+
+class NBAIE(InfoExtractor):
+ _VALID_URL = r'^(?:https?://)?(?:watch\.|www\.)?nba\.com/(?:nba/)?video(/[^?]*)(\?.*)?$'
+ IE_NAME = u'nba'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ raise ExtractorError(u'Invalid URL: %s' % url)
+
+ video_id = mobj.group(1)
+ if video_id.endswith('/index.html'):
+ video_id = video_id[:-len('/index.html')]
+
+ webpage = self._download_webpage(url, video_id)
+
+ video_url = u'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4'
+ def _findProp(rexp, default=None):
+ m = re.search(rexp, webpage)
+ if m:
+ return unescapeHTML(m.group(1))
+ else:
+ return default
+
+ shortened_video_id = video_id.rpartition('/')[2]
+ title = _findProp(r'<meta property="og:title" content="(.*?)"', shortened_video_id).replace('NBA.com: ', '')
+ info = {
+ 'id': shortened_video_id,
+ 'url': video_url,
+ 'ext': 'mp4',
+ 'title': title,
+ 'uploader_date': _findProp(r'<b>Date:</b> (.*?)</div>'),
+ 'description': _findProp(r'<div class="description">(.*?)</h1>'),
+ }
+ return [info]
+
+class JustinTVIE(InfoExtractor):
+ """Information extractor for justin.tv and twitch.tv"""
+ # TODO: One broadcast may be split into multiple videos. The key
+ # 'broadcast_id' is the same for all parts, and 'broadcast_part'
+ # starts at 1 and increases. Can we treat all parts as one video?
+
+ _VALID_URL = r"""(?x)^(?:http://)?(?:www\.)?(?:twitch|justin)\.tv/
+ (?:
+ (?P<channelid>[^/]+)|
+ (?:(?:[^/]+)/b/(?P<videoid>[^/]+))|
+ (?:(?:[^/]+)/c/(?P<chapterid>[^/]+))
+ )
+ /?(?:\#.*)?$
+ """
+ _JUSTIN_PAGE_LIMIT = 100
+ IE_NAME = u'justin.tv'
+
+ def report_download_page(self, channel, offset):
+ """Report attempt to download a single page of videos."""
+ self.to_screen(u'%s: Downloading video information from %d to %d' %
+ (channel, offset, offset + self._JUSTIN_PAGE_LIMIT))
+
+ # Return count of items, list of *valid* items
+ def _parse_page(self, url, video_id):
+ webpage = self._download_webpage(url, video_id,
+ u'Downloading video info JSON',
+ u'unable to download video info JSON')
+
+ response = json.loads(webpage)
+ if type(response) != list:
+ error_text = response.get('error', 'unknown error')
+ raise ExtractorError(u'Justin.tv API: %s' % error_text)
+ info = []
+ for clip in response:
+ video_url = clip['video_file_url']
+ if video_url:
+ video_extension = os.path.splitext(video_url)[1][1:]
+ video_date = re.sub('-', '', clip['start_time'][:10])
+ video_uploader_id = clip.get('user_id', clip.get('channel_id'))
+ video_id = clip['id']
+ video_title = clip.get('title', video_id)
+ info.append({
+ 'id': video_id,
+ 'url': video_url,
+ 'title': video_title,
+ 'uploader': clip.get('channel_name', video_uploader_id),
+ 'uploader_id': video_uploader_id,
+ 'upload_date': video_date,
+ 'ext': video_extension,
+ })
+ return (len(response), info)
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ raise ExtractorError(u'invalid URL: %s' % url)
+
+ api_base = 'http://api.justin.tv'
+ paged = False
+ if mobj.group('channelid'):
+ paged = True
+ video_id = mobj.group('channelid')
+ api = api_base + '/channel/archives/%s.json' % video_id
+ elif mobj.group('chapterid'):
+ chapter_id = mobj.group('chapterid')
+
+ webpage = self._download_webpage(url, chapter_id)
+ m = re.search(r'PP\.archive_id = "([0-9]+)";', webpage)
+ if not m:
+ raise ExtractorError(u'Cannot find archive of a chapter')
+ archive_id = m.group(1)
+
+ api = api_base + '/broadcast/by_chapter/%s.xml' % chapter_id
+ chapter_info_xml = self._download_webpage(api, chapter_id,
+ note=u'Downloading chapter information',
+ errnote=u'Chapter information download failed')
+ doc = xml.etree.ElementTree.fromstring(chapter_info_xml)
+ for a in doc.findall('.//archive'):
+ if archive_id == a.find('./id').text:
+ break
+ else:
+ raise ExtractorError(u'Could not find chapter in chapter information')
+
+ video_url = a.find('./video_file_url').text
+ video_ext = video_url.rpartition('.')[2] or u'flv'
+
+ chapter_api_url = u'https://api.twitch.tv/kraken/videos/c' + chapter_id
+ chapter_info_json = self._download_webpage(chapter_api_url, u'c' + chapter_id,
+ note='Downloading chapter metadata',
+ errnote='Download of chapter metadata failed')
+ chapter_info = json.loads(chapter_info_json)
+
+ 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 += u'?start=' + TODO:start_timestamp
+ # bracket_start is 13290, but we want 51670615
