- # Rewrite valid but non-extractable URLs as
- # extractable English language /watch/ URLs
- if re.match(self._VPAGE_URL, url) is None:
- request = urllib2.Request(url)
- try:
- webpage = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
- return
-
- mobj = re.search(r'\("id", "([0-9]+)"\);', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: Unable to extract id field')
- return
- yahoo_id = mobj.group(1)
-
- mobj = re.search(r'\("vid", "([0-9]+)"\);', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: Unable to extract vid field')
- return
- yahoo_vid = mobj.group(1)
-
- url = 'http://video.yahoo.com/watch/%s/%s' % (yahoo_vid, yahoo_id)
- return self._real_extract(url, new_video=False)
-
- # Retrieve video webpage to extract further information
- request = urllib2.Request(url)
- try:
- self.report_download_webpage(video_id)
- webpage = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
- return
-
- # Extract uploader and title from webpage
- self.report_extraction(video_id)
- mobj = re.search(r'<meta name="title" content="(.*)" />', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video title')
- return
- video_title = mobj.group(1).decode('utf-8')
- simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
-
- mobj = re.search(r'<h2 class="ti-5"><a href="http://video\.yahoo\.com/(people|profile)/[0-9]+" beacon=".*">(.*)</a></h2>', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video uploader')
- return
- video_uploader = mobj.group(1).decode('utf-8')
-
- # Extract video thumbnail
- mobj = re.search(r'<link rel="image_src" href="(.*)" />', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
- return
- video_thumbnail = mobj.group(1).decode('utf-8')
-
- # Extract video description
- mobj = re.search(r'<meta name="description" content="(.*)" />', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video description')
- return
- video_description = mobj.group(1).decode('utf-8')
- if not video_description:
- video_description = 'No description available.'
-
- # Extract video height and width
- mobj = re.search(r'<meta name="video_height" content="([0-9]+)" />', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video height')
- return
- yv_video_height = mobj.group(1)
-
- mobj = re.search(r'<meta name="video_width" content="([0-9]+)" />', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video width')
- return
- yv_video_width = mobj.group(1)
-
- # Retrieve video playlist to extract media URL
- # I'm not completely sure what all these options are, but we
- # seem to need most of them, otherwise the server sends a 401.
- yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents
- yv_bitrate = '700' # according to Wikipedia this is hard-coded
- request = urllib2.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id +
- '&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height +
- '&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797')
- try:
- self.report_download_webpage(video_id)
- webpage = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
- return
-
- # Extract media URL from playlist XML
- mobj = re.search(r'<STREAM APP="(http://.*)" FULLPATH="/?(/.*\.flv\?[^"]*)"', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: Unable to extract media URL')
- return
- video_url = urllib.unquote(mobj.group(1) + mobj.group(2)).decode('utf-8')
- video_url = re.sub(r'(?u)&(.+?);', htmlentity_transform, video_url)
-
- try:
- # Process video information
- self._downloader.process_info({
- 'id': video_id.decode('utf-8'),
- 'url': video_url,
- 'uploader': video_uploader,
- 'upload_date': u'NA',
- 'title': video_title,
- 'stitle': simple_title,
- 'ext': video_extension.decode('utf-8'),
- 'thumbnail': video_thumbnail.decode('utf-8'),
- 'description': video_description,
- 'thumbnail': video_thumbnail,
- 'player_url': None,
- })
- except UnavailableVideoError:
- self._downloader.trouble(u'\nERROR: unable to download video')
-
-
-class VimeoIE(InfoExtractor):
- """Information extractor for vimeo.com."""
-
- # _VALID_URL matches Vimeo URLs
- _VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:groups/[^/]+/)?(?:videos?/)?([0-9]+)'
- IE_NAME = u'vimeo'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[vimeo] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[vimeo] %s: Extracting information' % video_id)
-
- def _real_initialize(self):
- return
-
- def _real_extract(self, url, new_video=True):
- # Extract ID from URL
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
- return
-
- # At this point we have a new video
- self._downloader.increment_downloads()
- video_id = mobj.group(1)
-
- # Retrieve video webpage to extract further information
- request = urllib2.Request("http://vimeo.com/moogaloop/load/clip:%s" % video_id, None, std_headers)
- try:
- self.report_download_webpage(video_id)
- webpage = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
- return
-
- # Now we begin extracting as much information as we can from what we
- # retrieved. First we extract the information common to all extractors,
- # and latter we extract those that are Vimeo specific.
- self.report_extraction(video_id)
-
- # Extract title
- mobj = re.search(r'<caption>(.*?)</caption>', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video title')
- return
- video_title = mobj.group(1).decode('utf-8')
- simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
-
- # Extract uploader
- mobj = re.search(r'<uploader_url>http://vimeo.com/(.*?)</uploader_url>', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video uploader')
- return
- video_uploader = mobj.group(1).decode('utf-8')
-
- # Extract video thumbnail
- mobj = re.search(r'<thumbnail>(.*?)</thumbnail>', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
- return
- video_thumbnail = mobj.group(1).decode('utf-8')
-
- # # Extract video description
- # mobj = re.search(r'<meta property="og:description" content="(.*)" />', webpage)
- # if mobj is None:
- # self._downloader.trouble(u'ERROR: unable to extract video description')
- # return
- # video_description = mobj.group(1).decode('utf-8')
- # if not video_description: video_description = 'No description available.'
- video_description = 'Foo.'
-
- # Vimeo specific: extract request signature
- mobj = re.search(r'<request_signature>(.*?)</request_signature>', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract request signature')
- return
- sig = mobj.group(1).decode('utf-8')
-
- # Vimeo specific: extract video quality information
- mobj = re.search(r'<isHD>(\d+)</isHD>', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video quality information')
- return
- quality = mobj.group(1).decode('utf-8')
-
- if int(quality) == 1:
- quality = 'hd'
- else:
- quality = 'sd'
-
- # Vimeo specific: Extract request signature expiration
- mobj = re.search(r'<request_signature_expires>(.*?)</request_signature_expires>', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract request signature expiration')
- return
- sig_exp = mobj.group(1).decode('utf-8')
-
- video_url = "http://vimeo.com/moogaloop/play/clip:%s/%s/%s/?q=%s" % (video_id, sig, sig_exp, quality)
-
- try:
- # Process video information
- self._downloader.process_info({
- 'id': video_id.decode('utf-8'),
- 'url': video_url,
- 'uploader': video_uploader,
- 'upload_date': u'NA',
- 'title': video_title,
- 'stitle': simple_title,
- 'ext': u'mp4',
- 'thumbnail': video_thumbnail.decode('utf-8'),
- 'description': video_description,
- 'thumbnail': video_thumbnail,
- 'description': video_description,
- 'player_url': None,
- })
- except UnavailableVideoError:
- self._downloader.trouble(u'ERROR: unable to download video')
-
-
-class GenericIE(InfoExtractor):
- """Generic last-resort information extractor."""
-
- _VALID_URL = r'.*'
- IE_NAME = u'generic'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'WARNING: Falling back on generic information extractor.')
- self._downloader.to_screen(u'[generic] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[generic] %s: Extracting information' % video_id)
-
- def _real_initialize(self):
- return
-
- def _real_extract(self, url):
- # At this point we have a new video
- self._downloader.increment_downloads()
-
- video_id = url.split('/')[-1]
- request = urllib2.Request(url)
- try:
- self.report_download_webpage(video_id)
- webpage = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
- return
- except ValueError, err:
- # since this is the last-resort InfoExtractor, if
- # this error is thrown, it'll be thrown here
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
- return
-
- self.report_extraction(video_id)
- # Start with something easy: JW Player in SWFObject
- mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
- if mobj is None:
- # Broaden the search a little bit
- mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
- return
-
- # It's possible that one of the regexes
- # matched, but returned an empty group:
- if mobj.group(1) is None:
- self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
- return
-
- video_url = urllib.unquote(mobj.group(1))
- video_id = os.path.basename(video_url)
-
- # here's a fun little line of code for you:
- video_extension = os.path.splitext(video_id)[1][1:]
- video_id = os.path.splitext(video_id)[0]
-
- # it's tempting to parse this further, but you would
- # have to take into account all the variations like
- # Video Title - Site Name
- # Site Name | Video Title
- # Video Title - Tagline | Site Name
- # and so on and so forth; it's just not practical
- mobj = re.search(r'<title>(.*)</title>', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
- return
- video_title = mobj.group(1).decode('utf-8')
- video_title = sanitize_title(video_title)
- simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
-
- # video uploader is domain name
- mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
- return
- video_uploader = mobj.group(1).decode('utf-8')
-
- try:
- # Process video information
- self._downloader.process_info({
- 'id': video_id.decode('utf-8'),
- 'url': video_url.decode('utf-8'),
- 'uploader': video_uploader,
- 'upload_date': u'NA',
- 'title': video_title,
- 'stitle': simple_title,
- 'ext': video_extension.decode('utf-8'),
- 'format': u'NA',
- 'player_url': None,
- })
- except UnavailableVideoError, err:
- self._downloader.trouble(u'\nERROR: unable to download video')
-
-
-class YoutubeSearchIE(InfoExtractor):
- """Information Extractor for YouTube search queries."""
