.*)' 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 found') 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) video_url = self._html_search_regex(r'<source src="(.+?)" type="video/mp4">', webpage, u'video URL') video_title = self._html_search_regex('<h1 class="videoTitle slidePanelMovable">(.+?)</h1>', webpage, u'title') 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) self.report_extraction(video_id) video_url = self._html_search_regex(r'<media:player url="(?P<mp4url>http://mp4.ina.fr/[^"]+\.mp4)', webpage, u'video URL') video_title = self._search_regex(r'<title><!\[CDATA\[(?P<titre>.*?)]]>

(.*?)', data, u'video URL') return [{ 'id': video_id, 'url': video_url, 'ext': 'mp4', 'title': video_title, 'thumbnail': thumbnail, 'description': video_description, }] class XHamsterIE(InfoExtractor): """Information Extractor for xHamster""" _VALID_URL = r'(?:http://)?(?:www.)?xhamster\.com/movies/(?P[0-9]+)/.*\.html' def _real_extract(self,url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') mrss_url = 'http://xhamster.com/movies/%s/.html' % video_id webpage = self._download_webpage(mrss_url, video_id) mobj = re.search(r'\'srv\': \'(?P[^\']*)\',\s*\'file\': \'(?P[^\']+)\',', webpage) if mobj is None: raise ExtractorError(u'Unable to extract media URL') if len(mobj.group('server')) == 0: video_url = compat_urllib_parse.unquote(mobj.group('file')) else: video_url = mobj.group('server')+'/key='+mobj.group('file') video_extension = video_url.split('.')[-1] video_title = self._html_search_regex(r'(?P<title>.+?) - xHamster\.com', webpage, u'title') # Can't see the description anywhere in the UI # video_description = self._html_search_regex(r'Description: (?P[^<]+)', # webpage, u'description', fatal=False) # if video_description: video_description = unescapeHTML(video_description) mobj = re.search(r'hint=\'(?P[0-9]{4})-(?P[0-9]{2})-(?P[0-9]{2}) [0-9]{2}:[0-9]{2}:[0-9]{2} [A-Z]{3,4}\'', webpage) if mobj: video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d') else: video_upload_date = None self._downloader.report_warning(u'Unable to extract upload date') video_uploader_id = self._html_search_regex(r']+>(?P[^<]+)', webpage, u'uploader id', default=u'anonymous') video_thumbnail = self._search_regex(r'\'image\':\'(?P[^\']+)\'', webpage, u'thumbnail', fatal=False) return [{ 'id': video_id, 'url': video_url, 'ext': video_extension, 'title': video_title, # 'description': video_description, 'upload_date': video_upload_date, 'uploader_id': video_uploader_id, 'thumbnail': video_thumbnail }] class HypemIE(InfoExtractor): """Information Extractor for hypem""" _VALID_URL = r'(?:http://)?(?:www\.)?hypem\.com/track/([^/]+)/([^/]+)' def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) if mobj is None: raise ExtractorError(u'Invalid URL: %s' % url) track_id = mobj.group(1) data = { 'ax': 1, 'ts': time.time() } data_encoded = compat_urllib_parse.urlencode(data) complete_url = url + "?" + data_encoded request = compat_urllib_request.Request(complete_url) response, urlh = self._download_webpage_handle(request, track_id, u'Downloading webpage with the url') cookie = urlh.headers.get('Set-Cookie', '') self.report_extraction(track_id) html_tracks = self._html_search_regex(r'', response, u'tracks', flags=re.MULTILINE|re.DOTALL).strip() try: track_list = json.loads(html_tracks) track = track_list[u'tracks'][0] except ValueError: raise ExtractorError(u'Hypemachine contained invalid JSON.') key = track[u"key"] track_id = track[u"id"] artist = track[u"artist"] title = track[u"song"] serve_url = "http://hypem.com/serve/source/%s/%s" % (compat_str(track_id), compat_str(key)) request = compat_urllib_request.Request(serve_url, "" , {'Content-Type': 'application/json'}) request.add_header('cookie', cookie) song_data_json = self._download_webpage(request, track_id, u'Downloading metadata') try: song_data = json.loads(song_data_json) except ValueError: raise ExtractorError(u'Hypemachine contained invalid JSON.') final_url = song_data[u"url"] return [{ 'id': track_id, 'url': final_url, 'ext': "mp3", 'title': title, 'artist': artist, }] class Vbox7IE(InfoExtractor): """Information Extractor for Vbox7""" _VALID_URL = r'(?:http://)?(?:www\.)?vbox7\.com/play:([^/]+)' 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) redirect_page, urlh = self._download_webpage_handle(url, video_id) new_location = self._search_regex(r'window\.location = \'(.*)\';', redirect_page, u'redirect location') redirect_url = urlh.geturl() + new_location webpage = self._download_webpage(redirect_url, video_id, u'Downloading redirect page') title = self._html_search_regex(r'(.*)', webpage, u'title').split('/')[0].strip() ext = "flv" info_url = "http://vbox7.com/play/magare.do" data = compat_urllib_parse.urlencode({'as3':'1','vid':video_id}) info_request = compat_urllib_request.Request(info_url, data) info_request.add_header('Content-Type', 'application/x-www-form-urlencoded') info_response = self._download_webpage(info_request, video_id, u'Downloading info webpage') if info_response is None: raise ExtractorError(u'Unable to extract the media url') (final_url, thumbnail_url) = map(lambda x: x.split('=')[1], info_response.split('&')) return [{ 'id': video_id, 'url': final_url, 'ext': ext, 'title': title, 'thumbnail': thumbnail_url, }] 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(), BlipTVIE(), BlipTVUserIE(), 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(), ZDFIE(), TumblrIE(), BandcampIE(), RedTubeIE(), InaIE(), HowcastIE(), VineIE(), FlickrIE(), TeamcocoIE(), XHamsterIE(), HypemIE(), Vbox7IE(), GametrailersIE(), StatigramIE(), GenericIE() ] def get_info_extractor(ie_name): """Returns the info extractor class with the given ie_name""" return globals()[ie_name+'IE']