+ self._downloader.report_warning(u'Chapter detected, but we can just download the whole file. '
+ u'Chapter starts at %s and ends at %s' % (formatSeconds(bracket_start), formatSeconds(bracket_end)))
+
+ info = {
+ 'id': u'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]
+ else:
+ video_id = mobj.group('videoid')
+ api = api_base + '/broadcast/by_archive/%s.json' % video_id
+
+ self.report_extraction(video_id)
+
+ info = []
+ offset = 0
+ limit = self._JUSTIN_PAGE_LIMIT
+ while True:
+ if paged:
+ self.report_download_page(video_id, offset)
+ page_url = api + ('?offset=%d&limit=%d' % (offset, limit))
+ page_count, page_info = self._parse_page(page_url, video_id)
+ info.extend(page_info)
+ if not paged or page_count != limit:
+ break
+ offset += limit
+ return info
+
+class FunnyOrDieIE(InfoExtractor):
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?funnyordie\.com/videos/(?P<id>[0-9a-f]+)/.*$'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ raise ExtractorError(u'invalid URL: %s' % url)
+
+ video_id = mobj.group('id')
+ webpage = self._download_webpage(url, video_id)
+
+ m = re.search(r'<video[^>]*>\s*<source[^>]*>\s*<source src="(?P<url>[^"]+)"', webpage, re.DOTALL)
+ if not m:
+ raise ExtractorError(u'Unable to find video information')
+ video_url = unescapeHTML(m.group('url'))
+
+ m = re.search(r"<h1 class='player_page_h1'.*?>(?P<title>.*?)</h1>", webpage, flags=re.DOTALL)
+ if not m:
+ m = re.search(r'<title>(?P<title>[^<]+?)</title>', webpage)
+ if not m:
+ raise ExtractorError(u'Cannot find video title')
+ title = clean_html(m.group('title'))
+
+ m = re.search(r'<meta property="og:description" content="(?P<desc>.*?)"', webpage)
+ if m:
+ desc = unescapeHTML(m.group('desc'))
+ else:
+ desc = None
+
+ info = {
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': 'mp4',
+ 'title': title,
+ 'description': desc,
+ }
+ return [info]
+
+class SteamIE(InfoExtractor):
+ _VALID_URL = r"""http://store\.steampowered\.com/
+ (agecheck/)?
+ (?P<urltype>video|app)/ #If the page is only for videos or for a game
+ (?P<gameID>\d+)/?
+ (?P<videoID>\d*)(?P<extra>\??) #For urltype == video we sometimes get the videoID
+ """
+
+ @classmethod
+ def suitable(cls, url):
+ """Receives a URL and returns True if suitable for this IE."""
+ return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
+
+ def _real_extract(self, url):
+ m = re.match(self._VALID_URL, url, re.VERBOSE)
+ gameID = m.group('gameID')
+ videourl = 'http://store.steampowered.com/agecheck/video/%s/?snr=1_agecheck_agecheck__age-gate&ageDay=1&ageMonth=January&ageYear=1970' % gameID
+ self.report_age_confirmation()
+ webpage = self._download_webpage(videourl, gameID)
+ game_title = re.search(r'<h2 class="pageheader">(?P<game_title>.*?)</h2>', webpage).group('game_title')
+
+ urlRE = r"'movie_(?P<videoID>\d+)': \{\s*FILENAME: \"(?P<videoURL>[\w:/\.\?=]+)\"(,\s*MOVIE_NAME: \"(?P<videoName>[\w:/\.\?=\+-]+)\")?\s*\},"
+ mweb = re.finditer(urlRE, webpage)
+ namesRE = r'<span class="title">(?P<videoName>.+?)</span>'
+ titles = re.finditer(namesRE, webpage)
+ thumbsRE = r'<img class="movie_thumb" src="(?P<thumbnail>.+?)">'
+ thumbs = re.finditer(thumbsRE, webpage)
+ videos = []
+ for vid,vtitle,thumb in zip(mweb,titles,thumbs):
+ video_id = vid.group('videoID')
+ title = vtitle.group('videoName')
+ video_url = vid.group('videoURL')
+ video_thumb = thumb.group('thumbnail')
+ if not video_url:
+ raise ExtractorError(u'Cannot find video url for %s' % video_id)
+ info = {
+ 'id':video_id,
+ 'url':video_url,
+ 'ext': 'flv',
+ 'title': unescapeHTML(title),
+ 'thumbnail': video_thumb
+ }
+ videos.append(info)
+ return [self.playlist_result(videos, gameID, game_title)]
+
+class UstreamIE(InfoExtractor):
+ _VALID_URL = r'https?://www\.ustream\.tv/recorded/(?P<videoID>\d+)'
+ IE_NAME = u'ustream'
+
+ def _real_extract(self, url):
+ m = re.match(self._VALID_URL, url)
+ video_id = m.group('videoID')
+ video_url = u'http://tcdn.ustream.tv/video/%s' % video_id
+ webpage = self._download_webpage(url, video_id)
+ m = re.search(r'data-title="(?P<title>.+)"',webpage)
+ title = m.group('title')
+ m = re.search(r'<a class="state" data-content-type="channel" data-content-id="(?P<uploader>\d+)"',webpage)
+ uploader = m.group('uploader')
+ info = {
+ 'id':video_id,
+ 'url':video_url,
+ 'ext': 'flv',
+ 'title': title,
+ 'uploader': uploader
+ }
+ return [info]
+