- _VALID_URL = r'ytsearch(\d+|all)?:[\s\S]+'
- _TEMPLATE_URL = 'http://www.youtube.com/results?search_query=%s&page=%s&gl=US&hl=en'
- _VIDEO_INDICATOR = r'href="/watch\?v=.+?"'
- _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
- _youtube_ie = None
- _max_youtube_results = 1000
- IE_NAME = u'youtube:search'
-
- def __init__(self, youtube_ie, downloader=None):
- InfoExtractor.__init__(self, downloader)
- self._youtube_ie = youtube_ie
-
- def report_download_page(self, query, pagenum):
- """Report attempt to download playlist page with given number."""
- query = query.decode(preferredencoding())
- self._downloader.to_screen(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
-
- def _real_initialize(self):
- self._youtube_ie.initialize()
-
- def _real_extract(self, query):
- mobj = re.match(self._VALID_URL, query)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
- return
-
- prefix, query = query.split(':')
- prefix = prefix[8:]
- query = query.encode('utf-8')
- if prefix == '':
- self._download_n_results(query, 1)
- return
- elif prefix == 'all':
- self._download_n_results(query, self._max_youtube_results)
- return
- else:
- try:
- n = long(prefix)
- if n <= 0:
- self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
- return
- elif n > self._max_youtube_results:
- self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n))
- n = self._max_youtube_results
- self._download_n_results(query, n)
- return
- except ValueError: # parsing prefix as integer fails
- self._download_n_results(query, 1)
- return
-
- def _download_n_results(self, query, n):
- """Downloads a specified number of results for a query"""
-
- video_ids = []
- already_seen = set()
- pagenum = 1
-
- while True:
- self.report_download_page(query, pagenum)
- result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
- request = urllib2.Request(result_url)
- try:
- page = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
- return
-
- # Extract video identifiers
- for mobj in re.finditer(self._VIDEO_INDICATOR, page):
- video_id = page[mobj.span()[0]:mobj.span()[1]].split('=')[2][:-1]
- if video_id not in already_seen:
- video_ids.append(video_id)
- already_seen.add(video_id)
- if len(video_ids) == n:
- # Specified n videos reached
- for id in video_ids:
- self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
- return
-
- if re.search(self._MORE_PAGES_INDICATOR, page) is None:
- for id in video_ids:
- self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
- return
-
- pagenum = pagenum + 1
-
-
-class GoogleSearchIE(InfoExtractor):
- """Information Extractor for Google Video search queries."""
- _VALID_URL = r'gvsearch(\d+|all)?:[\s\S]+'
- _TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en'
- _VIDEO_INDICATOR = r'videoplay\?docid=([^\&>]+)\&'
- _MORE_PAGES_INDICATOR = r'<span>Next</span>'
- _google_ie = None
- _max_google_results = 1000
- IE_NAME = u'video.google:search'
-
- def __init__(self, google_ie, downloader=None):
- InfoExtractor.__init__(self, downloader)
- self._google_ie = google_ie
-
- def report_download_page(self, query, pagenum):
- """Report attempt to download playlist page with given number."""
- query = query.decode(preferredencoding())
- self._downloader.to_screen(u'[video.google] query "%s": Downloading page %s' % (query, pagenum))
-
- def _real_initialize(self):
- self._google_ie.initialize()
-
- def _real_extract(self, query):
- mobj = re.match(self._VALID_URL, query)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
- return
-
- prefix, query = query.split(':')
- prefix = prefix[8:]
- query = query.encode('utf-8')
- if prefix == '':
- self._download_n_results(query, 1)
- return
- elif prefix == 'all':
- self._download_n_results(query, self._max_google_results)
- return
- else:
- try:
- n = long(prefix)
- if n <= 0:
- self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
- return
- elif n > self._max_google_results:
- self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n))
- n = self._max_google_results
- self._download_n_results(query, n)
- return
- except ValueError: # parsing prefix as integer fails
- self._download_n_results(query, 1)
- return
-
- def _download_n_results(self, query, n):
- """Downloads a specified number of results for a query"""
-
- video_ids = []
- already_seen = set()
- pagenum = 1
-
- while True:
- self.report_download_page(query, pagenum)
- result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
- request = urllib2.Request(result_url)
- try:
- page = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
- return
-
- # Extract video identifiers
- for mobj in re.finditer(self._VIDEO_INDICATOR, page):
- video_id = mobj.group(1)
- if video_id not in already_seen:
- video_ids.append(video_id)
- already_seen.add(video_id)
- if len(video_ids) == n:
- # Specified n videos reached
- for id in video_ids:
- self._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id)
- return
-
- if re.search(self._MORE_PAGES_INDICATOR, page) is None:
- for id in video_ids:
- self._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id)
- return
-
- pagenum = pagenum + 1
-
-
-class YahooSearchIE(InfoExtractor):
- """Information Extractor for Yahoo! Video search queries."""
- _VALID_URL = r'yvsearch(\d+|all)?:[\s\S]+'
- _TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s'
- _VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"'
- _MORE_PAGES_INDICATOR = r'\s*Next'
- _yahoo_ie = None
- _max_yahoo_results = 1000
- IE_NAME = u'video.yahoo:search'
-
- def __init__(self, yahoo_ie, downloader=None):
- InfoExtractor.__init__(self, downloader)
- self._yahoo_ie = yahoo_ie
-
- def report_download_page(self, query, pagenum):
- """Report attempt to download playlist page with given number."""
- query = query.decode(preferredencoding())
- self._downloader.to_screen(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum))
-
- def _real_initialize(self):
- self._yahoo_ie.initialize()
-
- def _real_extract(self, query):
- mobj = re.match(self._VALID_URL, query)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
- return
-
- prefix, query = query.split(':')
- prefix = prefix[8:]
- query = query.encode('utf-8')
- if prefix == '':
- self._download_n_results(query, 1)
- return
- elif prefix == 'all':
- self._download_n_results(query, self._max_yahoo_results)
- return
- else:
- try:
- n = long(prefix)
- if n <= 0:
- self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
- return
- elif n > self._max_yahoo_results:
- self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n))
- n = self._max_yahoo_results
- self._download_n_results(query, n)
- return
- except ValueError: # parsing prefix as integer fails
- self._download_n_results(query, 1)
- return
-
- def _download_n_results(self, query, n):
- """Downloads a specified number of results for a query"""
-
- video_ids = []
- already_seen = set()
- pagenum = 1
-
- while True:
- self.report_download_page(query, pagenum)
- result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
- request = urllib2.Request(result_url)
- try:
- page = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
- return
-
- # Extract video identifiers
- for mobj in re.finditer(self._VIDEO_INDICATOR, page):
- video_id = mobj.group(1)
- if video_id not in already_seen:
- video_ids.append(video_id)
- already_seen.add(video_id)
- if len(video_ids) == n:
- # Specified n videos reached
- for id in video_ids:
- self._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id)
- return
-
- if re.search(self._MORE_PAGES_INDICATOR, page) is None:
- for id in video_ids:
- self._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id)
- return
-
- pagenum = pagenum + 1
-
-
-class YoutubePlaylistIE(InfoExtractor):
- """Information Extractor for YouTube playlists."""
