
from .common import InfoExtractor
-from ..compat import (
- compat_urlparse,
- compat_HTTPError,
-)
-from ..utils import (
- HEADRequest,
- ExtractorError,
-)
+from ..compat import compat_urlparse
from .spiegeltv import SpiegeltvIE
if n.tag.startswith('type') and n.tag != 'type6':
format_id = n.tag.rpartition('type')[2]
video_url = base_url + n.find('./filename').text
- # Test video URLs beforehand as some of them are invalid
- try:
- self._request_webpage(
- HEADRequest(video_url), video_id,
- 'Checking %s video URL' % format_id)
- except ExtractorError as e:
- if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
- self.report_warning(
- '%s video URL is invalid, skipping' % format_id, video_id)
- continue
formats.append({
'format_id': format_id,
'url': video_url,
})
duration = float(idoc[0].findall('./duration')[0].text)
+ self._check_formats(formats, video_id)
self._sort_formats(formats)
return {
from __future__ import unicode_literals
-import re
-
from .mtv import MTVServicesInfoExtractor
class SpikeIE(MTVServicesInfoExtractor):
_VALID_URL = r'''(?x)https?://
- (www\.spike\.com/(video-clips|episodes)/.+|
- m\.spike\.com/videos/video.rbml\?id=(?P<mobile_id>[^&]+))
+ (?:www\.spike\.com/(?:video-clips|(?:full-)?episodes)/.+|
+ m\.spike\.com/videos/video\.rbml\?id=(?P<id>[^&]+))
'''
_TEST = {
'url': 'http://www.spike.com/video-clips/lhtu8m/auction-hunters-can-allen-ride-a-hundred-year-old-motorcycle',
_MOBILE_TEMPLATE = 'http://m.spike.com/videos/video.rbml?id=%s'
def _real_extract(self, url):
- mobj = re.search(self._VALID_URL, url)
- mobile_id = mobj.group('mobile_id')
- if mobile_id is not None:
+ mobile_id = self._match_id(url)
+ if mobile_id:
url = 'http://www.spike.com/video-clips/%s' % mobile_id
return super(SpikeIE, self)._real_extract(url)
class SRMediathekIE(InfoExtractor):
- IE_DESC = 'Süddeutscher Rundfunk'
+ IE_DESC = 'Saarländischer Rundfunk'
_VALID_URL = r'https?://sr-mediathek\.sr-online\.de/index\.php\?.*?&id=(?P<id>[0-9]+)'
_TEST = {
--- /dev/null
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import unified_strdate
+
+
+class StreetVoiceIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:.+?\.)?streetvoice\.com/[^/]+/songs/(?P<id>[0-9]+)'
+ _TESTS = [{
+ 'url': 'http://streetvoice.com/skippylu/songs/94440/',
+ 'md5': '15974627fc01a29e492c98593c2fd472',
+ 'info_dict': {
+ 'id': '94440',
+ 'ext': 'mp3',
+ 'filesize': 4167053,
+ 'title': '輸',
+ 'description': 'Crispy脆樂團 - 輸',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 260,
+ 'upload_date': '20091018',
+ 'uploader': 'Crispy脆樂團',
+ 'uploader_id': '627810',
+ }
+ }, {
+ 'url': 'http://tw.streetvoice.com/skippylu/songs/94440/',
+ 'only_matching': True,
+ }]
+
+ def _real_extract(self, url):
+ song_id = self._match_id(url)
+
+ song = self._download_json(
+ 'http://streetvoice.com/music/api/song/%s' % song_id, song_id)
+
+ title = song['name']
+ author = song['musician']['name']
+
+ return {
+ 'id': song_id,
+ 'url': song['file'],
+ 'filesize': song.get('size'),
+ 'title': title,
+ 'description': '%s - %s' % (author, title),
+ 'thumbnail': self._proto_relative_url(song.get('image'), 'http:'),
+ 'duration': song.get('length'),
+ 'upload_date': unified_strdate(song.get('created_at')),
+ 'uploader': author,
+ 'uploader_id': compat_str(song['musician']['id']),
+ }
_TESTS = [
{
'url': 'http://teamcoco.com/video/80187/conan-becomes-a-mary-kay-beauty-consultant',
- 'file': '80187.mp4',
'md5': '3f7746aa0dc86de18df7539903d399ea',
'info_dict': {
+ 'id': '80187',
+ 'ext': 'mp4',
'title': 'Conan Becomes A Mary Kay Beauty Consultant',
'description': 'Mary Kay is perhaps the most trusted name in female beauty, so of course Conan is a natural choice to sell their products.'
}
}, {
'url': 'http://teamcoco.com/video/louis-ck-interview-george-w-bush',
- 'file': '19705.mp4',
'md5': 'cde9ba0fa3506f5f017ce11ead928f9a',
'info_dict': {
+ 'id': '19705',
+ 'ext': 'mp4',
"description": "Louis C.K. got starstruck by George W. Bush, so what? Part one.",
"title": "Louis C.K. Interview Pt. 1 11/3/11"
}
video_id = mobj.group("video_id")
if not video_id:
video_id = self._html_search_regex(
- r'data-node-id="(\d+?)"',
+ r'<div\s+class="player".*?data-id="(\d+?)"',
webpage, 'video id')
data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id
_TEST = {
'url': 'http://www.tele-task.de/archive/video/html5/26168/',
'info_dict': {
+ 'id': '26168',
'title': 'Duplicate Detection',
},
'playlist': [{
def _real_extract(self, url):
lecture_id = self._match_id(url)
-
webpage = self._download_webpage(url, lecture_id)
title = self._html_search_regex(
--- /dev/null
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+ int_or_none,
+ qualities,
+)
+
+
+class TestTubeIE(InfoExtractor):
+ _VALID_URL = r'https?://testtube\.com/[^/?#]+/(?P<id>[^/?#]+)'
+ _TESTS = [{
+ 'url': 'https://testtube.com/dnews/5-weird-ways-plants-can-eat-animals?utm_source=FB&utm_medium=DNews&utm_campaign=DNewsSocial',
+ 'info_dict': {
+ 'id': '60163',
+ 'display_id': '5-weird-ways-plants-can-eat-animals',
+ 'duration': 275,
+ 'ext': 'mp4',
+ 'title': '5 Weird Ways Plants Can Eat Animals',
+ 'description': 'Why have some plants evolved to eat meat?',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'uploader': 'DNews',
+ 'uploader_id': 'dnews',
+ },
+ }]
+
+ def _real_extract(self, url):
+ display_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, display_id)
+ video_id = self._search_regex(
+ r"player\.loadRevision3Item\('video_id',\s*([0-9]+)\);",
+ webpage, 'video ID')
+
+ all_info = self._download_json(
+ 'https://testtube.com/api/getPlaylist.json?api_key=ba9c741bce1b9d8e3defcc22193f3651b8867e62&codecs=h264,vp8,theora&video_id=%s' % video_id,
+ video_id)
+ info = all_info['items'][0]
+
+ formats = []
+ for vcodec, fdatas in info['media'].items():
+ for name, fdata in fdatas.items():
+ formats.append({
+ 'format_id': '%s-%s' % (vcodec, name),
+ 'url': fdata['url'],
+ 'vcodec': vcodec,
+ 'tbr': fdata.get('bitrate'),
+ })
+ self._sort_formats(formats)
+
+ duration = int_or_none(info.get('duration'))
+ images = info.get('images')
+ thumbnails = None
+ preference = qualities(['mini', 'small', 'medium', 'large'])
+ if images:
+ thumbnails = [{
+ 'id': thumbnail_id,
+ 'url': img_url,
+ 'preference': preference(thumbnail_id)
+ } for thumbnail_id, img_url in images.items()]
+
+ return {
+ 'id': video_id,
+ 'display_id': display_id,
+ 'title': info['title'],
+ 'description': info.get('summary'),
+ 'thumbnails': thumbnails,
+ 'uploader': info.get('show', {}).get('name'),
+ 'uploader_id': info.get('show', {}).get('slug'),
+ 'duration': duration,
+ 'formats': formats,
+ }
class TinyPicIE(InfoExtractor):
IE_NAME = 'tinypic'
IE_DESC = 'tinypic.com videos'
- _VALID_URL = r'http://tinypic\.com/player\.php\?v=(?P<id>[^&]+)&s=\d+'
-
- _TEST = {
- 'url': 'http://tinypic.com/player.php?v=6xw7tc%3E&s=5#.UtqZmbRFCM8',
- 'md5': '609b74432465364e72727ebc6203f044',
- 'info_dict': {
- 'id': '6xw7tc',
- 'ext': 'flv',
- 'title': 'shadow phenomenon weird',
+ _VALID_URL = r'http://(?:.+?\.)?tinypic\.com/player\.php\?v=(?P<id>[^&]+)&s=\d+'
+
+ _TESTS = [
+ {
+ 'url': 'http://tinypic.com/player.php?v=6xw7tc%3E&s=5#.UtqZmbRFCM8',
+ 'md5': '609b74432465364e72727ebc6203f044',
+ 'info_dict': {
+ 'id': '6xw7tc',
+ 'ext': 'flv',
+ 'title': 'shadow phenomenon weird',
+ },
+ },
+ {
+ 'url': 'http://de.tinypic.com/player.php?v=dy90yh&s=8',
+ 'only_matching': True,
}
- }
+ ]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
_TEST = {
'url': 'http://www.tou.tv/30-vies/S04E41',
- 'file': '30-vies_S04E41.mp4',
'info_dict': {
+ 'id': '30-vies_S04E41',
+ 'ext': 'mp4',
'title': '30 vies Saison 4 / Épisode 41',
'description': 'md5:da363002db82ccbe4dafeb9cab039b09',
'age_limit': 8,
_TESTS = [{
'url': 'http://vod.tvp.pl/filmy-fabularne/filmy-za-darmo/ogniem-i-mieczem/wideo/odc-2/4278035',
+ 'md5': 'cdd98303338b8a7f7abab5cd14092bf2',
'info_dict': {
'id': '4278035',
'ext': 'wmv',
'title': 'Ogniem i mieczem, odc. 2',
- 'description': 'Bohun dowiaduje się o złamaniu przez kniahinię danego mu słowa i wyrusza do Rozłogów. Helenie w ostatniej chwili udaje się uciec dzięki pomocy Zagłoby.',
},
}, {
'url': 'http://vod.tvp.pl/seriale/obyczajowe/czas-honoru/sezon-1-1-13/i-seria-odc-13/194536',
+ 'md5': '8aa518c15e5cc32dfe8db400dc921fbb',
'info_dict': {
'id': '194536',