+class WorldStarHipHopIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www|m)\.worldstar(?:candy|hiphop)\.com/videos/video\.php\?v=(?P<id>.*)'
+ IE_NAME = u'WorldStarHipHop'
+
+ def _real_extract(self, url):
+ _src_url = r'so\.addVariable\("file","(.*?)"\)'
+
+ m = re.match(self._VALID_URL, url)
+ video_id = m.group('id')
+
+ webpage_src = self._download_webpage(url, video_id)
+
+ mobj = re.search(_src_url, webpage_src)
+
+ if mobj is not None:
+ video_url = mobj.group(1)
+ if 'mp4' in video_url:
+ ext = 'mp4'
+ else:
+ ext = 'flv'
+ else:
+ raise ExtractorError(u'Cannot find video url for %s' % video_id)
+
+ mobj = re.search(r"<title>(.*)</title>", webpage_src)
+
+ if mobj is None:
+ raise ExtractorError(u'Cannot determine title')
+ title = mobj.group(1)
+
+ mobj = re.search(r'rel="image_src" href="(.*)" />', webpage_src)
+ # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
+ if mobj is not None:
+ thumbnail = mobj.group(1)
+ else:
+ _title = r"""candytitles.*>(.*)</span>"""
+ mobj = re.search(_title, webpage_src)
+ if mobj is not None:
+ title = mobj.group(1)
+ thumbnail = None
+
+ results = [{
+ 'id': video_id,
+ 'url' : video_url,
+ 'title' : title,
+ 'thumbnail' : thumbnail,
+ 'ext' : ext,
+ }]
+ return results
+
+class RBMARadioIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?rbmaradio\.com/shows/(?P<videoID>[^/]+)$'
+
+ def _real_extract(self, url):
+ m = re.match(self._VALID_URL, url)
+ video_id = m.group('videoID')
+
+ webpage = self._download_webpage(url, video_id)
+ m = re.search(r'<script>window.gon = {.*?};gon\.show=(.+?);</script>', webpage)
+ if not m:
+ raise ExtractorError(u'Cannot find metadata')
+ json_data = m.group(1)
+
+ try:
+ data = json.loads(json_data)
+ except ValueError as e:
+ raise ExtractorError(u'Invalid JSON: ' + str(e))
+
+ video_url = data['akamai_url'] + '&cbr=256'
+ url_parts = compat_urllib_parse_urlparse(video_url)
+ video_ext = url_parts.path.rpartition('.')[2]
+ info = {
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': video_ext,
+ 'title': data['title'],
+ 'description': data.get('teaser_text'),
+ 'location': data.get('country_of_origin'),
+ 'uploader': data.get('host', {}).get('name'),
+ 'uploader_id': data.get('host', {}).get('slug'),
+ 'thumbnail': data.get('image', {}).get('large_url_2x'),
+ 'duration': data.get('duration'),
+ }
+ return [info]
+
+
+class YouPornIE(InfoExtractor):
+ """Information extractor for youporn.com."""
+ _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+)'
+
+ def _print_formats(self, formats):
+ """Print all available formats"""
+ print(u'Available formats:')
+ print(u'ext\t\tformat')
+ print(u'---------------------------------')
+ for format in formats:
+ print(u'%s\t\t%s' % (format['ext'], format['format']))
+
+ def _specific(self, req_format, formats):
+ for x in formats:
+ if(x["format"]==req_format):
+ return x
+ return None
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ raise ExtractorError(u'Invalid URL: %s' % url)
+
+ video_id = mobj.group('videoid')
+
+ req = compat_urllib_request.Request(url)
+ req.add_header('Cookie', 'age_verified=1')
+ webpage = self._download_webpage(req, video_id)
+
+ # Get the video title
+ result = re.search(r'<h1.*?>(?P<title>.*)</h1>', webpage)
+ if result is None:
+ raise ExtractorError(u'Unable to extract video title')
+ video_title = result.group('title').strip()
+
+ # Get the video date
+ result = re.search(r'Date:</label>(?P<date>.*) </li>', webpage)
+ if result is None:
+ self._downloader.report_warning(u'unable to extract video date')
+ upload_date = None
+ else:
+ upload_date = unified_strdate(result.group('date').strip())
+
+ # Get the video uploader
+ result = re.search(r'Submitted:</label>(?P<uploader>.*)</li>', webpage)
+ if result is None:
+ self._downloader.report_warning(u'unable to extract uploader')
+ video_uploader = None
+ else:
+ video_uploader = result.group('uploader').strip()
+ video_uploader = clean_html( video_uploader )
+
+ # Get all of the formats available
+ DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>'
+ result = re.search(DOWNLOAD_LIST_RE, webpage)
+ if result is None:
+ raise ExtractorError(u'Unable to extract download list')
+ download_list_html = result.group('download_list').strip()
+
+ # Get all of the links from the page
+ LINK_RE = r'(?s)<a href="(?P<url>[^"]+)">'
+ links = re.findall(LINK_RE, download_list_html)
+ if(len(links) == 0):
+ raise ExtractorError(u'ERROR: no known formats available for video')