-
- _VALID_URL = r'(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL)?([0-9A-Za-z]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'
- _TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en'
- _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
- _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
- _youtube_ie = None
- IE_NAME = u'youtube:playlist'
-
- def __init__(self, youtube_ie, downloader=None):
- InfoExtractor.__init__(self, downloader)
- self._youtube_ie = youtube_ie
-
- def report_download_page(self, playlist_id, pagenum):
- """Report attempt to download playlist page with given number."""
- self._downloader.to_screen(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
-
- def _real_initialize(self):
- self._youtube_ie.initialize()
-
- def _real_extract(self, url):
- # Extract playlist id
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid url: %s' % url)
- return
-
- # Single video case
- if mobj.group(3) is not None:
- self._youtube_ie.extract(mobj.group(3))
- return
-
- # Download playlist pages
- # prefix is 'p' as default for playlists but there are other types that need extra care
- playlist_prefix = mobj.group(1)
- if playlist_prefix == 'a':
- playlist_access = 'artist'
- else:
- playlist_prefix = 'p'
- playlist_access = 'view_play_list'
- playlist_id = mobj.group(2)
- video_ids = []
- pagenum = 1
-
- while True:
- self.report_download_page(playlist_id, pagenum)
- request = urllib2.Request(self._TEMPLATE_URL % (playlist_access, playlist_prefix, playlist_id, pagenum))
- try:
- page = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
- return
-
- # Extract video identifiers
- ids_in_page = []
- for mobj in re.finditer(self._VIDEO_INDICATOR, page):
- if mobj.group(1) not in ids_in_page:
- ids_in_page.append(mobj.group(1))
- video_ids.extend(ids_in_page)
-
- if re.search(self._MORE_PAGES_INDICATOR, page) is None:
- break
- pagenum = pagenum + 1
-
- playliststart = self._downloader.params.get('playliststart', 1) - 1
- playlistend = self._downloader.params.get('playlistend', -1)
- video_ids = video_ids[playliststart:playlistend]
-
- for id in video_ids:
- self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
- return
-
-
-class YoutubeUserIE(InfoExtractor):
- """Information Extractor for YouTube users."""
-
- _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/user/)|ytuser:)([A-Za-z0-9_-]+)'
- _TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
- _GDATA_PAGE_SIZE = 50
- _GDATA_URL = 'http://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d'
- _VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
- _youtube_ie = None
- IE_NAME = u'youtube:user'
-
- def __init__(self, youtube_ie, downloader=None):
- InfoExtractor.__init__(self, downloader)
- self._youtube_ie = youtube_ie
-
- def report_download_page(self, username, start_index):
- """Report attempt to download user page."""
- self._downloader.to_screen(u'[youtube] user %s: Downloading video ids from %d to %d' %
- (username, start_index, start_index + self._GDATA_PAGE_SIZE))
-
- def _real_initialize(self):
- self._youtube_ie.initialize()
-
- def _real_extract(self, url):
- # Extract username
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid url: %s' % url)
- return
-
- username = mobj.group(1)
-
- # Download video ids using YouTube Data API. Result size per
- # query is limited (currently to 50 videos) so we need to query
- # page by page until there are no video ids - it means we got
- # all of them.
-
- video_ids = []
- pagenum = 0
-
- while True:
- start_index = pagenum * self._GDATA_PAGE_SIZE + 1
- self.report_download_page(username, start_index)
-
- request = urllib2.Request(self._GDATA_URL % (username, self._GDATA_PAGE_SIZE, start_index))
-
- try:
- page = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
- return
-
- # Extract video identifiers
- ids_in_page = []
-
- for mobj in re.finditer(self._VIDEO_INDICATOR, page):
- if mobj.group(1) not in ids_in_page:
- ids_in_page.append(mobj.group(1))
-
- video_ids.extend(ids_in_page)
-
- # A little optimization - if current page is not
- # "full", ie. does not contain PAGE_SIZE video ids then
- # we can assume that this page is the last one - there
- # are no more ids on further pages - no need to query
- # again.
-
- if len(ids_in_page) < self._GDATA_PAGE_SIZE:
- break
-
- pagenum += 1
-
- all_ids_count = len(video_ids)
- playliststart = self._downloader.params.get('playliststart', 1) - 1
- playlistend = self._downloader.params.get('playlistend', -1)
-
- if playlistend == -1:
- video_ids = video_ids[playliststart:]
- else:
- video_ids = video_ids[playliststart:playlistend]
-
- self._downloader.to_screen("[youtube] user %s: Collected %d video ids (downloading %d of them)" %
- (username, all_ids_count, len(video_ids)))
-
- for video_id in video_ids:
- self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % video_id)
-
-
-class DepositFilesIE(InfoExtractor):
- """Information extractor for depositfiles.com"""
-
- _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles\.com/(?:../(?#locale))?files/(.+)'
- IE_NAME = u'DepositFiles'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, file_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[DepositFiles] %s: Downloading webpage' % file_id)
-
- def report_extraction(self, file_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[DepositFiles] %s: Extracting information' % file_id)
-
- def _real_initialize(self):
- return
-
- def _real_extract(self, url):
- # At this point we have a new file
- self._downloader.increment_downloads()
-
- file_id = url.split('/')[-1]
- # Rebuild url in english locale
- url = 'http://depositfiles.com/en/files/' + file_id
-
- # Retrieve file webpage with 'Free download' button pressed
- free_download_indication = { 'gateway_result' : '1' }
- request = urllib2.Request(url, urllib.urlencode(free_download_indication))
- try:
- self.report_download_webpage(file_id)
- webpage = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: Unable to retrieve file webpage: %s' % str(err))
- return
-
- # Search for the real file URL
- mobj = re.search(r'<form action="(http://fileshare.+?)"', webpage)
- if (mobj is None) or (mobj.group(1) is None):
- # Try to figure out reason of the error.
- mobj = re.search(r'<strong>(Attention.*?)</strong>', webpage, re.DOTALL)
- if (mobj is not None) and (mobj.group(1) is not None):
- restriction_message = re.sub('\s+', ' ', mobj.group(1)).strip()
- self._downloader.trouble(u'ERROR: %s' % restriction_message)
- else:
- self._downloader.trouble(u'ERROR: unable to extract download URL from: %s' % url)
- return
-
- file_url = mobj.group(1)
- file_extension = os.path.splitext(file_url)[1][1:]
-
- # Search for file title
- mobj = re.search(r'<b title="(.*?)">', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
- return
- file_title = mobj.group(1).decode('utf-8')
-
- try:
- # Process file information
- self._downloader.process_info({
- 'id': file_id.decode('utf-8'),
- 'url': file_url.decode('utf-8'),
- 'uploader': u'NA',
- 'upload_date': u'NA',
- 'title': file_title,
- 'stitle': file_title,
- 'ext': file_extension.decode('utf-8'),
- 'format': u'NA',
- 'player_url': None,
- })
- except UnavailableVideoError, err:
- self._downloader.trouble(u'ERROR: unable to download file')
-
-
-class FacebookIE(InfoExtractor):
- """Information Extractor for Facebook"""
-
- _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/video/video\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
- _LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&'
- _NETRC_MACHINE = 'facebook'
- _available_formats = ['highqual', 'lowqual']
- _video_extensions = {
- 'highqual': 'mp4',
- 'lowqual': 'mp4',
- }
- IE_NAME = u'facebook'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def _reporter(self, message):
- """Add header and report message."""
- self._downloader.to_screen(u'[facebook] %s' % message)
-
- def report_login(self):
- """Report attempt to log in."""
- self._reporter(u'Logging in')
-
- def report_video_webpage_download(self, video_id):
- """Report attempt to download video webpage."""
- self._reporter(u'%s: Downloading video webpage' % video_id)
-
- def report_information_extraction(self, video_id):
- """Report attempt to extract video information."""