'ext': 'mp4',
'title': 'Czas honoru, I seria – odc. 13',
- # 'description': 'WŁADEK\nCzesław prosi Marię o dostarczenie Władkowi zarazki tyfusu. Jeśli zachoruje zostanie przewieziony do szpitala skąd łatwiej będzie go odbić. Czy matka zdecyduje się zarazić syna? Karol odwiedza Wandę przyznaje się, że ją oszukiwał, ale ostrzega też, że grozi jej aresztowanie i nalega, żeby wyjechała z Warszawy. Czy dziewczyna zdecyduje się znów oddalić od ukochanego? Rozpoczyna się akcja odbicia Władka.',
},
}, {
'url': 'http://www.tvp.pl/there-can-be-anything-so-i-shortened-it/17916176',
+ 'md5': 'c3b15ed1af288131115ff17a17c19dda',
'info_dict': {
'id': '17916176',
'ext': 'mp4',
'title': 'TVP Gorzów pokaże filmy studentów z podroży dookoła świata',
},
- 'params': {
- # m3u8 download
- 'skip_download': 'true',
- },
}, {
'url': 'http://vod.tvp.pl/seriale/obyczajowe/na-sygnale/sezon-2-27-/odc-39/17834272',
+ 'md5': 'c3b15ed1af288131115ff17a17c19dda',
'info_dict': {
'id': '17834272',
'ext': 'mp4',
'title': 'Na sygnale, odc. 39',
- 'description': 'Ekipa Wiktora ratuje młodą matkę, która spadła ze schodów trzymając na rękach noworodka. Okazuje się, że dziewczyna jest surogatką, a biologiczni rodzice dziecka próbują zmusić ją do oddania synka…',
- },
- 'params': {
- # m3u8 download
- 'skip_download': 'true',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
+
webpage = self._download_webpage(
'http://www.tvp.pl/sess/tvplayer.php?object_id=%s' % video_id, video_id)
- title = self._og_search_title(webpage)
- series = self._search_regex(
- r'{name:\s*([\'"])SeriesTitle\1,\s*value:\s*\1(?P<series>.*?)\1},',
+ title = self._search_regex(
+ r'name\s*:\s*([\'"])Title\1\s*,\s*value\s*:\s*\1(?P<title>.+?)\1',
+ webpage, 'title', group='title')
+ series_title = self._search_regex(
+ r'name\s*:\s*([\'"])SeriesTitle\1\s*,\s*value\s*:\s*\1(?P<series>.+?)\1',
webpage, 'series', group='series', default=None)
- if series is not None and series not in title:
- title = '%s, %s' % (series, title)
- description = self._og_search_description(webpage, default=None)
+ if series_title:
+ title = '%s, %s' % (series_title, title)
+
+ thumbnail = self._search_regex(
+ r"poster\s*:\s*'([^']+)'", webpage, 'thumbnail', default=None)
video_url = self._search_regex(
r'0:{src:([\'"])(?P<url>.*?)\1', webpage, 'formats', group='url', default=None)
- if video_url is None:
+ if not video_url:
video_url = self._download_json(
'http://www.tvp.pl/pub/stat/videofileinfo?video_id=%s' % video_id,
video_id)['video_url']
return {
'id': video_id,
'title': title,
- 'thumbnail': self._og_search_thumbnail(webpage),
- 'description': description,
+ 'thumbnail': thumbnail,
'formats': formats,
}
--- /dev/null
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+ xpath_text,
+ xpath_with_ns,
+ int_or_none,
+ float_or_none,
+)
+
+
+class TweakersIE(InfoExtractor):
+ _VALID_URL = r'https?://tweakers\.net/video/(?P<id>\d+)'
+ _TEST = {
+ 'url': 'https://tweakers.net/video/9926/new-nintendo-3ds-xl-op-alle-fronten-beter.html',
+ 'md5': '1b5afa817403bb5baa08359dca31e6df',
+ 'info_dict': {
+ 'id': '9926',
+ 'ext': 'mp4',
+ 'title': 'New Nintendo 3DS XL - Op alle fronten beter',
+ 'description': 'md5:f97324cc71e86e11c853f0763820e3ba',
+ 'thumbnail': 're:^https?://.*\.jpe?g$',
+ 'duration': 386,
+ }
+ }
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ playlist = self._download_xml(
+ 'https://tweakers.net/video/s1playlist/%s/playlist.xspf' % video_id,
+ video_id)
+
+ NS_MAP = {
+ 'xspf': 'http://xspf.org/ns/0/',
+ 's1': 'http://static.streamone.nl/player/ns/0',
+ }
+
+ track = playlist.find(xpath_with_ns('./xspf:trackList/xspf:track', NS_MAP))
+
+ title = xpath_text(
+ track, xpath_with_ns('./xspf:title', NS_MAP), 'title')
+ description = xpath_text(
+ track, xpath_with_ns('./xspf:annotation', NS_MAP), 'description')
+ thumbnail = xpath_text(
+ track, xpath_with_ns('./xspf:image', NS_MAP), 'thumbnail')
+ duration = float_or_none(
+ xpath_text(track, xpath_with_ns('./xspf:duration', NS_MAP), 'duration'),
+ 1000)
+
+ formats = [{
+ 'url': location.text,
+ 'format_id': location.get(xpath_with_ns('s1:label', NS_MAP)),
+ 'width': int_or_none(location.get(xpath_with_ns('s1:width', NS_MAP))),
+ 'height': int_or_none(location.get(xpath_with_ns('s1:height', NS_MAP))),
+ } for location in track.findall(xpath_with_ns('./xspf:location', NS_MAP))]
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'duration': duration,
+ 'formats': formats,
+ }
import itertools
import re
+import random
from .common import InfoExtractor
from ..compat import (
+ compat_str,
compat_urllib_parse,
compat_urllib_request,
)
)
-class TwitchIE(InfoExtractor):
- # TODO: One broadcast may be split into multiple videos. The key
- # 'broadcast_id' is the same for all parts, and 'broadcast_part'
- # starts at 1 and increases. Can we treat all parts as one video?
- _VALID_URL = r"""(?x)^(?:http://)?(?:www\.)?twitch\.tv/
- (?:
- (?P<channelid>[^/]+)|
- (?:(?:[^/]+)/v/(?P<vodid>[^/]+))|
- (?:(?:[^/]+)/b/(?P<videoid>[^/]+))|
- (?:(?:[^/]+)/c/(?P<chapterid>[^/]+))
- )
- /?(?:\#.*)?$
- """
- _PAGE_LIMIT = 100
+class TwitchBaseIE(InfoExtractor):
+ _VALID_URL_BASE = r'https?://(?:www\.)?twitch\.tv'
+
_API_BASE = 'https://api.twitch.tv'
+ _USHER_BASE = 'http://usher.twitch.tv'
_LOGIN_URL = 'https://secure.twitch.tv/user/login'
- _TESTS = [{
- 'url': 'http://www.twitch.tv/riotgames/b/577357806',
- 'info_dict': {
- 'id': 'a577357806',
- 'title': 'Worlds Semifinals - Star Horn Royal Club vs. OMG',
- },
- 'playlist_mincount': 12,
- }, {
- 'url': 'http://www.twitch.tv/acracingleague/c/5285812',
- 'info_dict': {
- 'id': 'c5285812',
- 'title': 'ACRL Off Season - Sports Cars @ Nordschleife',
- },
- 'playlist_mincount': 3,
- }, {
- 'url': 'http://www.twitch.tv/vanillatv',
- 'info_dict': {
- 'id': 'vanillatv',
- 'title': 'VanillaTV',
- },
- 'playlist_mincount': 412,
- }]
def _handle_error(self, response):
if not isinstance(response, dict):
expected=True)
def _download_json(self, url, video_id, note='Downloading JSON metadata'):
- response = super(TwitchIE, self)._download_json(url, video_id, note)
+ response = super(TwitchBaseIE, self)._download_json(url, video_id, note)
self._handle_error(response)
return response
- def _extract_media(self, item, item_id):
- ITEMS = {
- 'a': 'video',
- 'v': 'vod',
- 'c': 'chapter',
+ def _real_initialize(self):
+ self._login()
+
+ def _login(self):
+ (username, password) = self._get_login_info()
+ if username is None:
+ return
+
+ login_page = self._download_webpage(
+ self._LOGIN_URL, None, 'Downloading login page')
+
+ authenticity_token = self._search_regex(
+ r'<input name="authenticity_token" type="hidden" value="([^"]+)"',
+ login_page, 'authenticity token')
+
+ login_form = {
+ 'utf8': '✓'.encode('utf-8'),
+ 'authenticity_token': authenticity_token,
+ 'redirect_on_login': '',
+ 'embed_form': 'false',
+ 'mp_source_action': '',
+ 'follow': '',
+ 'user[login]': username,
+ 'user[password]': password,
}
- info = self._extract_info(self._download_json(
+
+ request = compat_urllib_request.Request(
+ self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
+ request.add_header('Referer', self._LOGIN_URL)
+ response = self._download_webpage(
+ request, None, 'Logging in as %s' % username)
+
+ m = re.search(
+ r"id=([\"'])login_error_message\1[^>]*>(?P<msg>[^<]+)", response)
+ if m:
+ raise ExtractorError(
+ 'Unable to login: %s' % m.group('msg').strip(), expected=True)
+
+
+class TwitchItemBaseIE(TwitchBaseIE):
+ def _download_info(self, item, item_id):
+ return self._extract_info(self._download_json(
'%s/kraken/videos/%s%s' % (self._API_BASE, item, item_id), item_id,
- 'Downloading %s info JSON' % ITEMS[item]))
-
- if item == 'v':
- access_token = self._download_json(
- '%s/api/vods/%s/access_token' % (self._API_BASE, item_id), item_id,
- 'Downloading %s access token' % ITEMS[item])
- formats = self._extract_m3u8_formats(
- 'http://usher.twitch.tv/vod/%s?nauth=%s&nauthsig=%s'
- % (item_id, access_token['token'], access_token['sig']),
- item_id, 'mp4')
- info['formats'] = formats
- return info
+ 'Downloading %s info JSON' % self._ITEM_TYPE))
+ def _extract_media(self, item_id):
+ info = self._download_info(self._ITEM_SHORTCUT, item_id)
response = self._download_json(
- '%s/api/videos/%s%s' % (self._API_BASE, item, item_id), item_id,