+
+ self.to_screen(u'Links found: %d' % len(links))
+
+ formats = []
+ for link in links:
+
+ # A link looks like this:
+ # http://cdn1.download.youporn.phncdn.com/201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4?nvb=20121113051249&nva=20121114051249&ir=1200&sr=1200&hash=014b882080310e95fb6a0
+ # A path looks like this:
+ # /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4
+ video_url = unescapeHTML( link )
+ path = compat_urllib_parse_urlparse( video_url ).path
+ extension = os.path.splitext( path )[1][1:]
+ format = path.split('/')[4].split('_')[:2]
+ size = format[0]
+ bitrate = format[1]
+ format = "-".join( format )
+ title = u'%s-%s-%s' % (video_title, size, bitrate)
+
+ formats.append({
+ 'id': video_id,
+ 'url': video_url,
+ 'uploader': video_uploader,
+ 'upload_date': upload_date,
+ 'title': title,
+ 'ext': extension,
+ 'format': format,
+ 'thumbnail': None,
+ 'description': None,
+ 'player_url': None
+ })
+
+ if self._downloader.params.get('listformats', None):
+ self._print_formats(formats)
+ return
+
+ req_format = self._downloader.params.get('format', None)
+ self.to_screen(u'Format: %s' % req_format)
+
+ if req_format is None or req_format == 'best':
+ return [formats[0]]
+ elif req_format == 'worst':
+ return [formats[-1]]
+ elif req_format in ('-1', 'all'):
+ return formats
+ else:
+ format = self._specific( req_format, formats )
+ if result is None:
+ raise ExtractorError(u'Requested format not available')
+ return [format]
+
+
+
+class PornotubeIE(InfoExtractor):
+ """Information extractor for pornotube.com."""
+ _VALID_URL = r'^(?:https?://)?(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ raise ExtractorError(u'Invalid URL: %s' % url)
+
+ video_id = mobj.group('videoid')
+ video_title = mobj.group('title')
+
+ # Get webpage content
+ webpage = self._download_webpage(url, video_id)
+
+ # Get the video URL
+ VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",'
+ result = re.search(VIDEO_URL_RE, webpage)
+ if result is None:
+ raise ExtractorError(u'Unable to extract video url')
+ video_url = compat_urllib_parse.unquote(result.group('url'))
+
+ #Get the uploaded date
+ VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by'
+ result = re.search(VIDEO_UPLOADED_RE, webpage)
+ if result is None:
+ raise ExtractorError(u'Unable to extract video title')
+ upload_date = unified_strdate(result.group('date'))
+
+ info = {'id': video_id,
+ 'url': video_url,
+ 'uploader': None,
+ 'upload_date': upload_date,
+ 'title': video_title,
+ 'ext': 'flv',
+ 'format': 'flv'}
+
+ return [info]
+
+class YouJizzIE(InfoExtractor):
+ """Information extractor for youjizz.com."""
+ _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+).html$'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ raise ExtractorError(u'Invalid URL: %s' % url)
+
+ video_id = mobj.group('videoid')
+
+ # Get webpage content
+ webpage = self._download_webpage(url, video_id)
+
+ # Get the video title
+ result = re.search(r'<title>(?P<title>.*)</title>', webpage)
+ if result is None:
+ raise ExtractorError(u'ERROR: unable to extract video title')
+ video_title = result.group('title').strip()
+
+ # Get the embed page
+ result = re.search(r'https?://www.youjizz.com/videos/embed/(?P<videoid>[0-9]+)', webpage)
+ if result is None:
+ raise ExtractorError(u'ERROR: unable to extract embed page')
+
+ embed_page_url = result.group(0).strip()
+ video_id = result.group('videoid')
+
+ webpage = self._download_webpage(embed_page_url, video_id)
+
+ # Get the video URL
+ result = re.search(r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);', webpage)
+ if result is None:
+ raise ExtractorError(u'ERROR: unable to extract video url')
+ video_url = result.group('source')
+
+ info = {'id': video_id,
+ 'url': video_url,
+ 'title': video_title,
+ 'ext': 'flv',
+ 'format': 'flv',
+ 'player_url': embed_page_url}
+
+ return [info]
+
+class EightTracksIE(InfoExtractor):
+ IE_NAME = '8tracks'
+ _VALID_URL = r'https?://8tracks.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ raise ExtractorError(u'Invalid URL: %s' % url)
+ playlist_id = mobj.group('id')
+
+ webpage = self._download_webpage(url, playlist_id)
+
+ m = re.search(r"PAGE.mix = (.*?);\n", webpage, flags=re.DOTALL)
+ if not m:
+ raise ExtractorError(u'Cannot find trax information')
+ json_like = m.group(1)
+ data = json.loads(json_like)
+