- self._reporter(u'%s: Extracting video information' % video_id)
-
- def _parse_page(self, video_webpage):
- """Extract video information from page"""
- # General data
- data = {'title': r'class="video_title datawrap">(.*?)</',
- 'description': r'<div class="datawrap">(.*?)</div>',
- 'owner': r'\("video_owner_name", "(.*?)"\)',
- 'upload_date': r'data-date="(.*?)"',
- 'thumbnail': r'\("thumb_url", "(?P<THUMB>.*?)"\)',
- }
- video_info = {}
- for piece in data.keys():
- mobj = re.search(data[piece], video_webpage)
- if mobj is not None:
- video_info[piece] = urllib.unquote_plus(mobj.group(1).decode("unicode_escape"))
-
- # Video urls
- video_urls = {}
- for fmt in self._available_formats:
- mobj = re.search(r'\("%s_src\", "(.+?)"\)' % fmt, video_webpage)
- if mobj is not None:
- # URL is in a Javascript segment inside an escaped Unicode format within
- # the generally utf-8 page
- video_urls[fmt] = urllib.unquote_plus(mobj.group(1).decode("unicode_escape"))
- video_info['video_urls'] = video_urls
-
- return video_info
-
- def _real_initialize(self):
- if self._downloader is None:
- return
-
- useremail = None
- password = None
- downloader_params = self._downloader.params
-
- # Attempt to use provided username and password or .netrc data
- if downloader_params.get('username', None) is not None:
- useremail = downloader_params['username']
- password = downloader_params['password']
- elif downloader_params.get('usenetrc', False):
- try:
- info = netrc.netrc().authenticators(self._NETRC_MACHINE)
- if info is not None:
- useremail = info[0]
- password = info[2]
- else:
- raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
- except (IOError, netrc.NetrcParseError), err:
- self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err))
- return
-
- if useremail is None:
- return
-
- # Log in
- login_form = {
- 'email': useremail,
- 'pass': password,
- 'login': 'Log+In'
- }
- request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form))
- try:
- self.report_login()
- login_results = urllib2.urlopen(request).read()
- if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None:
- self._downloader.to_stderr(u'WARNING: unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.')
- return
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err))
- return
-
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
- return
- video_id = mobj.group('ID')
-
- # Get video webpage
- self.report_video_webpage_download(video_id)
- request = urllib2.Request('https://www.facebook.com/video/video.php?v=%s' % video_id)
- try:
- page = urllib2.urlopen(request)
- video_webpage = page.read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
- return
-
- # Start extracting information
- self.report_information_extraction(video_id)
-
- # Extract information
- video_info = self._parse_page(video_webpage)
-
- # uploader
- if 'owner' not in video_info:
- self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
- return
- video_uploader = video_info['owner']
-
- # title
- if 'title' not in video_info:
- self._downloader.trouble(u'ERROR: unable to extract video title')
- return
- video_title = video_info['title']
- video_title = video_title.decode('utf-8')
- video_title = sanitize_title(video_title)
-
- # simplified title
- simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
- simple_title = simple_title.strip(ur'_')
-
- # thumbnail image
- if 'thumbnail' not in video_info:
- self._downloader.trouble(u'WARNING: unable to extract video thumbnail')
- video_thumbnail = ''
- else:
- video_thumbnail = video_info['thumbnail']
-
- # upload date
- upload_date = u'NA'
- if 'upload_date' in video_info:
- upload_time = video_info['upload_date']
- timetuple = email.utils.parsedate_tz(upload_time)
- if timetuple is not None:
- try:
- upload_date = time.strftime('%Y%m%d', timetuple[0:9])
- except:
- pass
-
- # description
- video_description = video_info.get('description', 'No description available.')
-
- url_map = video_info['video_urls']
- if len(url_map.keys()) > 0:
- # Decide which formats to download
- req_format = self._downloader.params.get('format', None)
- format_limit = self._downloader.params.get('format_limit', None)
-
- if format_limit is not None and format_limit in self._available_formats:
- format_list = self._available_formats[self._available_formats.index(format_limit):]
- else:
- format_list = self._available_formats
- existing_formats = [x for x in format_list if x in url_map]
- if len(existing_formats) == 0:
- self._downloader.trouble(u'ERROR: no known formats available for video')
- return
- if req_format is None:
- video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
- elif req_format == 'worst':
- video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality
- elif req_format == '-1':
- video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
- else:
- # Specific format
- if req_format not in url_map:
- self._downloader.trouble(u'ERROR: requested format not available')
- return
- video_url_list = [(req_format, url_map[req_format])] # Specific format
-
- for format_param, video_real_url in video_url_list:
-
- # At this point we have a new video
- self._downloader.increment_downloads()
-
- # Extension
- video_extension = self._video_extensions.get(format_param, 'mp4')
-
- try:
- # Process video information
- self._downloader.process_info({
- 'id': video_id.decode('utf-8'),
- 'url': video_real_url.decode('utf-8'),
- 'uploader': video_uploader.decode('utf-8'),
- 'upload_date': upload_date,
- 'title': video_title,
- 'stitle': simple_title,
- 'ext': video_extension.decode('utf-8'),
- 'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
- 'thumbnail': video_thumbnail.decode('utf-8'),
- 'description': video_description.decode('utf-8'),
- 'player_url': None,
- })
- except UnavailableVideoError, err:
- self._downloader.trouble(u'\nERROR: unable to download video')
-
-class BlipTVIE(InfoExtractor):
- """Information extractor for blip.tv"""
-
- _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv(/.+)$'
- _URL_EXT = r'^.*\.([a-z0-9]+)$'
- IE_NAME = u'blip.tv'
-
- def report_extraction(self, file_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id))
-
- def report_direct_download(self, title):
- """Report information extraction."""
- self._downloader.to_screen(u'[%s] %s: Direct download detected' % (self.IE_NAME, title))
-
- def _simplify_title(self, title):
- res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
- res = res.strip(ur'_')
- return res
-
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
- return
-
- if '?' in url:
- cchar = '&'
- else:
- cchar = '?'
- json_url = url + cchar + 'skin=json&version=2&no_wrap=1'
- request = urllib2.Request(json_url)
- self.report_extraction(mobj.group(1))
- info = None
- try:
- urlh = urllib2.urlopen(request)
- if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download
- basename = url.split('/')[-1]
- title,ext = os.path.splitext(basename)
- ext = ext.replace('.', '')
- self.report_direct_download(title)
- info = {
- 'id': title,
- 'url': url,
- 'title': title,
- 'stitle': self._simplify_title(title),
- 'ext': ext,
- 'urlhandle': urlh
- }
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
- return
- if info is None: # Regular URL
- try:
- json_code = urlh.read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to read video info webpage: %s' % str(err))
- return
-
- try:
- json_data = json.loads(json_code)
- if 'Post' in json_data:
- data = json_data['Post']
- else:
- data = json_data
-
- upload_date = datetime.datetime.strptime(data['datestamp'], '%m-%d-%y %H:%M%p').strftime('%Y%m%d')
- video_url = data['media']['url']
- umobj = re.match(self._URL_EXT, video_url)
- if umobj is None:
- raise ValueError('Can not determine filename extension')
- ext = umobj.group(1)
-
- info = {
- 'id': data['item_id'],
- 'url': video_url,
- 'uploader': data['display_name'],
- 'upload_date': upload_date,
- 'title': data['title'],
- 'stitle': self._simplify_title(data['title']),
- 'ext': ext,
- 'format': data['media']['mimeType'],
- 'thumbnail': data['thumbnailUrl'],
- 'description': data['description'],
- 'player_url': data['embedUrl']
- }
- except (ValueError,KeyError), err:
- self._downloader.trouble(u'ERROR: unable to parse video information: %s' % repr(err))
- return
-
- self._downloader.increment_downloads()
-
- try:
- self._downloader.process_info(info)
- except UnavailableVideoError, err:
- self._downloader.trouble(u'\nERROR: unable to download video')
-
-
-class MyVideoIE(InfoExtractor):
- """Information Extractor for myvideo.de."""
-
- _VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/watch/([0-9]+)/([^?/]+).*'
- IE_NAME = u'myvideo'
-
- def __init__(self, downloader=None):
- InfoExtractor.__init__(self, downloader)
-
- def report_download_webpage(self, video_id):
- """Report webpage download."""
