X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2FInfoExtractors.py;h=24a77a1abba247c49234189d794d7da6cc83486f;hb=3054ff0cbebc7969d918f0deee76cd37ea6f5b40;hp=4ca744daface942191f26a3dff41123471842671;hpb=f2cd958c0a09bca580a955c60c19e177f6ff45b8;p=youtube-dl diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 4ca744daf..24a77a1ab 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -376,6 +376,34 @@ class YoutubeIE(InfoExtractor): return (u'Did not fetch video subtitles', None, None) return (None, sub_lang, sub) + def _request_automatic_caption(self, video_id, webpage): + """We need the webpage for getting the captions url, pass it as an + argument to speed up the process.""" + sub_lang = self._downloader.params.get('subtitleslang') + sub_format = self._downloader.params.get('subtitlesformat') + self.to_screen(u'%s: Looking for automatic captions' % video_id) + mobj = re.search(r';ytplayer.config = ({.*?});', webpage) + err_msg = u'Couldn\'t find automatic captions for "%s"' % sub_lang + if mobj is None: + return [(err_msg, None, None)] + player_config = json.loads(mobj.group(1)) + try: + args = player_config[u'args'] + caption_url = args[u'ttsurl'] + timestamp = args[u'timestamp'] + params = compat_urllib_parse.urlencode({ + 'lang': 'en', + 'tlang': sub_lang, + 'fmt': sub_format, + 'ts': timestamp, + 'kind': 'asr', + }) + subtitles_url = caption_url + '&' + params + sub = self._download_webpage(subtitles_url, video_id, u'Downloading automatic captions') + return [(None, sub_lang, sub)] + except KeyError: + return [(err_msg, None, None)] + def _extract_subtitle(self, video_id): """ Return a list with a tuple: @@ -623,7 +651,14 @@ class YoutubeIE(InfoExtractor): if video_subtitles: (sub_error, sub_lang, sub) = video_subtitles[0] if sub_error: - self._downloader.report_error(sub_error) + # We try with the automatic captions + video_subtitles = self._request_automatic_caption(video_id, video_webpage) + (sub_error_auto, sub_lang, sub) = video_subtitles[0] + if sub is not None: + pass + else: + # We report the original error + self._downloader.report_error(sub_error) if self._downloader.params.get('allsubtitles', False): video_subtitles = self._extract_all_subtitles(video_id) @@ -1025,7 +1060,7 @@ class VimeoIE(InfoExtractor): """Information extractor for vimeo.com.""" # _VALID_URL matches Vimeo URLs - _VALID_URL = r'(?Phttps?://)?(?:(?:www|player)\.)?vimeo\.com/(?:(?:groups|album)/[^/]+/)?(?Pplay_redirect_hls\?clip_id=)?(?:videos?/)?(?P[0-9]+)' + _VALID_URL = r'(?Phttps?://)?(?:(?:www|player)\.)?vimeo(?Ppro)?\.com/(?:(?:(?:groups|album)/[^/]+)|(?:.*?)/)?(?Pplay_redirect_hls\?clip_id=)?(?:videos?/)?(?P[0-9]+)' IE_NAME = u'vimeo' def _real_extract(self, url, new_video=True): @@ -1037,7 +1072,7 @@ class VimeoIE(InfoExtractor): video_id = mobj.group('id') if not mobj.group('proto'): url = 'https://' + url - if mobj.group('direct_link'): + if mobj.group('direct_link') or mobj.group('pro'): url = 'https://vimeo.com/' + video_id # Retrieve video webpage to extract further information @@ -1064,7 +1099,7 @@ class VimeoIE(InfoExtractor): # Extract uploader and uploader_id video_uploader = config["video"]["owner"]["name"] - video_uploader_id = config["video"]["owner"]["url"].split('/')[-1] + video_uploader_id = config["video"]["owner"]["url"].split('/')[-1] if config["video"]["owner"]["url"] else None # Extract video thumbnail video_thumbnail = config["video"]["thumbnail"] @@ -1884,7 +1919,7 @@ class FacebookIE(InfoExtractor): class BlipTVIE(InfoExtractor): """Information extractor for blip.tv""" - _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv(/.+)$' + _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv/((.+/)|(play/)|(api\.swf#))(.+)$' _URL_EXT = r'^.*\.([a-z0-9]+)$' IE_NAME = u'blip.tv' @@ -1897,6 +1932,10 @@ class BlipTVIE(InfoExtractor): if mobj is None: raise ExtractorError(u'Invalid URL: %s' % url) + # See https://github.com/rg3/youtube-dl/issues/857 + api_mobj = re.match(r'http://a\.blip\.tv/api\.swf#(?P[\d\w]+)', url) + if api_mobj is not None: + url = 'http://blip.tv/play/g_%s' % api_mobj.group('video_id') urlp = compat_urllib_parse_urlparse(url) if urlp.path.startswith('/play/'): request = compat_urllib_request.Request(url) @@ -3941,7 +3980,7 @@ class SpiegelIE(InfoExtractor): video_id = m.group('videoID') webpage = self._download_webpage(url, video_id) - m = re.search(r'
(.*?)