+ session = str(random.randint(0, 1000000000))
+ mix_id = data['id']
+ track_count = data['tracks_count']
+ first_url = 'http://8tracks.com/sets/%s/play?player=sm&mix_id=%s&format=jsonh' % (session, mix_id)
+ next_url = first_url
+ res = []
+ for i in itertools.count():
+ api_json = self._download_webpage(next_url, playlist_id,
+ note=u'Downloading song information %s/%s' % (str(i+1), track_count),
+ errnote=u'Failed to download song information')
+ api_data = json.loads(api_json)
+ track_data = api_data[u'set']['track']
+ info = {
+ 'id': track_data['id'],
+ 'url': track_data['track_file_stream_url'],
+ 'title': track_data['performer'] + u' - ' + track_data['name'],
+ 'raw_title': track_data['name'],
+ 'uploader_id': data['user']['login'],
+ 'ext': 'm4a',
+ }
+ res.append(info)
+ if api_data['set']['at_last_track']:
+ break
+ next_url = 'http://8tracks.com/sets/%s/next?player=sm&mix_id=%s&format=jsonh&track_id=%s' % (session, mix_id, track_data['id'])
+ return res
+
+class KeekIE(InfoExtractor):
+ _VALID_URL = r'http://(?:www\.)?keek\.com/(?:!|\w+/keeks/)(?P<videoID>\w+)'
+ IE_NAME = u'keek'
+
+ def _real_extract(self, url):
+ m = re.match(self._VALID_URL, url)
+ video_id = m.group('videoID')
+ video_url = u'http://cdn.keek.com/keek/video/%s' % video_id
+ thumbnail = u'http://cdn.keek.com/keek/thumbnail/%s/w100/h75' % video_id
+ webpage = self._download_webpage(url, video_id)
+ m = re.search(r'<meta property="og:title" content="(?P<title>.*?)"', webpage)
+ title = unescapeHTML(m.group('title'))
+ m = re.search(r'<div class="user-name-and-bio">[\S\s]+?<h2>(?P<uploader>.+?)</h2>', webpage)
+ uploader = clean_html(m.group('uploader'))
+ info = {
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': 'mp4',
+ 'title': title,
+ 'thumbnail': thumbnail,
+ 'uploader': uploader
+ }
+ return [info]
+
+class TEDIE(InfoExtractor):
+ _VALID_URL=r'''http://www\.ted\.com/
+ (
+ ((?P<type_playlist>playlists)/(?P<playlist_id>\d+)) # We have a playlist
+ |
+ ((?P<type_talk>talks)) # We have a simple talk
+ )
+ (/lang/(.*?))? # The url may contain the language
+ /(?P<name>\w+) # Here goes the name and then ".html"
+ '''
+
+ @classmethod
+ def suitable(cls, url):
+ """Receives a URL and returns True if suitable for this IE."""
+ return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
+
+ def _real_extract(self, url):
+ m=re.match(self._VALID_URL, url, re.VERBOSE)
+ if m.group('type_talk'):
+ return [self._talk_info(url)]
+ else :
+ playlist_id=m.group('playlist_id')
+ name=m.group('name')
+ self.to_screen(u'Getting info of playlist %s: "%s"' % (playlist_id,name))
+ return [self._playlist_videos_info(url,name,playlist_id)]
+
+ def _talk_video_link(self,mediaSlug):
+ '''Returns the video link for that mediaSlug'''
+ return 'http://download.ted.com/talks/%s.mp4' % mediaSlug
+
+ def _playlist_videos_info(self,url,name,playlist_id=0):
+ '''Returns the videos of the playlist'''
+ video_RE=r'''
+ <li\ id="talk_(\d+)"([.\s]*?)data-id="(?P<video_id>\d+)"
+ ([.\s]*?)data-playlist_item_id="(\d+)"
+ ([.\s]*?)data-mediaslug="(?P<mediaSlug>.+?)"
+ '''
+ video_name_RE=r'<p\ class="talk-title"><a href="(?P<talk_url>/talks/(.+).html)">(?P<fullname>.+?)</a></p>'
+ webpage=self._download_webpage(url, playlist_id, 'Downloading playlist webpage')
+ m_videos=re.finditer(video_RE,webpage,re.VERBOSE)
+ m_names=re.finditer(video_name_RE,webpage)
+
+ playlist_RE = r'div class="headline">(\s*?)<h1>(\s*?)<span>(?P<playlist_title>.*?)</span>'
+ m_playlist = re.search(playlist_RE, webpage)
+ playlist_title = m_playlist.group('playlist_title')
+
+ playlist_entries = []
+ for m_video, m_name in zip(m_videos,m_names):
+ video_id=m_video.group('video_id')
+ talk_url='http://www.ted.com%s' % m_name.group('talk_url')
+ playlist_entries.append(self.url_result(talk_url, 'TED'))
+ return self.playlist_result(playlist_entries, playlist_id = playlist_id, playlist_title = playlist_title)
+
+ def _talk_info(self, url, video_id=0):
+ """Return the video for the talk in the url"""
+ m=re.match(self._VALID_URL, url,re.VERBOSE)
+ videoName=m.group('name')
+ webpage=self._download_webpage(url, video_id, 'Downloading \"%s\" page' % videoName)
+ # If the url includes the language we get the title translated
+ title_RE=r'<span id="altHeadline" >(?P<title>.*)</span>'
+ title=re.search(title_RE, webpage).group('title')
+ info_RE=r'''<script\ type="text/javascript">var\ talkDetails\ =(.*?)