- self._downloader.to_screen(u'[myvideo] %s: Downloading webpage' % video_id)
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[myvideo] %s: Extracting information' % video_id)
-
- def _real_initialize(self):
- return
-
- def _real_extract(self,url):
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- self._download.trouble(u'ERROR: invalid URL: %s' % url)
- return
-
- video_id = mobj.group(1)
- simple_title = mobj.group(2).decode('utf-8')
- # should actually not be necessary
- simple_title = sanitize_title(simple_title)
- simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', simple_title)
-
- # Get video webpage
- request = urllib2.Request('http://www.myvideo.de/watch/%s' % video_id)
- try:
- self.report_download_webpage(video_id)
- webpage = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
- return
-
- self.report_extraction(video_id)
- mobj = re.search(r'<link rel=\'image_src\' href=\'(http://is[0-9].myvideo\.de/de/movie[0-9]+/[a-f0-9]+)/thumbs/[^.]+\.jpg\' />',
- webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract media URL')
- return
- video_url = mobj.group(1) + ('/%s.flv' % video_id)
-
- mobj = re.search('<title>([^<]+)</title>', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract title')
- return
-
- video_title = mobj.group(1)
- video_title = sanitize_title(video_title)
-
- try:
- self._downloader.process_info({
- 'id': video_id,
- 'url': video_url,
- 'uploader': u'NA',
- 'upload_date': u'NA',
- 'title': video_title,
- 'stitle': simple_title,
- 'ext': u'flv',
- 'format': u'NA',
- 'player_url': None,
- })
- except UnavailableVideoError:
- self._downloader.trouble(u'\nERROR: Unable to download video')
-
-class ComedyCentralIE(InfoExtractor):
- """Information extractor for The Daily Show and Colbert Report """
-
- _VALID_URL = r'^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport))|(https?://)?(www\.)?(?P<showname>thedailyshow|colbertnation)\.com/full-episodes/(?P<episode>.*)$'
- IE_NAME = u'comedycentral'
-
- def report_extraction(self, episode_id):
- self._downloader.to_screen(u'[comedycentral] %s: Extracting information' % episode_id)
-
- def report_config_download(self, episode_id):
- self._downloader.to_screen(u'[comedycentral] %s: Downloading configuration' % episode_id)
-
- def report_index_download(self, episode_id):
- self._downloader.to_screen(u'[comedycentral] %s: Downloading show index' % episode_id)
-
- def report_player_url(self, episode_id):
- self._downloader.to_screen(u'[comedycentral] %s: Determining player URL' % episode_id)
-
- def _simplify_title(self, title):
- res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
- res = res.strip(ur'_')
- return res
-
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
- return
-
- if mobj.group('shortname'):
- if mobj.group('shortname') in ('tds', 'thedailyshow'):
- url = 'http://www.thedailyshow.com/full-episodes/'
- else:
- url = 'http://www.colbertnation.com/full-episodes/'
- mobj = re.match(self._VALID_URL, url)
- assert mobj is not None
-
- dlNewest = not mobj.group('episode')
- if dlNewest:
- epTitle = mobj.group('showname')
- else:
- epTitle = mobj.group('episode')
-
- req = urllib2.Request(url)
- self.report_extraction(epTitle)
- try:
- htmlHandle = urllib2.urlopen(req)
- html = htmlHandle.read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err))
- return
- if dlNewest:
- url = htmlHandle.geturl()
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: Invalid redirected URL: ' + url)
- return
- if mobj.group('episode') == '':
- self._downloader.trouble(u'ERROR: Redirected URL is still not specific: ' + url)
- return
- epTitle = mobj.group('episode')
-
- mMovieParams = re.findall('<param name="movie" value="(http://media.mtvnservices.com/([^"]*episode.*?:.*?))"/>', html)
- if len(mMovieParams) == 0:
- self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url)
- return
-
- playerUrl_raw = mMovieParams[0][0]
- self.report_player_url(epTitle)
- try:
- urlHandle = urllib2.urlopen(playerUrl_raw)
- playerUrl = urlHandle.geturl()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to find out player URL: ' + unicode(err))
- return
-
- uri = mMovieParams[0][1]
- indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + urllib.urlencode({'uri': uri})
- self.report_index_download(epTitle)
- try:
- indexXml = urllib2.urlopen(indexUrl).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download episode index: ' + unicode(err))
- return
-
- idoc = xml.etree.ElementTree.fromstring(indexXml)
- itemEls = idoc.findall('.//item')
- for itemEl in itemEls:
- mediaId = itemEl.findall('./guid')[0].text
- shortMediaId = mediaId.split(':')[-1]
- showId = mediaId.split(':')[-2].replace('.com', '')
- officialTitle = itemEl.findall('./title')[0].text
- officialDate = itemEl.findall('./pubDate')[0].text
-
- configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' +
- urllib.urlencode({'uri': mediaId}))
- configReq = urllib2.Request(configUrl)
- self.report_config_download(epTitle)
- try:
- configXml = urllib2.urlopen(configReq).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download webpage: %s' % unicode(err))
- return
-
- cdoc = xml.etree.ElementTree.fromstring(configXml)
- turls = []
- for rendition in cdoc.findall('.//rendition'):
- finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text)
- turls.append(finfo)
-
- if len(turls) == 0:
- self._downloader.trouble(u'\nERROR: unable to download ' + mediaId + ': No videos found')
- continue
-
- # For now, just pick the highest bitrate
- format,video_url = turls[-1]
-
- self._downloader.increment_downloads()
-
- effTitle = showId + '-' + epTitle
- info = {
- 'id': shortMediaId,
- 'url': video_url,
- 'uploader': showId,
- 'upload_date': officialDate,
- 'title': effTitle,
- 'stitle': self._simplify_title(effTitle),
- 'ext': 'mp4',
- 'format': format,
- 'thumbnail': None,
- 'description': officialTitle,
- 'player_url': playerUrl
- }
-
- try:
- self._downloader.process_info(info)
- except UnavailableVideoError, err:
- self._downloader.trouble(u'\nERROR: unable to download ' + mediaId)
- continue
-
-
-class EscapistIE(InfoExtractor):
- """Information extractor for The Escapist """
-
- _VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
- IE_NAME = u'escapist'
-
- def report_extraction(self, showName):
- self._downloader.to_screen(u'[escapist] %s: Extracting information' % showName)
-
- def report_config_download(self, showName):
- self._downloader.to_screen(u'[escapist] %s: Downloading configuration' % showName)
-
- def _simplify_title(self, title):
- res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
- res = res.strip(ur'_')
- return res
-
- def _real_extract(self, url):
- htmlParser = HTMLParser.HTMLParser()
-
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
- return
- showName = mobj.group('showname')
- videoId = mobj.group('episode')
-
- self.report_extraction(showName)
- try:
- webPage = urllib2.urlopen(url).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download webpage: ' + unicode(err))
- return
-
- descMatch = re.search('<meta name="description" content="([^"]*)"', webPage)
- description = htmlParser.unescape(descMatch.group(1))
- imgMatch = re.search('<meta property="og:image" content="([^"]*)"', webPage)
- imgUrl = htmlParser.unescape(imgMatch.group(1))
- playerUrlMatch = re.search('<meta property="og:video" content="([^"]*)"', webPage)
- playerUrl = htmlParser.unescape(playerUrlMatch.group(1))
- configUrlMatch = re.search('config=(.*)$', playerUrl)
- configUrl = urllib2.unquote(configUrlMatch.group(1))
-
- self.report_config_download(showName)
- try:
- configJSON = urllib2.urlopen(configUrl).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download configuration: ' + unicode(err))
- return
-
- # Technically, it's JavaScript, not JSON
- configJSON = configJSON.replace("'", '"')
-
- try:
- config = json.loads(configJSON)
- except (ValueError,), err:
- self._downloader.trouble(u'ERROR: Invalid JSON in configuration file: ' + unicode(err))
- return
-
- playlist = config['playlist']
- videoUrl = playlist[1]['url']
-
- self._downloader.increment_downloads()
- info = {
- 'id': videoId,
- 'url': videoUrl,
- 'uploader': showName,
- 'upload_date': None,
- 'title': showName,
- 'stitle': self._simplify_title(showName),
- 'ext': 'flv',
- 'format': 'flv',
- 'thumbnail': imgUrl,
- 'description': description,
- 'player_url': playerUrl,
- }
-
- try:
- self._downloader.process_info(info)
- except UnavailableVideoError, err:
- self._downloader.trouble(u'\nERROR: unable to download ' + videoId)
-
-
-class CollegeHumorIE(InfoExtractor):
- """Information extractor for collegehumor.com"""
-
- _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/video/(?P<videoid>[0-9]+)/(?P<shorttitle>.*)$'
- IE_NAME = u'collegehumor'
-
- def report_webpage(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
-
- def _simplify_title(self, title):
- res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
- res = res.strip(ur'_')
- return res
-
- def _real_extract(self, url):
- htmlParser = HTMLParser.HTMLParser()
-
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
- return
- video_id = mobj.group('videoid')
-
- self.report_webpage(video_id)
- request = urllib2.Request(url)
- try:
- webpage = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
- return
-
- m = re.search(r'id="video:(?P<internalvideoid>[0-9]+)"', webpage)
- if m is None:
- self._downloader.trouble(u'ERROR: Cannot extract internal video ID')
- return
- internal_video_id = m.group('internalvideoid')
-
- info = {
- 'id': video_id,
- 'internal_id': internal_video_id,
- }
-
- self.report_extraction(video_id)
- xmlUrl = 'http://www.collegehumor.com/moogaloop/video:' + internal_video_id
- try:
- metaXml = urllib2.urlopen(xmlUrl).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % str(err))
- return
-
- mdoc = xml.etree.ElementTree.fromstring(metaXml)
- try:
- videoNode = mdoc.findall('./video')[0]
- info['description'] = videoNode.findall('./description')[0].text
- info['title'] = videoNode.findall('./caption')[0].text
- info['stitle'] = self._simplify_title(info['title'])
- info['url'] = videoNode.findall('./file')[0].text
- info['thumbnail'] = videoNode.findall('./thumbnail')[0].text
- info['ext'] = info['url'].rpartition('.')[2]
- info['format'] = info['ext']
- except IndexError:
- self._downloader.trouble(u'\nERROR: Invalid metadata XML file')
- return
-
- self._downloader.increment_downloads()
-
- try:
- self._downloader.process_info(info)
- except UnavailableVideoError, err:
- self._downloader.trouble(u'\nERROR: unable to download video')
-
-
-class XVideosIE(InfoExtractor):
- """Information extractor for xvideos.com"""
-
- _VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)'
- IE_NAME = u'xvideos'
-
- def report_webpage(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id))
-
- def report_extraction(self, video_id):
- """Report information extraction."""