- 'Downloading %s playlist JSON' % ITEMS[item])
+ '%s/api/videos/%s%s' % (self._API_BASE, self._ITEM_SHORTCUT, item_id), item_id,
+ 'Downloading %s playlist JSON' % self._ITEM_TYPE)
entries = []
chunks = response['chunks']
qualities = list(chunks.keys())
'view_count': info['views'],
}
- def _real_initialize(self):
- self._login()
+ def _real_extract(self, url):
+ return self._extract_media(self._match_id(url))
- def _login(self):
- (username, password) = self._get_login_info()
- if username is None:
- return
- login_page = self._download_webpage(
- self._LOGIN_URL, None, 'Downloading login page')
+class TwitchVideoIE(TwitchItemBaseIE):
+ IE_NAME = 'twitch:video'
+ _VALID_URL = r'%s/[^/]+/b/(?P<id>[^/]+)' % TwitchBaseIE._VALID_URL_BASE
+ _ITEM_TYPE = 'video'
+ _ITEM_SHORTCUT = 'a'
- authenticity_token = self._search_regex(
- r'<input name="authenticity_token" type="hidden" value="([^"]+)"',
- login_page, 'authenticity token')
+ _TEST = {
+ 'url': 'http://www.twitch.tv/riotgames/b/577357806',
+ 'info_dict': {
+ 'id': 'a577357806',
+ 'title': 'Worlds Semifinals - Star Horn Royal Club vs. OMG',
+ },
+ 'playlist_mincount': 12,
+ }
- login_form = {
- 'utf8': '✓'.encode('utf-8'),
- 'authenticity_token': authenticity_token,
- 'redirect_on_login': '',
- 'embed_form': 'false',
- 'mp_source_action': '',
- 'follow': '',
- 'user[login]': username,
- 'user[password]': password,
- }
- request = compat_urllib_request.Request(
- self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
- request.add_header('Referer', self._LOGIN_URL)
- response = self._download_webpage(
- request, None, 'Logging in as %s' % username)
+class TwitchChapterIE(TwitchItemBaseIE):
+ IE_NAME = 'twitch:chapter'
+ _VALID_URL = r'%s/[^/]+/c/(?P<id>[^/]+)' % TwitchBaseIE._VALID_URL_BASE
+ _ITEM_TYPE = 'chapter'
+ _ITEM_SHORTCUT = 'c'
- m = re.search(
- r"id=([\"'])login_error_message\1[^>]*>(?P<msg>[^<]+)", response)
- if m:
- raise ExtractorError(
- 'Unable to login: %s' % m.group('msg').strip(), expected=True)
+ _TESTS = [{
+ 'url': 'http://www.twitch.tv/acracingleague/c/5285812',
+ 'info_dict': {
+ 'id': 'c5285812',
+ 'title': 'ACRL Off Season - Sports Cars @ Nordschleife',
+ },
+ 'playlist_mincount': 3,
+ }, {
+ 'url': 'http://www.twitch.tv/tsm_theoddone/c/2349361',
+ 'only_matching': True,
+ }]
+
+
+class TwitchVodIE(TwitchItemBaseIE):
+ IE_NAME = 'twitch:vod'
+ _VALID_URL = r'%s/[^/]+/v/(?P<id>[^/]+)' % TwitchBaseIE._VALID_URL_BASE
+ _ITEM_TYPE = 'vod'
+ _ITEM_SHORTCUT = 'v'
+
+ _TEST = {
+ 'url': 'http://www.twitch.tv/ksptv/v/3622000',
+ 'info_dict': {
+ 'id': 'v3622000',
+ 'ext': 'mp4',
+ 'title': '''KSPTV: Squadcast: "Everyone's on vacation so here's Dahud" Edition!''',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 6951,
+ 'timestamp': 1419028564,
+ 'upload_date': '20141219',
+ 'uploader': 'KSPTV',
+ 'uploader_id': 'ksptv',
+ 'view_count': int,
+ },
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
+ }
+
+ def _real_extract(self, url):
+ item_id = self._match_id(url)
+ info = self._download_info(self._ITEM_SHORTCUT, item_id)
+ access_token = self._download_json(
+ '%s/api/vods/%s/access_token' % (self._API_BASE, item_id), item_id,
+ 'Downloading %s access token' % self._ITEM_TYPE)
+ formats = self._extract_m3u8_formats(
+ '%s/vod/%s?nauth=%s&nauthsig=%s'
+ % (self._USHER_BASE, item_id, access_token['token'], access_token['sig']),
+ item_id, 'mp4')
+ info['formats'] = formats
+ return info
+
+
+class TwitchPlaylistBaseIE(TwitchBaseIE):
+ _PLAYLIST_URL = '%s/kraken/channels/%%s/videos/?offset=%%d&limit=%%d' % TwitchBaseIE._API_BASE
+ _PAGE_LIMIT = 100
+
+ def _extract_playlist(self, channel_id):
+ info = self._download_json(
+ '%s/kraken/channels/%s' % (self._API_BASE, channel_id),
+ channel_id, 'Downloading channel info JSON')
+ channel_name = info.get('display_name') or info.get('name')
+ entries = []
+ offset = 0
+ limit = self._PAGE_LIMIT
+ for counter in itertools.count(1):
+ response = self._download_json(
+ self._PLAYLIST_URL % (channel_id, offset, limit),
+ channel_id, 'Downloading %s videos JSON page %d' % (self._PLAYLIST_TYPE, counter))
+ page_entries = self._extract_playlist_page(response)
+ if not page_entries:
+ break
+ entries.extend(page_entries)
+ offset += limit
+ return self.playlist_result(
+ [self.url_result(entry) for entry in set(entries)],
+ channel_id, channel_name)
+
+ def _extract_playlist_page(self, response):
+ videos = response.get('videos')
+ return [video['url'] for video in videos] if videos else []
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- if mobj.group('chapterid'):
- return self._extract_media('c', mobj.group('chapterid'))
+ return self._extract_playlist(self._match_id(url))
- """
- webpage = self._download_webpage(url, chapter_id)
- m = re.search(r'PP\.archive_id = "([0-9]+)";', webpage)
+
+class TwitchProfileIE(TwitchPlaylistBaseIE):
+ IE_NAME = 'twitch:profile'
+ _VALID_URL = r'%s/(?P<id>[^/]+)/profile/?(?:\#.*)?$' % TwitchBaseIE._VALID_URL_BASE
+ _PLAYLIST_TYPE = 'profile'
+
+ _TEST = {
+ 'url': 'http://www.twitch.tv/vanillatv/profile',
+ 'info_dict': {
+ 'id': 'vanillatv',
+ 'title': 'VanillaTV',
+ },
+ 'playlist_mincount': 412,
+ }
+
+
+class TwitchPastBroadcastsIE(TwitchPlaylistBaseIE):
+ IE_NAME = 'twitch:past_broadcasts'
+ _VALID_URL = r'%s/(?P<id>[^/]+)/profile/past_broadcasts/?(?:\#.*)?$' % TwitchBaseIE._VALID_URL_BASE
+ _PLAYLIST_URL = TwitchPlaylistBaseIE._PLAYLIST_URL + '&broadcasts=true'
+ _PLAYLIST_TYPE = 'past broadcasts'
+
+ _TEST = {
+ 'url': 'http://www.twitch.tv/spamfish/profile/past_broadcasts',
+ 'info_dict': {
+ 'id': 'spamfish',
+ 'title': 'Spamfish',
+ },
+ 'playlist_mincount': 54,
+ }
+
+
+class TwitchBookmarksIE(TwitchPlaylistBaseIE):
+ IE_NAME = 'twitch:bookmarks'
+ _VALID_URL = r'%s/(?P<id>[^/]+)/profile/bookmarks/?(?:\#.*)?$' % TwitchBaseIE._VALID_URL_BASE
+ _PLAYLIST_URL = '%s/api/bookmark/?user=%%s&offset=%%d&limit=%%d' % TwitchBaseIE._API_BASE
+ _PLAYLIST_TYPE = 'bookmarks'
+
+ _TEST = {
+ 'url': 'http://www.twitch.tv/ognos/profile/bookmarks',
+ 'info_dict': {
+ 'id': 'ognos',
+ 'title': 'Ognos',
+ },
+ 'playlist_mincount': 3,
+ }
+
+ def _extract_playlist_page(self, response):
+ entries = []
+ for bookmark in response.get('bookmarks', []):
+ video = bookmark.get('video')
+ if not video:
+ continue
+ entries.append(video['url'])
+ return entries
+
+
+class TwitchStreamIE(TwitchBaseIE):
+ IE_NAME = 'twitch:stream'
+ _VALID_URL = r'%s/(?P<id>[^/]+)/?(?:\#.*)?$' % TwitchBaseIE._VALID_URL_BASE
+
+ _TEST = {
+ 'url': 'http://www.twitch.tv/shroomztv',
+ 'info_dict': {
+ 'id': '12772022048',
+ 'display_id': 'shroomztv',
+ 'ext': 'mp4',
+ 'title': 're:^ShroomzTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+ 'description': 'H1Z1 - lonewolfing with ShroomzTV | A3 Battle Royale later - @ShroomzTV',
+ 'is_live': True,
+ 'timestamp': 1421928037,
+ 'upload_date': '20150122',
+ 'uploader': 'ShroomzTV',
+ 'uploader_id': 'shroomztv',
+ 'view_count': int,
+ },
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
+ }
+
+ def _real_extract(self, url):
+ channel_id = self._match_id(url)
+
+ stream = self._download_json(
+ '%s/kraken/streams/%s' % (self._API_BASE, channel_id), channel_id,
+ 'Downloading stream JSON').get('stream')
+
+ # Fallback on profile extraction if stream is offline
+ if not stream:
+ return self.url_result(
+ 'http://www.twitch.tv/%s/profile' % channel_id,
+ 'TwitchProfile', channel_id)
+
+ access_token = self._download_json(
+ '%s/api/channels/%s/access_token' % (self._API_BASE, channel_id), channel_id,
+ 'Downloading channel access token')
+
+ query = {
+ 'allow_source': 'true',
+ 'p': random.randint(1000000, 10000000),
+ 'player': 'twitchweb',
+ 'segment_preference': '4',
+ 'sig': access_token['sig'],
+ 'token': access_token['token'],
+ }
+
+ formats = self._extract_m3u8_formats(
+ '%s/api/channel/hls/%s.m3u8?%s'
+ % (self._USHER_BASE, channel_id, compat_urllib_parse.urlencode(query).encode('utf-8')),
+ channel_id, 'mp4')
+
+ view_count = stream.get('viewers')
+ timestamp = parse_iso8601(stream.get('created_at'))
+
+ channel = stream['channel']
+ title = self._live_title(channel.get('display_name') or channel.get('name'))
+ description = channel.get('status')
+
+ thumbnails = []
+ for thumbnail_key, thumbnail_url in stream['preview'].items():