+ "id":(?P<videoID>[\d]+).*?
+ "mediaSlug":"(?P<mediaSlug>[\w\d]+?)"'''
+ thumb_RE=r'</span>[\s.]*</div>[\s.]*<img src="(?P<thumbnail>.*?)"'
+ thumb_match=re.search(thumb_RE,webpage)
+ info_match=re.search(info_RE,webpage,re.VERBOSE)
+ video_id=info_match.group('videoID')
+ mediaSlug=info_match.group('mediaSlug')
+ video_url=self._talk_video_link(mediaSlug)
+ info = {
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': 'mp4',
+ 'title': title,
+ 'thumbnail': thumb_match.group('thumbnail')
+ }
+ return info
+
+class MySpassIE(InfoExtractor):
+ _VALID_URL = r'http://www.myspass.de/.*'
+
+ def _real_extract(self, url):
+ META_DATA_URL_TEMPLATE = 'http://www.myspass.de/myspass/includes/apps/video/getvideometadataxml.php?id=%s'
+
+ # video id is the last path element of the URL
+ # usually there is a trailing slash, so also try the second but last
+ url_path = compat_urllib_parse_urlparse(url).path
+ url_parent_path, video_id = os.path.split(url_path)
+ if not video_id:
+ _, video_id = os.path.split(url_parent_path)
+
+ # get metadata
+ metadata_url = META_DATA_URL_TEMPLATE % video_id
+ metadata_text = self._download_webpage(metadata_url, video_id)
+ metadata = xml.etree.ElementTree.fromstring(metadata_text.encode('utf-8'))
+
+ # extract values from metadata
+ url_flv_el = metadata.find('url_flv')
+ if url_flv_el is None:
+ raise ExtractorError(u'Unable to extract download url')
+ video_url = url_flv_el.text
+ extension = os.path.splitext(video_url)[1][1:]
+ title_el = metadata.find('title')
+ if title_el is None:
+ raise ExtractorError(u'Unable to extract title')
+ title = title_el.text
+ format_id_el = metadata.find('format_id')
+ if format_id_el is None:
+ format = ext
+ else:
+ format = format_id_el.text
+ description_el = metadata.find('description')
+ if description_el is not None:
+ description = description_el.text
+ else:
+ description = None
+ imagePreview_el = metadata.find('imagePreview')
+ if imagePreview_el is not None:
+ thumbnail = imagePreview_el.text
+ else:
+ thumbnail = None
+ info = {
+ 'id': video_id,
+ 'url': video_url,
+ 'title': title,
+ 'ext': extension,
+ 'format': format,
+ 'thumbnail': thumbnail,
+ 'description': description
+ }
+ return [info]
+
+class SpiegelIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$'
+
+ def _real_extract(self, url):
+ m = re.match(self._VALID_URL, url)
+ video_id = m.group('videoID')
+
+ webpage = self._download_webpage(url, video_id)
+ m = re.search(r'<div class="spVideoTitle">(.*?)</div>', webpage)
+ if not m:
+ raise ExtractorError(u'Cannot find title')
+ video_title = unescapeHTML(m.group(1))
+
+ xml_url = u'http://video2.spiegel.de/flash/' + video_id + u'.xml'
+ xml_code = self._download_webpage(xml_url, video_id,
+ note=u'Downloading XML', errnote=u'Failed to download XML')
+
+ idoc = xml.etree.ElementTree.fromstring(xml_code)
+ last_type = idoc[-1]
+ filename = last_type.findall('./filename')[0].text
+ duration = float(last_type.findall('./duration')[0].text)
+
+ video_url = 'http://video2.spiegel.de/flash/' + filename
+ video_ext = filename.rpartition('.')[2]
+ info = {
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': video_ext,
+ 'title': video_title,
+ 'duration': duration,
+ }
+ return [info]
+
+class LiveLeakIE(InfoExtractor):
+
+ _VALID_URL = r'^(?:http?://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)'
+ IE_NAME = u'liveleak'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ raise ExtractorError(u'Invalid URL: %s' % url)
+
+ video_id = mobj.group('video_id')
+
+ webpage = self._download_webpage(url, video_id)
+
+ m = re.search(r'file: "(.*?)",', webpage)
+ if not m:
+ raise ExtractorError(u'Unable to find video url')
+ video_url = m.group(1)
+
+ m = re.search(r'<meta property="og:title" content="(?P<title>.*?)"', webpage)
+ if not m:
+ raise ExtractorError(u'Cannot find video title')
+ title = unescapeHTML(m.group('title')).replace('LiveLeak.com -', '').strip()
+
+ m = re.search(r'<meta property="og:description" content="(?P<desc>.*?)"', webpage)
+ if m:
+ desc = unescapeHTML(m.group('desc'))
+ else:
+ desc = None
+
+ m = re.search(r'By:.*?(\w+)</a>', webpage)
+ if m:
+ uploader = clean_html(m.group(1))
+ else:
+ uploader = None
+
+ info = {
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': 'mp4',
+ 'title': title,
+ 'description': desc,
+ 'uploader': uploader
+ }
+
+ return [info]
+
+class ARDIE(InfoExtractor):
+ _VALID_URL = r'^(?:https?://)?(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[^/\?]+)(?:\?.*)?'