- self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
-
- def _simplify_title(self, title):
- res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
- res = res.strip(ur'_')
- return res
-
- def _real_extract(self, url):
- htmlParser = HTMLParser.HTMLParser()
-
- mobj = re.match(self._VALID_URL, url)
- if mobj is None:
- self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
- return
- video_id = mobj.group(1).decode('utf-8')
-
- self.report_webpage(video_id)
-
- request = urllib2.Request(r'http://www.xvideos.com/video' + video_id)
- try:
- webpage = urllib2.urlopen(request).read()
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
- return
-
- self.report_extraction(video_id)
-
-
- # Extract video URL
- mobj = re.search(r'flv_url=(.+?)&', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video url')
- return
- video_url = urllib2.unquote(mobj.group(1).decode('utf-8'))
-
-
- # Extract title
- mobj = re.search(r'<title>(.*?)\s+-\s+XVID', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video title')
- return
- video_title = mobj.group(1).decode('utf-8')
-
-
- # Extract video thumbnail
- mobj = re.search(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]/[a-fA-F0-9]/[a-fA-F0-9]/([a-fA-F0-9.]+jpg)', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
- return
- video_thumbnail = mobj.group(1).decode('utf-8')
-
-
-
- self._downloader.increment_downloads()
- info = {
- 'id': video_id,
- 'url': video_url,
- 'uploader': None,
- 'upload_date': None,
- 'title': video_title,
- 'stitle': self._simplify_title(video_title),
- 'ext': 'flv',
- 'format': 'flv',
- 'thumbnail': video_thumbnail,
- 'description': None,
- 'player_url': None,
- }
-
- try:
- self._downloader.process_info(info)
- except UnavailableVideoError, err:
- self._downloader.trouble(u'\nERROR: unable to download ' + video_id)
-
-
-class PostProcessor(object):
- """Post Processor class.
-
- PostProcessor objects can be added to downloaders with their
- add_post_processor() method. When the downloader has finished a
- successful download, it will take its internal chain of PostProcessors
- and start calling the run() method on each one of them, first with
- an initial argument and then with the returned value of the previous
- PostProcessor.
-
- The chain will be stopped if one of them ever returns None or the end
- of the chain is reached.
-
- PostProcessor objects follow a "mutual registration" process similar
- to InfoExtractor objects.
- """
-
- _downloader = None
-
- def __init__(self, downloader=None):
- self._downloader = downloader
-
- def set_downloader(self, downloader):
- """Sets the downloader for this PP."""
- self._downloader = downloader
-
- def run(self, information):
- """Run the PostProcessor.
-
- The "information" argument is a dictionary like the ones
- composed by InfoExtractors. The only difference is that this
- one has an extra field called "filepath" that points to the
- downloaded file.
-
- When this method returns None, the postprocessing chain is
- stopped. However, this method may return an information
- dictionary that will be passed to the next postprocessing
- object in the chain. It can be the one it received after
- changing some fields.
-
- In addition, this method may raise a PostProcessingError
- exception that will be taken into account by the downloader
- it was called from.
- """
- return information # by default, do nothing
-
-
-class FFmpegExtractAudioPP(PostProcessor):
-
- def __init__(self, downloader=None, preferredcodec=None, preferredquality=None, keepvideo=False):
- PostProcessor.__init__(self, downloader)
- if preferredcodec is None:
- preferredcodec = 'best'
- self._preferredcodec = preferredcodec
- self._preferredquality = preferredquality
- self._keepvideo = keepvideo
-
- @staticmethod
- def get_audio_codec(path):
- try:
- cmd = ['ffprobe', '-show_streams', '--', path]
- handle = subprocess.Popen(cmd, stderr=file(os.path.devnull, 'w'), stdout=subprocess.PIPE)
- output = handle.communicate()[0]
- if handle.wait() != 0:
- return None
- except (IOError, OSError):
- return None
- audio_codec = None
- for line in output.split('\n'):
- if line.startswith('codec_name='):
- audio_codec = line.split('=')[1].strip()
- elif line.strip() == 'codec_type=audio' and audio_codec is not None:
- return audio_codec
- return None
-
- @staticmethod
- def run_ffmpeg(path, out_path, codec, more_opts):
- try:
- cmd = ['ffmpeg', '-y', '-i', path, '-vn', '-acodec', codec] + more_opts + ['--', out_path]
- ret = subprocess.call(cmd, stdout=file(os.path.devnull, 'w'), stderr=subprocess.STDOUT)
- return (ret == 0)
- except (IOError, OSError):
- return False
-
- def run(self, information):
- path = information['filepath']
-
- filecodec = self.get_audio_codec(path)
- if filecodec is None:
- self._downloader.to_stderr(u'WARNING: unable to obtain file audio codec with ffprobe')
- return None
-
- more_opts = []
- if self._preferredcodec == 'best' or self._preferredcodec == filecodec:
- if filecodec in ['aac', 'mp3', 'vorbis']:
- # Lossless if possible
- acodec = 'copy'
- extension = filecodec
- if filecodec == 'aac':
- more_opts = ['-f', 'adts']
- if filecodec == 'vorbis':
- extension = 'ogg'
- else:
- # MP3 otherwise.
- acodec = 'libmp3lame'
- extension = 'mp3'
- more_opts = []
- if self._preferredquality is not None:
- more_opts += ['-ab', self._preferredquality]
- else:
- # We convert the audio (lossy)
- acodec = {'mp3': 'libmp3lame', 'aac': 'aac', 'vorbis': 'libvorbis'}[self._preferredcodec]
- extension = self._preferredcodec
- more_opts = []
- if self._preferredquality is not None:
- more_opts += ['-ab', self._preferredquality]
- if self._preferredcodec == 'aac':
- more_opts += ['-f', 'adts']
- if self._preferredcodec == 'vorbis':
- extension = 'ogg'
-
- (prefix, ext) = os.path.splitext(path)
- new_path = prefix + '.' + extension
- self._downloader.to_screen(u'[ffmpeg] Destination: %s' % new_path)
- status = self.run_ffmpeg(path, new_path, acodec, more_opts)
-
- if not status:
- self._downloader.to_stderr(u'WARNING: error running ffmpeg')
- return None
-
- # Try to update the date time for extracted audio file.