+ m = re.search(r'(?P<width>\d+)x(?P<height>\d+)\.jpg$', thumbnail_key)
if not m:
- raise ExtractorError('Cannot find archive of a chapter')
- archive_id = m.group(1)
-
- api = api_base + '/broadcast/by_chapter/%s.xml' % chapter_id
- doc = self._download_xml(
- api, chapter_id,
- note='Downloading chapter information',
- errnote='Chapter information download failed')
- for a in doc.findall('.//archive'):
- if archive_id == a.find('./id').text:
- break
- else:
- raise ExtractorError('Could not find chapter in chapter information')
-
- video_url = a.find('./video_file_url').text
- video_ext = video_url.rpartition('.')[2] or 'flv'
-
- chapter_api_url = 'https://api.twitch.tv/kraken/videos/c' + chapter_id
- chapter_info = self._download_json(
- chapter_api_url, 'c' + chapter_id,
- note='Downloading chapter metadata',
- errnote='Download of chapter metadata failed')
-
- bracket_start = int(doc.find('.//bracket_start').text)
- bracket_end = int(doc.find('.//bracket_end').text)
-
- # TODO determine start (and probably fix up file)
- # youtube-dl -v http://www.twitch.tv/firmbelief/c/1757457
- #video_url += '?start=' + TODO:start_timestamp
- # bracket_start is 13290, but we want 51670615
- self._downloader.report_warning('Chapter detected, but we can just download the whole file. '
- 'Chapter starts at %s and ends at %s' % (formatSeconds(bracket_start), formatSeconds(bracket_end)))
-
- info = {
- 'id': 'c' + chapter_id,
- 'url': video_url,
- 'ext': video_ext,
- 'title': chapter_info['title'],
- 'thumbnail': chapter_info['preview'],
- 'description': chapter_info['description'],
- 'uploader': chapter_info['channel']['display_name'],
- 'uploader_id': chapter_info['channel']['name'],
- }
- return info
- """
- elif mobj.group('videoid'):
- return self._extract_media('a', mobj.group('videoid'))
- elif mobj.group('vodid'):
- return self._extract_media('v', mobj.group('vodid'))
- elif mobj.group('channelid'):
- channel_id = mobj.group('channelid')
- info = self._download_json(
- '%s/kraken/channels/%s' % (self._API_BASE, channel_id),
- channel_id, 'Downloading channel info JSON')
- channel_name = info.get('display_name') or info.get('name')
- entries = []
- offset = 0
- limit = self._PAGE_LIMIT
- for counter in itertools.count(1):
- response = self._download_json(
- '%s/kraken/channels/%s/videos/?offset=%d&limit=%d'
- % (self._API_BASE, channel_id, offset, limit),
- channel_id, 'Downloading channel videos JSON page %d' % counter)
- videos = response['videos']
- if not videos:
- break
- entries.extend([self.url_result(video['url'], 'Twitch') for video in videos])
- offset += limit
- return self.playlist_result(entries, channel_id, channel_name)
+ continue
+ thumbnails.append({
+ 'url': thumbnail_url,
+ 'width': int(m.group('width')),
+ 'height': int(m.group('height')),
+ })
+
+ return {
+ 'id': compat_str(stream['_id']),
+ 'display_id': channel_id,
+ 'title': title,
+ 'description': description,
+ 'thumbnails': thumbnails,
+ 'uploader': channel.get('display_name'),
+ 'uploader_id': channel.get('name'),
+ 'timestamp': timestamp,
+ 'view_count': view_count,
+ 'formats': formats,
+ 'is_live': True,
+ }
import re
from .common import InfoExtractor
-from ..utils import int_or_none
+from ..utils import (
+ int_or_none,
+ qualities,
+)
class UbuIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?ubu\.com/film/(?P<id>[\da-z_-]+)\.html'
_TEST = {
'url': 'http://ubu.com/film/her_noise.html',
- 'md5': '8edd46ee8aa6b265fb5ed6cf05c36bc9',
+ 'md5': '138d5652618bf0f03878978db9bef1ee',
'info_dict': {
'id': 'her_noise',
- 'ext': 'mp4',
+ 'ext': 'm4v',
'title': 'Her Noise - The Making Of (2007)',
'duration': 3600,
},
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
-
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(
r'<title>.+?Film & Video: ([^<]+)</title>', webpage, 'title')
duration = int_or_none(self._html_search_regex(
- r'Duration: (\d+) minutes', webpage, 'duration', fatal=False, default=None))
- if duration:
- duration *= 60
+ r'Duration: (\d+) minutes', webpage, 'duration', fatal=False),
+ invscale=60)
formats = []
-
FORMAT_REGEXES = [
- ['sq', r"'flashvars'\s*,\s*'file=([^']+)'"],
- ['hq', r'href="(http://ubumexico\.centro\.org\.mx/video/[^"]+)"']
+ ('sq', r"'flashvars'\s*,\s*'file=([^']+)'"),
+ ('hq', r'href="(http://ubumexico\.centro\.org\.mx/video/[^"]+)"'),
]
-
+ preference = qualities([fid for fid, _ in FORMAT_REGEXES])
for format_id, format_regex in FORMAT_REGEXES:
m = re.search(format_regex, webpage)
if m:
formats.append({
'url': m.group(1),
'format_id': format_id,
+ 'preference': preference(format_id),
})
+ self._sort_formats(formats)
return {
'id': video_id,
)
from ..utils import (
ExtractorError,
+ int_or_none,
)
# Download via HLS API
formats.extend(self._download_api_formats(video_id))
+ # Download SMIL
+ smil_blocks = sorted((
+ f for f in video_info['videoVersions']
+ if f['sourceType'] == 13),
+ key=lambda f: f['version'])
+ smil_url = '%s/Video/V2/VFILE/%s/%sr.smil' % (
+ self._SMIL_BASE_URL, video_id, video_id.lower())
+ if smil_blocks:
+ smil_url_m = self._search_regex(
+ r'url="([^"]+)"', smil_blocks[-1]['data'], 'SMIL URL',
+ default=None)
+ if smil_url_m is not None:
+ smil_url = smil_url_m
+ if smil_url:
+ smil_xml = self._download_webpage(
+ smil_url, video_id, 'Downloading SMIL info', fatal=False)
+ if smil_xml:
+ formats.extend(self._formats_from_smil(smil_xml))
+
self._sort_formats(formats)
- timestamp_ms = int(self._search_regex(
- r'/Date\((\d+)\)/', video_info['launchDate'], 'launch date'))
+ timestamp_ms = int_or_none(self._search_regex(
+ r'/Date\((\d+)\)/',
+ video_info['launchDate'], 'launch date', fatal=False))
return {
'id': video_id,
float_or_none,
int_or_none,
)
+from ..compat import (
+ compat_urllib_request
+)
class ViddlerIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?viddler\.com/(?:v|embed|player)/(?P<id>[a-z0-9]+)'
- _TEST = {
- "url": "http://www.viddler.com/v/43903784",
+ _TESTS = [{
+ 'url': 'http://www.viddler.com/v/43903784',
'md5': 'ae43ad7cb59431ce043f0ff7fa13cbf4',
'info_dict': {
'id': '43903784',
'ext': 'mp4',
- "title": "Video Made Easy",
- 'description': 'You don\'t need to be a professional to make high-quality video content. Viddler provides some quick and easy tips on how to produce great video content with limited resources. ',
- "uploader": "viddler",
+ 'title': 'Video Made Easy',
+ 'description': 'md5:6a697ebd844ff3093bd2e82c37b409cd',
+ 'uploader': 'viddler',
'timestamp': 1335371429,
'upload_date': '20120425',
- "duration": 100.89,
+ 'duration': 100.89,
'thumbnail': 're:^https?://.*\.jpg$',
'view_count': int,
+ 'comment_count': int,
'categories': ['video content', 'high quality video', 'video made easy', 'how to produce video with limited resources', 'viddler'],
}
- }
+ }, {
+ 'url': 'http://www.viddler.com/v/4d03aad9/',
+ 'md5': 'faa71fbf70c0bee7ab93076fd007f4b0',
+ 'info_dict': {
+ 'id': '4d03aad9',
+ 'ext': 'mp4',
+ 'title': 'WALL-TO-GORTAT',
+ 'upload_date': '20150126',
+ 'uploader': 'deadspin',
+ 'timestamp': 1422285291,
+ 'view_count': int,
+ 'comment_count': int,
+ }
+ }, {
+ 'url': 'http://www.viddler.com/player/221ebbbd/0/',
+ 'md5': '0defa2bd0ea613d14a6e9bd1db6be326',
+ 'info_dict': {
+ 'id': '221ebbbd',
+ 'ext': 'mp4',
+ 'title': 'LETeens-Grammar-snack-third-conditional',
+ 'description': ' ',
+ 'upload_date': '20140929',
+ 'uploader': 'BCLETeens',
+ 'timestamp': 1411997190,
+ 'view_count': int,
+ 'comment_count': int,
+ }
+ }]
def _real_extract(self, url):
video_id = self._match_id(url)
json_url = (
'http://api.viddler.com/api/v2/viddler.videos.getPlaybackDetails.json?video_id=%s&key=v0vhrt7bg2xq1vyxhkct' %
video_id)
- data = self._download_json(json_url, video_id)['video']
+ headers = {'Referer': 'http://static.cdn-ec.viddler.com/js/arpeggio/v2/embed.html'}
+ request = compat_urllib_request.Request(json_url, None, headers)
+ data = self._download_json(request, video_id)['video']
formats = []
for filed in data['files']:
if filed.get('status', 'ready') != 'ready':
continue
+ format_id = filed.get('profile_id') or filed['profile_name']
f = {
- 'format_id': filed['profile_id'],
+ 'format_id': format_id,
'format_note': filed['profile_name'],
'url': self._proto_relative_url(filed['url']),
'width': int_or_none(filed.get('width')),
if filed.get('cdn_url'):
f = f.copy()