+ _TITLE = r'<h1(?: class="boxTopHeadline")?>(?P<title>.*)</h1>'
+ _MEDIA_STREAM = r'mediaCollection\.addMediaStream\((?P<media_type>\d+), (?P<quality>\d+), "(?P<rtmp_url>[^"]*)", "(?P<video_url>[^"]*)", "[^"]*"\)'
+
+ def _real_extract(self, url):
+ # determine video id from url
+ m = re.match(self._VALID_URL, url)
+
+ numid = re.search(r'documentId=([0-9]+)', url)
+ if numid:
+ video_id = numid.group(1)
+ else:
+ video_id = m.group('video_id')
+
+ # determine title and media streams from webpage
+ html = self._download_webpage(url, video_id)
+ title = re.search(self._TITLE, html).group('title')
+ streams = [m.groupdict() for m in re.finditer(self._MEDIA_STREAM, html)]
+ if not streams:
+ assert '"fsk"' in html
+ raise ExtractorError(u'This video is only available after 8:00 pm')
+
+ # choose default media type and highest quality for now
+ stream = max([s for s in streams if int(s["media_type"]) == 0],
+ key=lambda s: int(s["quality"]))
+
+ # there's two possibilities: RTMP stream or HTTP download
+ info = {'id': video_id, 'title': title, 'ext': 'mp4'}
+ if stream['rtmp_url']:
+ self.to_screen(u'RTMP download detected')
+ assert stream['video_url'].startswith('mp4:')
+ info["url"] = stream["rtmp_url"]
+ info["play_path"] = stream['video_url']
+ else:
+ assert stream["video_url"].endswith('.mp4')
+ info["url"] = stream["video_url"]
+ return [info]
+
+class TumblrIE(InfoExtractor):
+ _VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/((post)|(video))/(?P<id>\d*)/(.*?)'
+
+ def _real_extract(self, url):
+ m_url = re.match(self._VALID_URL, url)
+ video_id = m_url.group('id')
+ blog = m_url.group('blog_name')
+
+ url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id)
+ webpage = self._download_webpage(url, video_id)
+
+ re_video = r'src=\\x22(?P<video_url>http://%s\.tumblr\.com/video_file/%s/(.*?))\\x22 type=\\x22video/(?P<ext>.*?)\\x22' % (blog, video_id)
+ video = re.search(re_video, webpage)
+ if video is None:
+ self.to_screen("No video founded")
+ return []
+ video_url = video.group('video_url')
+ ext = video.group('ext')
+
+ re_thumb = r'posters(.*?)\[\\x22(?P<thumb>.*?)\\x22' # We pick the first poster
+ thumb = re.search(re_thumb, webpage).group('thumb').replace('\\', '')
+
+ # The only place where you can get a title, it's not complete,
+ # but searching in other places doesn't work for all videos
+ re_title = r'<title>(?P<title>.*?)</title>'
+ title = unescapeHTML(re.search(re_title, webpage, re.DOTALL).group('title'))
+
+ return [{'id': video_id,
+ 'url': video_url,
+ 'title': title,
+ 'thumbnail': thumb,
+ 'ext': ext
+ }]
+
+class BandcampIE(InfoExtractor):
+ _VALID_URL = r'http://.*?\.bandcamp\.com/track/(?P<title>.*)'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ title = mobj.group('title')
+ webpage = self._download_webpage(url, title)
+ # We get the link to the free download page
+ m_download = re.search(r'freeDownloadPage: "(.*?)"', webpage)
+ if m_download is None:
+ raise ExtractorError(u'No free songs founded')
+
+ download_link = m_download.group(1)
+ id = re.search(r'var TralbumData = {(.*?)id: (?P<id>\d*?)$',
+ webpage, re.MULTILINE|re.DOTALL).group('id')
+
+ download_webpage = self._download_webpage(download_link, id,
+ 'Downloading free downloads page')
+ # We get the dictionary of the track from some javascrip code
+ info = re.search(r'items: (.*?),$',
+ download_webpage, re.MULTILINE).group(1)
+ info = json.loads(info)[0]
+ # We pick mp3-320 for now, until format selection can be easily implemented.