- if information.get('filetime') is not None:
- try:
- os.utime(new_path, (time.time(), information['filetime']))
- except:
- self._downloader.to_stderr(u'WARNING: Cannot update utime of audio file')
-
- if not self._keepvideo:
- try:
- os.remove(path)
- except (IOError, OSError):
- self._downloader.to_stderr(u'WARNING: Unable to remove downloaded video file')
- return None
-
- information['filepath'] = new_path
- return information
-
-
-def updateSelf(downloader, filename):
- ''' Update the program file with the latest version from the repository '''
- # Note: downloader only used for options
- if not os.access(filename, os.W_OK):
- sys.exit('ERROR: no write permissions on %s' % filename)
-
- downloader.to_screen('Updating to latest version...')
-
- try:
- try:
- urlh = urllib.urlopen(UPDATE_URL)
- newcontent = urlh.read()
-
- vmatch = re.search("__version__ = '([^']+)'", newcontent)
- if vmatch is not None and vmatch.group(1) == __version__:
- downloader.to_screen('youtube-dl is up-to-date (' + __version__ + ')')
- return
- finally:
- urlh.close()
- except (IOError, OSError), err:
- sys.exit('ERROR: unable to download latest version')
-
- try:
- outf = open(filename, 'wb')
- try:
- outf.write(newcontent)
- finally:
- outf.close()
- except (IOError, OSError), err:
- sys.exit('ERROR: unable to overwrite current version')
-
- downloader.to_screen('Updated youtube-dl. Restart youtube-dl to use the new version.')
-
-def parseOpts():
- # Deferred imports
- import getpass
- import optparse
-
- def _format_option_string(option):
- ''' ('-o', '--option') -> -o, --format METAVAR'''
-
- opts = []
-
- if option._short_opts: opts.append(option._short_opts[0])
- if option._long_opts: opts.append(option._long_opts[0])
- if len(opts) > 1: opts.insert(1, ', ')
-
- if option.takes_value(): opts.append(' %s' % option.metavar)
-
- return "".join(opts)
-
- def _find_term_columns():
- columns = os.environ.get('COLUMNS', None)
- if columns:
- return int(columns)
-
- try:
- sp = subprocess.Popen(['stty', 'size'], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
- out,err = sp.communicate()
- return int(out.split()[1])
- except:
- pass
- return None
-
- max_width = 80
- max_help_position = 80
-
- # No need to wrap help messages if we're on a wide console
- columns = _find_term_columns()
- if columns: max_width = columns
-
- fmt = optparse.IndentedHelpFormatter(width=max_width, max_help_position=max_help_position)
- fmt.format_option_strings = _format_option_string
-
- kw = {
- 'version' : __version__,
- 'formatter' : fmt,
- 'usage' : '%prog [options] url [url...]',
- 'conflict_handler' : 'resolve',
- }
-
- parser = optparse.OptionParser(**kw)
-
- # option groups
- general = optparse.OptionGroup(parser, 'General Options')
- selection = optparse.OptionGroup(parser, 'Video Selection')
- authentication = optparse.OptionGroup(parser, 'Authentication Options')
- video_format = optparse.OptionGroup(parser, 'Video Format Options')
- postproc = optparse.OptionGroup(parser, 'Post-processing Options')
- filesystem = optparse.OptionGroup(parser, 'Filesystem Options')
- verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options')
-
- general.add_option('-h', '--help',
- action='help', help='print this help text and exit')
- general.add_option('-v', '--version',
- action='version', help='print program version and exit')
- general.add_option('-U', '--update',
- action='store_true', dest='update_self', help='update this program to latest version')
- general.add_option('-i', '--ignore-errors',
- action='store_true', dest='ignoreerrors', help='continue on download errors', default=False)
- general.add_option('-r', '--rate-limit',
- dest='ratelimit', metavar='LIMIT', help='download rate limit (e.g. 50k or 44.6m)')
- general.add_option('-R', '--retries',
- dest='retries', metavar='RETRIES', help='number of retries (default is 10)', default=10)
- general.add_option('--dump-user-agent',
- action='store_true', dest='dump_user_agent',
- help='display the current browser identification', default=False)
- general.add_option('--list-extractors',
- action='store_true', dest='list_extractors',
- help='List all supported extractors and the URLs they would handle', default=False)
-
- selection.add_option('--playlist-start',
- dest='playliststart', metavar='NUMBER', help='playlist video to start at (default is 1)', default=1)
- selection.add_option('--playlist-end',
- dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1)
- selection.add_option('--match-title', dest='matchtitle', metavar='REGEX',help='download only matching titles (regex or caseless sub-string)')
- selection.add_option('--reject-title', dest='rejecttitle', metavar='REGEX',help='skip download for matching titles (regex or caseless sub-string)')
-
- authentication.add_option('-u', '--username',
- dest='username', metavar='USERNAME', help='account username')
- authentication.add_option('-p', '--password',
- dest='password', metavar='PASSWORD', help='account password')
- authentication.add_option('-n', '--netrc',
- action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
-
-
- video_format.add_option('-f', '--format',
- action='store', dest='format', metavar='FORMAT', help='video format code')
- video_format.add_option('--all-formats',
- action='store_const', dest='format', help='download all available video formats', const='all')
- video_format.add_option('--max-quality',
- action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
- video_format.add_option('-F', '--list-formats',
- action='store_true', dest='listformats', help='list all available formats (currently youtube only)')
-
-
- verbosity.add_option('-q', '--quiet',
- action='store_true', dest='quiet', help='activates quiet mode', default=False)
- verbosity.add_option('-s', '--simulate',
- action='store_true', dest='simulate', help='do not download the video and do not write anything to disk', default=False)
- verbosity.add_option('--skip-download',
- action='store_true', dest='skip_download', help='do not download the video', default=False)
- verbosity.add_option('-g', '--get-url',
- action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
- verbosity.add_option('-e', '--get-title',
- action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
- verbosity.add_option('--get-thumbnail',
- action='store_true', dest='getthumbnail',
- help='simulate, quiet but print thumbnail URL', default=False)
- verbosity.add_option('--get-description',
- action='store_true', dest='getdescription',
- help='simulate, quiet but print video description', default=False)
- verbosity.add_option('--get-filename',
- action='store_true', dest='getfilename',
- help='simulate, quiet but print output filename', default=False)
- verbosity.add_option('--get-format',
- action='store_true', dest='getformat',
- help='simulate, quiet but print output format', default=False)
- verbosity.add_option('--no-progress',
- action='store_true', dest='noprogress', help='do not print progress bar', default=False)
- verbosity.add_option('--console-title',
- action='store_true', dest='consoletitle',
- help='display progress in console titlebar', default=False)
-
-
- filesystem.add_option('-t', '--title',
- action='store_true', dest='usetitle', help='use title in file name', default=False)
- filesystem.add_option('-l', '--literal',
- action='store_true', dest='useliteral', help='use literal title in file name', default=False)
- filesystem.add_option('-A', '--auto-number',
- action='store_true', dest='autonumber',
- help='number downloaded files starting from 00000', default=False)
- filesystem.add_option('-o', '--output',
- dest='outtmpl', metavar='TEMPLATE', help='output filename template. Use %(stitle)s to get the title, %(uploader)s for the uploader name, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, and %% for a literal percent')
- filesystem.add_option('-a', '--batch-file',
- dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)')
- filesystem.add_option('-w', '--no-overwrites',
- action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
- filesystem.add_option('-c', '--continue',
- action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False)
- filesystem.add_option('--no-continue',
- action='store_false', dest='continue_dl',
- help='do not resume partially downloaded files (restart from beginning)')
- filesystem.add_option('--cookies',
- dest='cookiefile', metavar='FILE', help='file to read cookies from and dump cookie jar in')
- filesystem.add_option('--no-part',
- action='store_true', dest='nopart', help='do not use .part files', default=False)
- filesystem.add_option('--no-mtime',
- action='store_false', dest='updatetime',
- help='do not use the Last-modified header to set the file modification time', default=True)
- filesystem.add_option('--write-description',
- action='store_true', dest='writedescription',
- help='write video description to a .description file', default=False)
- filesystem.add_option('--write-info-json',
- action='store_true', dest='writeinfojson',
- help='write video metadata to a .info.json file', default=False)
-
-
- postproc.add_option('--extract-audio', action='store_true', dest='extractaudio', default=False,
- help='convert video files to audio-only files (requires ffmpeg and ffprobe)')
- postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best',
- help='"best", "aac", "vorbis" or "mp3"; best by default')
- postproc.add_option('--audio-quality', metavar='QUALITY', dest='audioquality', default='128K',
- help='ffmpeg audio bitrate specification, 128k by default')
- postproc.add_option('-k', '--keep-video', action='store_true', dest='keepvideo', default=False,
- help='keeps the video file on disk after the post-processing; the video is erased by default')
-
-
- parser.add_option_group(general)
- parser.add_option_group(selection)
- parser.add_option_group(filesystem)
- parser.add_option_group(verbosity)
- parser.add_option_group(video_format)
- parser.add_option_group(authentication)
- parser.add_option_group(postproc)
-
- opts, args = parser.parse_args()
-
- return parser, opts, args
-
-def gen_extractors():
- """ Return a list of an instance of every supported extractor.