- f['url'] = self._proto_relative_url(filed['cdn_url'])
- f['format_id'] = filed['profile_id'] + '-cdn'
+ f['url'] = self._proto_relative_url(filed['cdn_url'], 'http:')
+ f['format_id'] = format_id + '-cdn'
f['source_preference'] = 1
formats.append(f)
if filed.get('html5_video_source'):
f = f.copy()
- f['url'] = self._proto_relative_url(
- filed['html5_video_source'])
- f['format_id'] = filed['profile_id'] + '-html5'
+ f['url'] = self._proto_relative_url(filed['html5_video_source'])
+ f['format_id'] = format_id + '-html5'
f['source_preference'] = 0
formats.append(f)
self._sort_formats(formats)
t.get('text') for t in data.get('tags', []) if 'text' in t]
return {
- '_type': 'video',
'id': video_id,
'title': data['title'],
'formats': formats,
'uploader': data.get('author'),
'duration': float_or_none(data.get('length')),
'view_count': int_or_none(data.get('view_count')),
+ 'comment_count': int_or_none(data.get('comment_count')),
'categories': categories,
}
# coding: utf-8
from __future__ import unicode_literals
+import re
+
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
compat_urllib_request,
)
from ..utils import (
+ ExtractorError,
remove_start,
)
req.add_header('Referer', url)
webpage = self._download_webpage(req, video_id)
- escaped_data = self._search_regex(
- r'unescape\("([^"]+)"\)', webpage, 'escaped data')
+ try:
+ escaped_data = re.findall(r'unescape\("([^"]+)"\)', webpage)[-1]
+ except IndexError:
+ raise ExtractorError('Unable to extract escaped data')
+
playlist = compat_urllib_parse.unquote(escaped_data)
thumbnail = self._search_regex(
'title': title,
'formats': formats,
'thumbnail': thumbnail,
- 'http_referer': iframe_url,
+ 'http_headers': {
+ 'Referer': iframe_url,
+ },
}
class VideoTtIE(InfoExtractor):
ID_NAME = 'video.tt'
IE_DESC = 'video.tt - Your True Tube'
- _VALID_URL = r'http://(?:www\.)?video\.tt/(?:video/|watch_video\.php\?v=)(?P<id>[\da-zA-Z]{9})'
+ _VALID_URL = r'http://(?:www\.)?video\.tt/(?:(?:video|embed)/|watch_video\.php\?v=)(?P<id>[\da-zA-Z]{9})'
- _TEST = {
+ _TESTS = [{
'url': 'http://www.video.tt/watch_video.php?v=amd5YujV8',
'md5': 'b13aa9e2f267effb5d1094443dff65ba',
'info_dict': {
'upload_date': '20130827',
'uploader': 'joseph313',
}
- }
+ }, {
+ 'url': 'http://video.tt/embed/amd5YujV8',
+ 'only_matching': True,
+ }]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
_VALID_URL = r'https?://vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
_TESTS = [{
'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
- 'file': '75524534.mp4',
'md5': 'c507a72f780cacc12b2248bb4006d253',
'info_dict': {
+ 'id': '75524534',
+ 'ext': 'mp4',
'title': "DICK HARDWICK 'Comedian'",
'uploader': 'Richard Hardwick',
}
+# coding: utf-8
from __future__ import unicode_literals
import re
class WashingtonPostIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?washingtonpost\.com/.*?/(?P<id>[^/]+)/(?:$|[?#])'
- _TEST = {
+ _TESTS = [{
'url': 'http://www.washingtonpost.com/sf/national/2014/03/22/sinkhole-of-bureaucracy/',
'info_dict': {
+ 'id': 'sinkhole-of-bureaucracy',
'title': 'Sinkhole of bureaucracy',
},
'playlist': [{
'upload_date': '20140322',
'uploader': 'The Washington Post',
},
+ }],
+ }, {
+ 'url': 'http://www.washingtonpost.com/blogs/wonkblog/wp/2014/12/31/one-airline-figured-out-how-to-make-sure-its-airplanes-never-disappear/',
+ 'info_dict': {
+ 'id': 'one-airline-figured-out-how-to-make-sure-its-airplanes-never-disappear',
+ 'title': 'One airline figured out how to make sure its airplanes never disappear',
+ },
+ 'playlist': [{
+ 'md5': 'a7c1b5634ba5e57a6a82cdffa5b1e0d0',
+ 'info_dict': {
+ 'id': '0e4bb54c-9065-11e4-a66f-0ca5037a597d',
+ 'ext': 'mp4',
+ 'description': 'Washington Post transportation reporter Ashley Halsey III explains why a plane\'s black box needs to be recovered from a crash site instead of having its information streamed in real time throughout the flight.',
+ 'upload_date': '20141230',
+ 'uploader': 'The Washington Post',
+ 'timestamp': 1419974765,
+ 'title': 'Why black boxes don’t transmit data in real time',
+ }
}]
- }
+ }]
def _real_extract(self, url):
page_id = self._match_id(url)
webpage = self._download_webpage(url, page_id)
title = self._og_search_title(webpage)
- uuids = re.findall(r'data-video-uuid="([^"]+)"', webpage)
+
+ uuids = re.findall(r'''(?x)
+ (?:
+ <div\s+class="posttv-video-embed[^>]*?data-uuid=|
+ data-video-uuid=
+ )"([^"]+)"''', webpage)
entries = []
for i, uuid in enumerate(uuids, start=1):
vinfo_all = self._download_json(
'filesize': s.get('fileSize'),
'url': s.get('url'),
'ext': 'mp4',
+ 'preference': -100 if s.get('type') == 'smil' else None,
'protocol': {
'MP4': 'http',
'F4F': 'f4m',
- }.get(s.get('type'))
+ }.get(s.get('type')),
} for s in vinfo.get('streams', [])]
source_media_url = vinfo.get('sourceMediaURL')
if source_media_url:
{
'url': 'http://www1.wdr.de/mediathek/video/sendungen/quarks_und_co/filterseite-quarks-und-co100.html',
'playlist_mincount': 146,
+ 'info_dict': {
+ 'id': 'mediathek/video/sendungen/quarks_und_co/filterseite-quarks-und-co100',
+ }
}
]
'title': mobj.group('title'),
'age_limit': int(mobj.group('age_limit')),
'url': url,
- 'user_agent': 'mobile',
+ 'http_headers': {
+ 'User-Agent': 'mobile',
+ },
}
--- /dev/null
+# encoding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+ int_or_none,
+ unified_strdate,
+)
+
+
+class WSJIE(InfoExtractor):
+ _VALID_URL = r'https?://video-api\.wsj\.com/api-video/player/iframe\.html\?guid=(?P<id>[a-zA-Z0-9-]+)'
+ IE_DESC = 'Wall Street Journal'
+ _TEST = {
+ 'url': 'http://video-api.wsj.com/api-video/player/iframe.html?guid=1BD01A4C-BFE8-40A5-A42F-8A8AF9898B1A',
+ 'md5': '9747d7a6ebc2f4df64b981e1dde9efa9',
+ 'info_dict': {
+ 'id': '1BD01A4C-BFE8-40A5-A42F-8A8AF9898B1A',
+ 'ext': 'mp4',
+ 'upload_date': '20150202',
+ 'uploader_id': 'bbright',
+ 'creator': 'bbright',
+ 'categories': list, # a long list
+ 'duration': 90,
+ 'title': 'Bills Coach Rex Ryan Updates His Old Jets Tattoo',
+ },
+ }
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ bitrates = [128, 174, 264, 320, 464, 664, 1264]
+ api_url = (
+ 'http://video-api.wsj.com/api-video/find_all_videos.asp?'
+ 'type=guid&count=1&query=%s&'
+ 'fields=hls,adZone,thumbnailList,guid,state,secondsUntilStartTime,'
+ 'author,description,name,linkURL,videoStillURL,duration,videoURL,'
+ 'adCategory,catastrophic,linkShortURL,doctypeID,youtubeID,'
+ 'titletag,rssURL,wsj-section,wsj-subsection,allthingsd-section,'
+ 'allthingsd-subsection,sm-section,sm-subsection,provider,'
+ 'formattedCreationDate,keywords,keywordsOmniture,column,editor,'
+ 'emailURL,emailPartnerID,showName,omnitureProgramName,'
+ 'omnitureVideoFormat,linkRelativeURL,touchCastID,'
+ 'omniturePublishDate,%s') % (
+ video_id, ','.join('video%dkMP4Url' % br for br in bitrates))
+ info = self._download_json(api_url, video_id)['items'][0]
+
+ # Thumbnails are conveniently in the correct format already
+ thumbnails = info.get('thumbnailList')
+ creator = info.get('author')
+ uploader_id = info.get('editor')
+ categories = info.get('keywords')
+ duration = int_or_none(info.get('duration'))
+ upload_date = unified_strdate(
+ info.get('formattedCreationDate'), day_first=False)
+ title = info.get('name', info.get('titletag'))
+
+ formats = [{
+ 'format_id': 'f4m',
+ 'format_note': 'f4m (meta URL)',
+ 'url': info['videoURL'],
+ }]
+ if info.get('hls'):
+ formats.extend(self._extract_m3u8_formats(
+ info['hls'], video_id, ext='mp4',
+ preference=0, entry_protocol='m3u8_native'))
+ for br in bitrates:
+ field = 'video%dkMP4Url' % br
+ if info.get(field):
+ formats.append({
+ 'format_id': 'mp4-%d' % br,
+ 'container': 'mp4',
+ 'tbr': br,
+ 'url': info[field],
+ })
+ self._sort_formats(formats)
+
+ return {
+ 'id': video_id,
+ 'formats': formats,
+ 'thumbnails': thumbnails,
+ 'creator': creator,
+ 'uploader_id': uploader_id,
+ 'duration': duration,
+ 'upload_date': upload_date,
+ 'title': title,
+ 'formats': formats,
+ 'categories': categories,
+ }
--- /dev/null
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+import base64
+
+from .common import InfoExtractor
+from ..compat import compat_urllib_parse_unquote
+from ..utils import (
+ ExtractorError,
+ parse_iso8601,
+ parse_duration,
+)
+
+
+class XuiteIE(InfoExtractor):
+ _REGEX_BASE64 = r'(?:[A-Za-z0-9+/]{4})*(?:[A-Za-z0-9+/]{2}==|[A-Za-z0-9+/]{3}=)?'