', webpage) + m = re.search(r'
(.*?)
', webpage) if not m: raise ExtractorError(u'Cannot find title') video_title = unescapeHTML(m.group(1)) @@ -4070,8 +4109,8 @@ class ZDFIE(InfoExtractor): if streams is None: raise ExtractorError(u'No media url found.') - # s['media_type'] == 'wstreaming' -> use 'Windows Media Player' und mms url - # s['media_type'] == 'hstreaming' -> use 'Quicktime' und rtsp url + # s['media_type'] == 'wstreaming' -> use 'Windows Media Player' and mms url + # s['media_type'] == 'hstreaming' -> use 'Quicktime' and rtsp url # choose first/default media type and highest quality for now for s in streams: #find 300 - dsl1000mbit if s['quality'] == '300' and s['media_type'] == 'wstreaming': @@ -4263,7 +4302,7 @@ class HowcastIE(InfoExtractor): self.report_extraction(video_id) - mobj = re.search(r'\'file\': "(http://mobile-media\.howcast\.com/\d+\.mp4)"', webpage) + mobj = re.search(r'\'?file\'?: "(http://mobile-media\.howcast\.com/[0-9]+\.mp4)"', webpage) if mobj is None: raise ExtractorError(u'Unable to extract video URL') video_url = mobj.group(1) @@ -4444,6 +4483,149 @@ class TeamcocoIE(InfoExtractor): 'thumbnail': thumbnail, 'description': 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] + + mobj = re.search(r'(?P<title>.+?) - xHamster\.com', webpage) + if mobj is None: + raise ExtractorError(u'Unable to extract title') + video_title = unescapeHTML(mobj.group('title')) + + mobj = re.search(r'Description: (?P[^<]+)', webpage) + if mobj is None: + video_description = u'' + else: + video_description = unescapeHTML(mobj.group('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 is None: + raise ExtractorError(u'Unable to extract upload date') + video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d') + + mobj = re.search(r']+>(?P[^>]+)', webpage) + if mobj is None: + video_uploader_id = u'anonymous' + else: + video_uploader_id = mobj.group('uploader_id') + + mobj = re.search(r'\'image\':\'(?P[^\']+)\'', webpage) + if mobj is None: + raise ExtractorError(u'Unable to extract thumbnail URL') + video_thumbnail = mobj.group('thumbnail') + + 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) + mobj = re.search(r'', response, flags=re.MULTILINE|re.DOTALL) + if mobj is None: + raise ExtractorError(u'Unable to extrack tracks') + html_tracks = mobj.group(1).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) + redirect_url = urlh.geturl() + re.search(r'window\.location = \'(.*)\';', redirect_page).group(1) + webpage = self._download_webpage(redirect_url, video_id, u'Downloading redirect page') + + title = re.search(r'(.*)', webpage) + title = (title.group(1)).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. @@ -4463,8 +4645,8 @@ def gen_extractors(): YahooSearchIE(), DepositFilesIE(), FacebookIE(), - BlipTVUserIE(), BlipTVIE(), + BlipTVUserIE(), VimeoIE(), MyVideoIE(), ComedyCentralIE(), @@ -4507,6 +4689,9 @@ def gen_extractors(): VineIE(), FlickrIE(), TeamcocoIE(), + XHamsterIE(), + HypemIE(), + Vbox7IE(), GenericIE() ]