+ mp3_info = info[u'downloads'][u'mp3-320']
+ # If we try to use this url it says the link has expired
+ initial_url = mp3_info[u'url']
+ re_url = r'(?P<server>http://(.*?)\.bandcamp\.com)/download/track\?enc=mp3-320&fsig=(?P<fsig>.*?)&id=(?P<id>.*?)&ts=(?P<ts>.*)$'
+ m_url = re.match(re_url, initial_url)
+ #We build the url we will use to get the final track url
+ # This url is build in Bandcamp in the script download_bunde_*.js
+ request_url = '%s/statdownload/track?enc=mp3-320&fsig=%s&id=%s&ts=%s&.rand=665028774616&.vrs=1' % (m_url.group('server'), m_url.group('fsig'), id, m_url.group('ts'))
+ final_url_webpage = self._download_webpage(request_url, id, 'Requesting download url')
+ # If we could correctly generate the .rand field the url would be
+ #in the "download_url" key
+ final_url = re.search(r'"retry_url":"(.*?)"', final_url_webpage).group(1)
+
+ track_info = {'id':id,
+ 'title' : info[u'title'],
+ 'ext' : 'mp3',
+ 'url' : final_url,
+ 'thumbnail' : info[u'thumb_url'],
+ 'uploader' : info[u'artist']
+ }
+
+ return [track_info]
+
+class RedTubeIE(InfoExtractor):
+ """Information Extractor for redtube"""
+ _VALID_URL = r'(?:http://)?(?:www\.)?redtube\.com/(?P<id>[0-9]+)'
+
+ def _real_extract(self,url):
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ raise ExtractorError(u'Invalid URL: %s' % url)
+
+ video_id = mobj.group('id')
+ video_extension = 'mp4'
+ webpage = self._download_webpage(url, video_id)
+ self.report_extraction(video_id)
+ mobj = re.search(r'<source src="'+'(.+)'+'" type="video/mp4">',webpage)
+
+ if mobj is None:
+ raise ExtractorError(u'Unable to extract media URL')
+
+ video_url = mobj.group(1)
+ mobj = re.search('<h1 class="videoTitle slidePanelMovable">(.+)</h1>',webpage)
+ if mobj is None:
+ raise ExtractorError(u'Unable to extract title')
+ video_title = mobj.group(1)
+
+ return [{
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': video_extension,
+ 'title': video_title,
+ }]
+
+class InaIE(InfoExtractor):
+ """Information Extractor for Ina.fr"""
+ _VALID_URL = r'(?:http://)?(?:www.)?ina\.fr/video/(?P<id>I[0-9]+)/.*'
+
+ def _real_extract(self,url):
+ mobj = re.match(self._VALID_URL, url)
+
+ video_id = mobj.group('id')
+ mrss_url='http://player.ina.fr/notices/%s.mrss' % video_id
+ video_extension = 'mp4'
+ webpage = self._download_webpage(mrss_url, video_id)
+
+ mobj = re.search(r'<media:player url="(?P<mp4url>http://mp4.ina.fr/[^"]+\.mp4)', webpage)
+ if mobj is None:
+ raise ExtractorError(u'Unable to extract media URL')
+ video_url = mobj.group(1)
+
+ mobj = re.search(r'<title><!\[CDATA\[(?P<titre>.*?)]]></title>', webpage)
+ if mobj is None:
+ raise ExtractorError(u'Unable to extract title')
+ video_title = mobj.group(1)
+
+ return [{
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': video_extension,
+ 'title': video_title,
+ }]
+
+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.
+ """
+ return [
+ YoutubePlaylistIE(),
+ YoutubeChannelIE(),
+ YoutubeUserIE(),
+ YoutubeSearchIE(),
+ YoutubeIE(),
+ MetacafeIE(),
+ DailymotionIE(),
+ GoogleSearchIE(),
+ PhotobucketIE(),
+ YahooIE(),
+ YahooSearchIE(),
+ DepositFilesIE(),
+ FacebookIE(),
+ BlipTVUserIE(),
+ BlipTVIE(),
+ VimeoIE(),
+ MyVideoIE(),
+ ComedyCentralIE(),
+ EscapistIE(),
+ CollegeHumorIE(),
+ XVideosIE(),
+ SoundcloudSetIE(),
+ SoundcloudIE(),
+ InfoQIE(),
+ MixcloudIE(),
+ StanfordOpenClassroomIE(),
+ MTVIE(),
+ YoukuIE(),
+ XNXXIE(),
+ YouJizzIE(),
+ PornotubeIE(),
+ YouPornIE(),
+ GooglePlusIE(),
+ ArteTvIE(),
+ NBAIE(),
+ WorldStarHipHopIE(),
+ JustinTVIE(),
+ FunnyOrDieIE(),
+ SteamIE(),
+ UstreamIE(),
+ RBMARadioIE(),
+ EightTracksIE(),
+ KeekIE(),
+ TEDIE(),
+ MySpassIE(),
+ SpiegelIE(),
+ LiveLeakIE(),
+ ARDIE(),
+ TumblrIE(),
+ BandcampIE(),
+ RedTubeIE(),
+ InaIE(),
+ GenericIE()
+ ]
+
+def get_info_extractor(ie_name):
+ """Returns the info extractor class with the given ie_name"""
+ return globals()[ie_name+'IE']
Rapsys Git / youtubedl / commitdiff