+ _VALID_URL = r'https?://vlog\.xuite\.net/(?:play|embed)/(?P<id>%s)' % _REGEX_BASE64
+ _TESTS = [{
+ # Audio
+ 'url': 'http://vlog.xuite.net/play/RGkzc1ZULTM4NjA5MTQuZmx2',
+ 'md5': '63a42c705772aa53fd4c1a0027f86adf',
+ 'info_dict': {
+ 'id': '3860914',
+ 'ext': 'mp3',
+ 'title': '孤單南半球-歐德陽',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 247.246,
+ 'timestamp': 1314932940,
+ 'upload_date': '20110902',
+ 'uploader': '阿能',
+ 'uploader_id': '15973816',
+ 'categories': ['個人短片'],
+ },
+ }, {
+ # Video with only one format
+ 'url': 'http://vlog.xuite.net/play/TkRZNjhULTM0NDE2MjkuZmx2',
+ 'md5': 'c45737fc8ac5dc8ac2f92ecbcecf505e',
+ 'info_dict': {
+ 'id': '3441629',
+ 'ext': 'mp4',
+ 'title': '孫燕姿 - 眼淚成詩',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 217.399,
+ 'timestamp': 1299383640,
+ 'upload_date': '20110306',
+ 'uploader': 'Valen',
+ 'uploader_id': '10400126',
+ 'categories': ['影視娛樂'],
+ },
+ }, {
+ # Video with two formats
+ 'url': 'http://vlog.xuite.net/play/bWo1N1pLLTIxMzAxMTcwLmZsdg==',
+ 'md5': '1166e0f461efe55b62e26a2d2a68e6de',
+ 'info_dict': {
+ 'id': '21301170',
+ 'ext': 'mp4',
+ 'title': '暗殺教室 02',
+ 'description': '字幕:【極影字幕社】',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 1384.907,
+ 'timestamp': 1421481240,
+ 'upload_date': '20150117',
+ 'uploader': '我只是想認真點',
+ 'uploader_id': '242127761',
+ 'categories': ['電玩動漫'],
+ },
+ }, {
+ 'url': 'http://vlog.xuite.net/play/S1dDUjdyLTMyOTc3NjcuZmx2/%E5%AD%AB%E7%87%95%E5%A7%BF-%E7%9C%BC%E6%B7%9A%E6%88%90%E8%A9%A9',
+ 'only_matching': True,
+ }]
+
+ def _extract_flv_config(self, media_id):
+ base64_media_id = base64.b64encode(media_id.encode('utf-8')).decode('utf-8')
+ flv_config = self._download_xml(
+ 'http://vlog.xuite.net/flash/player?media=%s' % base64_media_id,
+ 'flv config')
+ prop_dict = {}
+ for prop in flv_config.findall('./property'):
+ prop_id = base64.b64decode(prop.attrib['id']).decode('utf-8')
+ # CDATA may be empty in flv config
+ if not prop.text:
+ continue
+ encoded_content = base64.b64decode(prop.text).decode('utf-8')
+ prop_dict[prop_id] = compat_urllib_parse_unquote(encoded_content)
+ return prop_dict
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, video_id)
+
+ error_msg = self._search_regex(
+ r'<div id="error-message-content">([^<]+)',
+ webpage, 'error message', default=None)
+ if error_msg:
+ raise ExtractorError(
+ '%s returned error: %s' % (self.IE_NAME, error_msg),
+ expected=True)
+
+ video_id = self._html_search_regex(
+ r'data-mediaid="(\d+)"', webpage, 'media id')
+ flv_config = self._extract_flv_config(video_id)
+
+ FORMATS = {
+ 'audio': 'mp3',
+ 'video': 'mp4',
+ }
+
+ formats = []
+ for format_tag in ('src', 'hq_src'):
+ video_url = flv_config.get(format_tag)
+ if not video_url:
+ continue
+ format_id = self._search_regex(
+ r'\bq=(.+?)\b', video_url, 'format id', default=format_tag)
+ formats.append({
+ 'url': video_url,
+ 'ext': FORMATS.get(flv_config['type'], 'mp4'),
+ 'format_id': format_id,
+ 'height': int(format_id) if format_id.isnumeric() else None,
+ })
+ self._sort_formats(formats)
+
+ timestamp = flv_config.get('publish_datetime')
+ if timestamp:
+ timestamp = parse_iso8601(timestamp + ' +0800', ' ')
+
+ category = flv_config.get('category')
+ categories = [category] if category else []
+
+ return {
+ 'id': video_id,
+ 'title': flv_config['title'],
+ 'description': flv_config.get('description'),
+ 'thumbnail': flv_config.get('thumb'),
+ 'timestamp': timestamp,
+ 'uploader': flv_config.get('author_name'),
+ 'uploader_id': flv_config.get('author_id'),
+ 'duration': parse_duration(flv_config.get('duration')),
+ 'categories': categories,
+ 'formats': formats,
+ }
'266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'vcodec': 'h264'},
# Dash mp4 audio
- '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 48, 'preference': -50},
- '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 128, 'preference': -50},
- '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 256, 'preference': -50},
+ '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 48, 'preference': -50, 'container': 'm4a_dash'},
+ '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 128, 'preference': -50, 'container': 'm4a_dash'},
+ '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 256, 'preference': -50, 'container': 'm4a_dash'},
# Dash webm
'167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40},
player_url = None
# Get video info
+ embed_webpage = None
if re.search(r'player-age-gate-content">', video_webpage) is not None:
age_gate = True
# We simulate the access to the video from www.youtube.com/v/{video_id}
url += '&signature=' + url_data['sig'][0]
elif 's' in url_data:
encrypted_sig = url_data['s'][0]
+ ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")'
jsplayer_url_json = self._search_regex(
- r'"assets":.+?"js":\s*("[^"]+")',
- embed_webpage if age_gate else video_webpage, 'JS player URL')
+ ASSETS_RE,
+ embed_webpage if age_gate else video_webpage,
+ 'JS player URL (1)', default=None)
+ if not jsplayer_url_json and not age_gate:
+ # We need the embed website after all
+ if embed_webpage is None:
+ embed_url = proto + '://www.youtube.com/embed/%s' % video_id
+ embed_webpage = self._download_webpage(
+ embed_url, video_id, 'Downloading embed webpage')
+ jsplayer_url_json = self._search_regex(
+ ASSETS_RE, embed_webpage, 'JS player URL')
+
player_url = json.loads(jsplayer_url_json)
if player_url is None:
player_url_json = self._search_regex(
}, {
'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
'info_dict': {
+ 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
'title': 'YDL_Empty_List',
},
'playlist_count': 0,
'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
'info_dict': {
'title': '29C3: Not my department',
+ 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
},
'playlist_count': 95,
}, {
'url': 'PLBB231211A4F62143',
'info_dict': {
'title': '[OLD]Team Fortress 2 (Class-based LP)',
+ 'id': 'PLBB231211A4F62143',
},
'playlist_mincount': 26,
}, {
'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
'info_dict': {
'title': 'Uploads from Cauchemar',
+ 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
},
'playlist_mincount': 799,
}, {
'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
'info_dict': {
'title': 'YDL_safe_search',
+ 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
},
'playlist_count': 2,
}, {
'playlist_count': 4,
'info_dict': {
'title': 'JODA15',
+ 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
}
}, {
'note': 'Embedded SWF player',
'playlist_count': 4,
'info_dict': {
'title': 'JODA7',
+ 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ',
}
}, {
'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
'info_dict': {
- 'title': 'Uploads from Interstellar Movie',
+ 'title': 'Uploads from Interstellar Movie',
+ 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
},
'playlist_mincout': 21,
}]
'note': 'paginated channel',
'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
'playlist_mincount': 91,
+ 'info_dict': {
+ 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
+ }
}]
def extract_videos_from_page(self, page):
IE_NAME = 'youtube:truncated_url'
IE_DESC = False # Do not list
_VALID_URL = r'''(?x)
- (?:https?://)?[^/]+/watch\?(?:
+ (?:https?://)?
+ (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
+ (?:watch\?(?:
feature=[a-z_]+|
- annotation_id=annotation_[^&]+
- )?$|
- (?:https?://)?(?:www\.)?youtube\.com/attribution_link\?a=[^&]+$
+ annotation_id=annotation_[^&]+|
+ x-yt-cl=[0-9]+|
+ hl=[^&]*|
+ )?
+ |
+ attribution_link\?a=[^&]+
+ )
+ $
'''
_TESTS = [{
}, {
'url': 'http://www.youtube.com/watch?',
'only_matching': True,
+ }, {
+ 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.youtube.com/watch?feature=foo',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.youtube.com/watch?hl=en-GB',
+ 'only_matching': True,
}]
def _real_extract(self, url):
class YoutubeTruncatedIDIE(InfoExtractor):
IE_NAME = 'youtube:truncated_id'
IE_DESC = False # Do not list
- _VALID_URL = r'https?://(?:www\.)youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
+ _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
_TESTS = [{
'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
from __future__ import unicode_literals
import json
+import operator
import re
from .utils import (
ExtractorError,
)
+_OPERATORS = [
+ ('|', operator.or_),
+ ('^', operator.xor),
+ ('&', operator.and_),
+ ('>>', operator.rshift),
+ ('<<', operator.lshift),
+ ('-', operator.sub),
+ ('+', operator.add),
+ ('%', operator.mod),
+ ('/', operator.truediv),
+ ('*', operator.mul),
+]
+_ASSIGN_OPERATORS = [(op + '=', opfunc) for op, opfunc in _OPERATORS]
+_ASSIGN_OPERATORS.append(('=', lambda cur, right: right))
+
+_NAME_RE = r'[a-zA-Z_$][a-zA-Z_$0-9]*'
+
class JSInterpreter(object):
- def __init__(self, code):
- self.code = code
+ def __init__(self, code, objects=None):
+ if objects is None:
+ objects = {}
+ self.code = self._remove_comments(code)
self._functions = {}
- self._objects = {}
+ self._objects = objects
+
+ def _remove_comments(self, code):
+ return re.sub(r'(?s)/\*.*?\*/', '', code)
- def interpret_statement(self, stmt, local_vars, allow_recursion=20):
+ def interpret_statement(self, stmt, local_vars, allow_recursion=100):
if allow_recursion < 0:
raise ExtractorError('Recursion limit reached')
- if stmt.startswith('var '):
- stmt = stmt[len('var '):]
- ass_m = re.match(r'^(?P<out>[a-z]+)(?:\[(?P<index>[^\]]+)\])?' +
- r'=(?P<expr>.*)$', stmt)
- if ass_m:
- if ass_m.groupdict().get('index'):
- def assign(val):
- lvar = local_vars[ass_m.group('out')]
- idx = self.interpret_expression(
- ass_m.group('index'), local_vars, allow_recursion)
- assert isinstance(idx, int)
- lvar[idx] = val
- return val
- expr = ass_m.group('expr')
- else:
- def assign(val):
- local_vars[ass_m.group('out')] = val
- return val
- expr = ass_m.group('expr')
- elif stmt.startswith('return '):
- assign = lambda v: v
- expr = stmt[len('return '):]
+ should_abort = False
+ stmt = stmt.lstrip()
+ stmt_m = re.match(r'var\s', stmt)
+ if stmt_m:
+ expr = stmt[len(stmt_m.group(0)):]
else:
- # Try interpreting it as an expression
- expr = stmt
- assign = lambda v: v
+ return_m = re.match(r'return(?:\s+|$)', stmt)
+ if return_m:
+ expr = stmt[len(return_m.group(0)):]
+ should_abort = True
+ else:
+ # Try interpreting it as an expression
+ expr = stmt
v = self.interpret_expression(expr, local_vars, allow_recursion)
- return assign(v)
+ return v, should_abort
def interpret_expression(self, expr, local_vars, allow_recursion):
+ expr = expr.strip()
+
+ if expr == '': # Empty expression
+ return None
+
+ if expr.startswith('('):
+ parens_count = 0
+ for m in re.finditer(r'[()]', expr):
+ if m.group(0) == '(':
+ parens_count += 1
+ else:
+ parens_count -= 1
+ if parens_count == 0:
+ sub_expr = expr[1:m.start()]
+ sub_result = self.interpret_expression(
+ sub_expr, local_vars, allow_recursion)
+ remaining_expr = expr[m.end():].strip()
+ if not remaining_expr:
+ return sub_result
+ else:
+ expr = json.dumps(sub_result) + remaining_expr
+ break
+ else:
+ raise ExtractorError('Premature end of parens in %r' % expr)
+
+ for op, opfunc in _ASSIGN_OPERATORS:
+ m = re.match(r'''(?x)
+ (?P<out>%s)(?:\[(?P<index>[^\]]+?)\])?