- The order does matter; the first extractor matched is the one handling the URL.
- """
- youtube_ie = YoutubeIE()
- google_ie = GoogleIE()
- yahoo_ie = YahooIE()
- return [
- YoutubePlaylistIE(youtube_ie),
- YoutubeUserIE(youtube_ie),
- YoutubeSearchIE(youtube_ie),
- youtube_ie,
- MetacafeIE(youtube_ie),
- DailymotionIE(),
- google_ie,
- GoogleSearchIE(google_ie),
- PhotobucketIE(),
- yahoo_ie,
- YahooSearchIE(yahoo_ie),
- DepositFilesIE(),
- FacebookIE(),
- BlipTVIE(),
- VimeoIE(),
- MyVideoIE(),
- ComedyCentralIE(),
- EscapistIE(),
- CollegeHumorIE(),
- XVideosIE(),
-
- GenericIE()
- ]
-
-def main():
- parser, opts, args = parseOpts()
-
- # Open appropriate CookieJar
- if opts.cookiefile is None:
- jar = cookielib.CookieJar()
- else:
- try:
- jar = cookielib.MozillaCookieJar(opts.cookiefile)
- if os.path.isfile(opts.cookiefile) and os.access(opts.cookiefile, os.R_OK):
- jar.load()
- except (IOError, OSError), err:
- sys.exit(u'ERROR: unable to open cookie file')
-
- # Dump user agent
- if opts.dump_user_agent:
- print std_headers['User-Agent']
- sys.exit(0)
-
- # Batch file verification
- batchurls = []
- if opts.batchfile is not None:
- try:
- if opts.batchfile == '-':
- batchfd = sys.stdin
- else:
- batchfd = open(opts.batchfile, 'r')
- batchurls = batchfd.readlines()
- batchurls = [x.strip() for x in batchurls]
- batchurls = [x for x in batchurls if len(x) > 0 and not re.search(r'^[#/;]', x)]
- except IOError:
- sys.exit(u'ERROR: batch file could not be read')
- all_urls = batchurls + args
-
- # General configuration
- cookie_processor = urllib2.HTTPCookieProcessor(jar)
- opener = urllib2.build_opener(urllib2.ProxyHandler(), cookie_processor, YoutubeDLHandler())
- urllib2.install_opener(opener)
- socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
-
- extractors = gen_extractors()
-
- if opts.list_extractors:
- for ie in extractors:
- print(ie.IE_NAME)
- matchedUrls = filter(lambda url: ie.suitable(url), all_urls)
- all_urls = filter(lambda url: url not in matchedUrls, all_urls)
- for mu in matchedUrls:
- print(u' ' + mu)
- sys.exit(0)
-
- # Conflicting, missing and erroneous options
- if opts.usenetrc and (opts.username is not None or opts.password is not None):
- parser.error(u'using .netrc conflicts with giving username/password')
- if opts.password is not None and opts.username is None:
- parser.error(u'account username missing')
- if opts.outtmpl is not None and (opts.useliteral or opts.usetitle or opts.autonumber):
- parser.error(u'using output template conflicts with using title, literal title or auto number')
- if opts.usetitle and opts.useliteral:
- parser.error(u'using title conflicts with using literal title')
- if opts.username is not None and opts.password is None:
- opts.password = getpass.getpass(u'Type account password and press return:')
- if opts.ratelimit is not None:
- numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
- if numeric_limit is None:
- parser.error(u'invalid rate limit specified')
- opts.ratelimit = numeric_limit
- if opts.retries is not None:
- try:
- opts.retries = long(opts.retries)
- except (TypeError, ValueError), err:
- parser.error(u'invalid retry count specified')
- try:
- opts.playliststart = int(opts.playliststart)
- if opts.playliststart <= 0:
- raise ValueError(u'Playlist start must be positive')
- except (TypeError, ValueError), err:
- parser.error(u'invalid playlist start number specified')
- try:
- opts.playlistend = int(opts.playlistend)
- if opts.playlistend != -1 and (opts.playlistend <= 0 or opts.playlistend < opts.playliststart):
- raise ValueError(u'Playlist end must be greater than playlist start')
- except (TypeError, ValueError), err:
- parser.error(u'invalid playlist end number specified')
- if opts.extractaudio:
- if opts.audioformat not in ['best', 'aac', 'mp3', 'vorbis']:
- parser.error(u'invalid audio format specified')
-
- # File downloader
- fd = FileDownloader({
- 'usenetrc': opts.usenetrc,
- 'username': opts.username,
- 'password': opts.password,
- 'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat),
- 'forceurl': opts.geturl,
- 'forcetitle': opts.gettitle,
- 'forcethumbnail': opts.getthumbnail,
- 'forcedescription': opts.getdescription,
- 'forcefilename': opts.getfilename,
- 'forceformat': opts.getformat,
- 'simulate': opts.simulate,
- 'skip_download': (opts.skip_download or opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat),
- 'format': opts.format,
- 'format_limit': opts.format_limit,
- 'listformats': opts.listformats,
- 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding()))
- or (opts.format == '-1' and opts.usetitle and u'%(stitle)s-%(id)s-%(format)s.%(ext)s')
- or (opts.format == '-1' and opts.useliteral and u'%(title)s-%(id)s-%(format)s.%(ext)s')
- or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s')
- or (opts.usetitle and opts.autonumber and u'%(autonumber)s-%(stitle)s-%(id)s.%(ext)s')
- or (opts.useliteral and opts.autonumber and u'%(autonumber)s-%(title)s-%(id)s.%(ext)s')
- or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s')
- or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s')
- or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s')
- or u'%(id)s.%(ext)s'),
- 'ignoreerrors': opts.ignoreerrors,
- 'ratelimit': opts.ratelimit,
- 'nooverwrites': opts.nooverwrites,
- 'retries': opts.retries,
- 'continuedl': opts.continue_dl,
- 'noprogress': opts.noprogress,
- 'playliststart': opts.playliststart,
- 'playlistend': opts.playlistend,
- 'logtostderr': opts.outtmpl == '-',
- 'consoletitle': opts.consoletitle,
- 'nopart': opts.nopart,
- 'updatetime': opts.updatetime,
- 'writedescription': opts.writedescription,
- 'writeinfojson': opts.writeinfojson,
- 'matchtitle': opts.matchtitle,
- 'rejecttitle': opts.rejecttitle,
- })
- for extractor in extractors:
- fd.add_info_extractor(extractor)
-
- # PostProcessors
- if opts.extractaudio:
- fd.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, keepvideo=opts.keepvideo))
-
- # Update version
- if opts.update_self:
- updateSelf(fd, sys.argv[0])
-
- # Maybe do nothing
- if len(all_urls) < 1:
- if not opts.update_self:
- parser.error(u'you must provide at least one URL')
- else:
- sys.exit()
- retcode = fd.download(all_urls)
-
- # Dump cookie jar if requested
- if opts.cookiefile is not None:
- try:
- jar.save()
- except (IOError, OSError), err:
- sys.exit(u'ERROR: unable to save cookie jar')
-
- sys.exit(retcode)
-
-
-if __name__ == '__main__':
- try:
- main()
- except DownloadError:
- sys.exit(1)
- except SameFileError:
- sys.exit(u'ERROR: fixed output name but more than one file to download')
- except KeyboardInterrupt:
- sys.exit(u'\nERROR: Interrupted by user')