+ \s*%s
+ (?P<expr>.*)$''' % (_NAME_RE, re.escape(op)), expr)
+ if not m:
+ continue
+ right_val = self.interpret_expression(
+ m.group('expr'), local_vars, allow_recursion - 1)
+
+ if m.groupdict().get('index'):
+ lvar = local_vars[m.group('out')]
+ idx = self.interpret_expression(
+ m.group('index'), local_vars, allow_recursion)
+ assert isinstance(idx, int)
+ cur = lvar[idx]
+ val = opfunc(cur, right_val)
+ lvar[idx] = val
+ return val
+ else:
+ cur = local_vars.get(m.group('out'))
+ val = opfunc(cur, right_val)
+ local_vars[m.group('out')] = val
+ return val
+
if expr.isdigit():
return int(expr)
- if expr.isalpha():
- return local_vars[expr]
+ var_m = re.match(
+ r'(?!if|return|true|false)(?P<name>%s)$' % _NAME_RE,
+ expr)
+ if var_m:
+ return local_vars[var_m.group('name')]
try:
return json.loads(expr)
pass
m = re.match(
- r'^(?P<var>[$a-zA-Z0-9_]+)\.(?P<member>[^(]+)(?:\(+(?P<args>[^()]*)\))?$',
+ r'(?P<var>%s)\.(?P<member>[^(]+)(?:\(+(?P<args>[^()]*)\))?$' % _NAME_RE,
expr)
if m:
variable = m.group('var')
return obj[member](argvals)
m = re.match(
- r'^(?P<in>[a-z]+)\[(?P<idx>.+)\]$', expr)
+ r'(?P<in>%s)\[(?P<idx>.+)\]$' % _NAME_RE, expr)
if m:
val = local_vars[m.group('in')]
idx = self.interpret_expression(
m.group('idx'), local_vars, allow_recursion - 1)
return val[idx]
- m = re.match(r'^(?P<a>.+?)(?P<op>[%])(?P<b>.+?)$', expr)
- if m:
- a = self.interpret_expression(
- m.group('a'), local_vars, allow_recursion)
- b = self.interpret_expression(
- m.group('b'), local_vars, allow_recursion)
- return a % b
+ for op, opfunc in _OPERATORS:
+ m = re.match(r'(?P<x>.+?)%s(?P<y>.+)' % re.escape(op), expr)
+ if not m:
+ continue
+ x, abort = self.interpret_statement(
+ m.group('x'), local_vars, allow_recursion - 1)
+ if abort:
+ raise ExtractorError(
+ 'Premature left-side return of %s in %r' % (op, expr))
+ y, abort = self.interpret_statement(
+ m.group('y'), local_vars, allow_recursion - 1)
+ if abort:
+ raise ExtractorError(
+ 'Premature right-side return of %s in %r' % (op, expr))
+ return opfunc(x, y)
m = re.match(
- r'^(?P<func>[a-zA-Z$]+)\((?P<args>[a-z0-9,]+)\)$', expr)
+ r'^(?P<func>%s)\((?P<args>[a-zA-Z0-9_$,]+)\)$' % _NAME_RE, expr)
if m:
fname = m.group('func')
argvals = tuple([
if fname not in self._functions:
self._functions[fname] = self.extract_function(fname)
return self._functions[fname](argvals)
+
raise ExtractorError('Unsupported JS expression %r' % expr)
def extract_object(self, objname):
def extract_function(self, funcname):
func_m = re.search(
- (r'(?:function %s|[{;]%s\s*=\s*function)' % (
- re.escape(funcname), re.escape(funcname))) +
- r'\((?P<args>[a-z,]+)\){(?P<code>[^}]+)}',
+ r'''(?x)
+ (?:function\s+%s|[{;]%s\s*=\s*function)\s*
+ \((?P<args>[^)]*)\)\s*
+ \{(?P<code>[^}]+)\}''' % (
+ re.escape(funcname), re.escape(funcname)),
self.code)
if func_m is None:
raise ExtractorError('Could not find JS function %r' % funcname)
return self.build_function(argnames, func_m.group('code'))
+ def call_function(self, funcname, *args):
+ f = self.extract_function(funcname)
+ return f(args)
+
def build_function(self, argnames, code):
def resf(args):
local_vars = dict(zip(argnames, args))
for stmt in code.split(';'):
- res = self.interpret_statement(stmt, local_vars)
+ res, abort = self.interpret_statement(stmt, local_vars)
+ if abort:
+ break
return res
return resf
import shlex
import sys
+from .downloader.external import list_external_downloaders
from .compat import (
compat_expanduser,
compat_getenv,
'--playlist-end',
dest='playlistend', metavar='NUMBER', default=None, type=int,
help='playlist video to end at (default is last)')
+ selection.add_option(
+ '--playlist-items',
+ dest='playlist_items', metavar='ITEM_SPEC', default=None,
+ help='playlist video items to download. Specify indices of the videos in the playlist seperated by commas like: "--playlist-items 1,2,5,8" if you want to download videos indexed 1, 2, 5, 8 in the playlist. You can specify range: "--playlist-items 1-3,7,10-13", it will download the videos at index 1, 2, 3, 7, 10, 11, 12 and 13.')
selection.add_option(
'--match-title',
dest='matchtitle', metavar='REGEX',
authentication.add_option(
'-p', '--password',
dest='password', metavar='PASSWORD',
- help='account password')
+ help='account password. If this option is left out, youtube-dl will ask interactively.')
authentication.add_option(
'-2', '--twofactor',
dest='twofactor', metavar='TWOFACTOR',
'extensions aac, m4a, mp3, mp4, ogg, wav, webm. '
'You can also use the special names "best",'
' "bestvideo", "bestaudio", "worst". '
+ ' You can filter the video results by putting a condition in'
+ ' brackets, as in -f "best[height=720]"'
+ ' (or -f "[filesize>10M]"). '
+ ' This works for filesize, height, width, tbr, abr, vbr, and fps'
+ ' and the comparisons <, <=, >, >=, =, != .'
+ ' Formats for which the value is not known are excluded unless you'
+ ' put a question mark (?) after the operator.'
+ ' You can combine format filters, so '
+ '-f "[height <=? 720][tbr>500]" '
+ 'selects up to 720p videos (or videos where the height is not '
+ 'known) with a bitrate of at least 500 KBit/s.'
' By default, youtube-dl will pick the best quality.'
' Use commas to download multiple audio formats, such as'
' -f 136/137/mp4/bestvideo,140/m4a/bestaudio.'
downloader.add_option(
'-R', '--retries',
dest='retries', metavar='RETRIES', default=10,
- help='number of retries (default is %default)')
+ help='number of retries (default is %default), or "infinite".')
downloader.add_option(
'--buffer-size',
dest='buffersize', metavar='SIZE', default='1024',
'--playlist-reverse',
action='store_true',
help='Download playlist videos in reverse order')
+ downloader.add_option(
+ '--xattr-set-filesize',
+ dest='xattr_set_filesize', action='store_true',
+ help='(experimental) set file xattribute ytdl.filesize with expected filesize')
+ downloader.add_option(
+ '--external-downloader',
+ dest='external_downloader', metavar='COMMAND',
+ help='(experimental) Use the specified external downloader. '
+ 'Currently supports %s' % ','.join(list_external_downloaders()))
workarounds = optparse.OptionGroup(parser, 'Workarounds')
workarounds.add_option(
'--bidi-workaround',
dest='bidi_workaround', action='store_true',
help='Work around terminals that lack bidirectional text support. Requires bidiv or fribidi executable in PATH')
+ workarounds.add_option(
+ '--sleep-interval', metavar='SECONDS',
+ dest='sleep_interval', type=float,
+ help='Number of seconds to sleep before each download.')
verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options')
verbosity.add_option(
'--write-annotations',
action='store_true', dest='writeannotations', default=False,
help='write video annotations to a .annotation file')
- filesystem.add_option(
- '--write-thumbnail',
- action='store_true', dest='writethumbnail', default=False,
- help='write thumbnail image to disk')
filesystem.add_option(
'--load-info',
dest='load_info_filename', metavar='FILE',
action='store_true', dest='rm_cachedir',
help='Delete all filesystem cache files')
+ thumbnail = optparse.OptionGroup(parser, 'Thumbnail images')
+ thumbnail.add_option(
+ '--write-thumbnail',
+ action='store_true', dest='writethumbnail', default=False,
+ help='write thumbnail image to disk')
+ thumbnail.add_option(
+ '--write-all-thumbnails',
+ action='store_true', dest='write_all_thumbnails', default=False,
+ help='write all thumbnail image formats to disk')
+ thumbnail.add_option(
+ '--list-thumbnails',
+ action='store_true', dest='list_thumbnails', default=False,
+ help='Simulate and list all available thumbnail formats')
+
postproc = optparse.OptionGroup(parser, 'Post-processing Options')
postproc.add_option(
'-x', '--extract-audio',
postproc.add_option(
'--fixup',
metavar='POLICY', dest='fixup', default='detect_or_warn',
- help='(experimental) Automatically correct known faults of the file. '
+ help='Automatically correct known faults of the file. '
'One of never (do nothing), warn (only emit a warning), '
- 'detect_or_warn(check whether we can do anything about it, warn '
- 'otherwise')
+ 'detect_or_warn(the default; fix file if we can, warn otherwise)')
postproc.add_option(
'--prefer-avconv',
action='store_false', dest='prefer_ffmpeg',
parser.add_option_group(selection)
parser.add_option_group(downloader)
parser.add_option_group(filesystem)
+ parser.add_option_group(thumbnail)
parser.add_option_group(verbosity)
parser.add_option_group(workarounds)
parser.add_option_group(video_format)
FFmpegEmbedSubtitlePP,
FFmpegExtractAudioPP,
FFmpegFixupStretchedPP,
+ FFmpegFixupM4aPP,
FFmpegMergerPP,
FFmpegMetadataPP,
FFmpegVideoConvertorPP,
'FFmpegAudioFixPP',
'FFmpegEmbedSubtitlePP',
'FFmpegExtractAudioPP',
+ 'FFmpegFixupM4aPP',
'FFmpegFixupStretchedPP',
'FFmpegMergerPP',
'FFmpegMetadataPP',
metadata['artist'] = info['uploader']
elif info.get('uploader_id') is not None:
metadata['artist'] = info['uploader_id']
+ if info.get('description') is not None:
+ metadata['description'] = info['description']
+ metadata['comment'] = info['description']
+ if info.get('webpage_url') is not None:
+ metadata['purl'] = info['webpage_url']
if not metadata:
self._downloader.to_screen('[ffmpeg] There isn\'t any metadata to add')
def run(self, info):
stretched_ratio = info.get('stretched_ratio')
if stretched_ratio is None or stretched_ratio == 1:
- return
+ return True, info
filename = info['filepath']
temp_filename = prepend_extension(filename, 'temp')
os.rename(encodeFilename(temp_filename), encodeFilename(filename))
return True, info
+
+
+class FFmpegFixupM4aPP(FFmpegPostProcessor):
+ def run(self, info):
+ if info.get('container') != 'm4a_dash':
+ return True, info
+
+ filename = info['filepath']
+ temp_filename = prepend_extension(filename, 'temp')
+
+ options = ['-c', 'copy', '-f', 'mp4']
+ self._downloader.to_screen('[ffmpeg] Correcting container in "%s"' % filename)
+ self.run_ffmpeg(filename, temp_filename, options)
+
+ os.remove(encodeFilename(filename))
+ os.rename(encodeFilename(temp_filename), encodeFilename(filename))
+
+ return True, info
import zlib
from .compat import (
+ compat_basestring,
compat_chr,
compat_getenv,
compat_html_entities,
def find_xpath_attr(node, xpath, key, val):
# Here comes the crazy part: In 2.6, if the xpath is a unicode,
# .//node does not match if a node is a direct child of . !
- if isinstance(xpath, unicode):
+ if isinstance(xpath, compat_str):
xpath = xpath.encode('ascii')
for f in node.findall(xpath):
pass
if sys.version_info < (3, 2):
- import httplib
-
- class HTTPSConnectionV3(httplib.HTTPSConnection):
- def __init__(self, *args, **kwargs):
- httplib.HTTPSConnection.__init__(self, *args, **kwargs)
-
- def connect(self):
- sock = socket.create_connection((self.host, self.port), self.timeout)
- if getattr(self, '_tunnel_host', False):
- self.sock = sock
- self._tunnel()
- try:
- self.sock = ssl.wrap_socket(sock, self.key_file, self.cert_file, ssl_version=ssl.PROTOCOL_TLSv1)
- except ssl.SSLError:
- self.sock = ssl.wrap_socket(sock, self.key_file, self.cert_file, ssl_version=ssl.PROTOCOL_SSLv23)
-
- return YoutubeDLHTTPSHandler(params, https_conn_class=HTTPSConnectionV3, **kwargs)
+ return YoutubeDLHTTPSHandler(params, **kwargs)
else: # Python < 3.4
- context = ssl.SSLContext(ssl.PROTOCOL_SSLv23)
+ context = ssl.SSLContext(ssl.PROTOCOL_TLSv1)
context.verify_mode = (ssl.CERT_NONE
if opts_no_check_certificate
else ssl.CERT_REQUIRED)
sock = compat_socket_create_connection(
(self.host, self.port), self.timeout, sa)
if is_https:
- self.sock = ssl.wrap_socket(sock, self.key_file, self.cert_file)
+ self.sock = ssl.wrap_socket(
+ sock, self.key_file, self.cert_file,
+ ssl_version=ssl.PROTOCOL_TLSv1)
else:
self.sock = sock
hc.connect = functools.partial(_hc_connect, hc)
def http_request(self, req):
for h, v in std_headers.items():
- if h not in req.headers:
+ # Capitalize is needed because of Python bug 2275: http://bugs.python.org/issue2275
+ # The dict keys are capitalized because of this bug by urllib
+ if h.capitalize() not in req.headers:
req.add_header(h, v)
if 'Youtubedl-no-compression' in req.headers:
if 'Accept-encoding' in req.headers:
del req.headers['Accept-encoding']
del req.headers['Youtubedl-no-compression']
- if 'Youtubedl-user-agent' in req.headers:
- if 'User-agent' in req.headers:
- del req.headers['User-agent']
- req.headers['User-agent'] = req.headers['Youtubedl-user-agent']
- del req.headers['Youtubedl-user-agent']
if sys.version_info < (2, 7) and '#' in req.get_full_url():
# Python 2.6 is brain-dead when it comes to fragments
self._params = params
def https_open(self, req):
+ kwargs = {}
+ if hasattr(self, '_context'): # python > 2.6
+ kwargs['context'] = self._context
+ if hasattr(self, '_check_hostname'): # python 3.x
+ kwargs['check_hostname'] = self._check_hostname
return self.do_open(functools.partial(
_create_http_connection, self, self._https_conn_class, True),
- req)
+ req, **kwargs)
def parse_iso8601(date_str, delimiter='T'):
# %z (UTC offset) is only supported in python>=3.2
date_str = re.sub(r' ?(\+|-)[0-9]{2}:?[0-9]{2}$', '', date_str)
# Remove AM/PM + timezone
- date_str = re.sub(r'(?i)\s*(?:AM|PM)\s+[A-Z]+', '', date_str)
+ date_str = re.sub(r'(?i)\s*(?:AM|PM)(?:\s+[A-Z]+)?', '', date_str)
format_expressions = [
'%d %B %Y',
except AttributeError:
# If the output stream doesn't have a fileno, it's virtual
return False
+ except io.UnsupportedOperation:
+ # Some strange Windows pseudo files?
+ return False
if fileno not in WIN_OUTPUT_IDS:
return False
def parse_duration(s):
- if not isinstance(s, basestring if sys.version_info < (3, 0) else compat_str):
+ if not isinstance(s, compat_basestring):
return None
s = s.strip()
(?P<only_hours>[0-9.]+)\s*(?:hours?)|
(?:
- (?:(?P<hours>[0-9]+)\s*(?:[:h]|hours?)\s*)?
+ (?:
+ (?:(?P<days>[0-9]+)\s*(?:[:d]|days?)\s*)?
+ (?P<hours>[0-9]+)\s*(?:[:h]|hours?)\s*
+ )?
(?P<mins>[0-9]+)\s*(?:[:m]|mins?|minutes?)\s*
)?
(?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?\s*(?:s|secs?|seconds?)?
res += int(m.group('mins')) * 60
if m.group('hours'):
res += int(m.group('hours')) * 60 * 60
+ if m.group('days'):
+ res += int(m.group('days')) * 24 * 60 * 60
if m.group('ms'):
res += float(m.group('ms'))
return res
def escape_rfc3986(s):
"""Escape non-ASCII characters as suggested by RFC 3986"""
- if sys.version_info < (3, 0) and isinstance(s, unicode):
+ if sys.version_info < (3, 0) and isinstance(s, compat_str):
s = s.encode('utf-8')
return compat_urllib_parse.quote(s, b"%/;:@&=+$,!~*'()?#[]")
res = re.sub(r'''(?x)
"(?:[^"\\]*(?:\\\\|\\")?)*"|
'(?:[^'\\]*(?:\\\\|\\')?)*'|
- [a-zA-Z_][a-zA-Z_0-9]*
+ [a-zA-Z_][.a-zA-Z_0-9]*
''', fix_kv, code)
res = re.sub(r',(\s*\])', lambda m: m.group(1), res)
return res
except AttributeError: # Python < 3
getheader = url_handle.info().getheader
+ cd = getheader('Content-Disposition')
+ if cd:
+ m = re.match(r'attachment;\s*filename="(?P<filename>[^"]+)"', cd)
+ if m:
+ e = determine_ext(m.group('filename'), default_ext=None)
+ if e:
+ return e
+
return getheader('Content-Type').split("/")[1]
if content_limit is None:
return False # Content available for everyone
return age_limit < content_limit
+
+
+def is_html(first_bytes):
+ """ Detect whether a file contains HTML by examining its first bytes. """
+
+ BOMS = [
+ (b'\xef\xbb\xbf', 'utf-8'),
+ (b'\x00\x00\xfe\xff', 'utf-32-be'),
+ (b'\xff\xfe\x00\x00', 'utf-32-le'),
+ (b'\xff\xfe', 'utf-16-le'),
+ (b'\xfe\xff', 'utf-16-be'),
+ ]
+ for bom, enc in BOMS:
+ if first_bytes.startswith(bom):
+ s = first_bytes[len(bom):].decode(enc, 'replace')
+ break
+ else:
+ s = first_bytes.decode('utf-8', 'replace')
+
+ return re.match(r'^\s*<', s)
+
+
+def determine_protocol(info_dict):
+ protocol = info_dict.get('protocol')
+ if protocol is not None:
+ return protocol
+
+ url = info_dict['url']
+ if url.startswith('rtmp'):
+ return 'rtmp'
+ elif url.startswith('mms'):
+ return 'mms'
+ elif url.startswith('rtsp'):
+ return 'rtsp'
+
+ ext = determine_ext(url)
+ if ext == 'm3u8':
+ return 'm3u8'
+ elif ext == 'f4m':
+ return 'f4m'
+
+ return compat_urllib_parse_urlparse(url).scheme
+
+
+def render_table(header_row, data):
+ """ Render a list of rows, each as a list of values """
+ table = [header_row] + data
+ max_lens = [max(len(compat_str(v)) for v in col) for col in zip(*table)]
+ format_str = ' '.join('%-' + compat_str(ml + 1) + 's' for ml in max_lens[:-1]) + '%s'
+ return '\n'.join(format_str % tuple(row) for row in table)
from __future__ import unicode_literals
-__version__ = '2015.01.16'
+__version__ = '2015.02.06'
Rapsys Git / youtubedl / commitdiff