diff options
Diffstat (limited to 'youtube_dl/InfoExtractors.py')
| -rwxr-xr-x | youtube_dl/InfoExtractors.py | 66 |
1 files changed, 27 insertions, 39 deletions
diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 83be8313f..092bfef22 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -2333,7 +2333,6 @@ class ComedyCentralIE(InfoExtractor): (the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?)) |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*))))) $""" - IE_NAME = u'comedycentral' _available_formats = ['3500', '2200', '1700', '1200', '750', '400'] @@ -2361,16 +2360,12 @@ class ComedyCentralIE(InfoExtractor): 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_config_download(self, episode_id, media_id): + self._downloader.to_screen(u'[comedycentral] %s: Downloading configuration for %s' % (episode_id, media_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 _print_formats(self, formats): print('Available formats:') for x in formats: @@ -2409,6 +2404,7 @@ class ComedyCentralIE(InfoExtractor): try: htmlHandle = compat_urllib_request.urlopen(req) html = htmlHandle.read() + webpage = html.decode('utf-8') except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) return @@ -2423,29 +2419,20 @@ class ComedyCentralIE(InfoExtractor): return epTitle = mobj.group('episode') - mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', html) + mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage) if len(mMovieParams) == 0: # The Colbert Report embeds the information in a without # a URL prefix; so extract the alternate reference # and then add the URL prefix manually. - altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', html) + altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', webpage) if len(altMovieParams) == 0: self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url) return else: mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])] - playerUrl_raw = mMovieParams[0][0] - self.report_player_url(epTitle) - try: - urlHandle = compat_urllib_request.urlopen(playerUrl_raw) - playerUrl = urlHandle.geturl() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self._downloader.trouble(u'ERROR: unable to find out player URL: ' + compat_str(err)) - return - uri = mMovieParams[0][1] indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + compat_urllib_parse.urlencode({'uri': uri}) self.report_index_download(epTitle) @@ -2459,7 +2446,7 @@ class ComedyCentralIE(InfoExtractor): idoc = xml.etree.ElementTree.fromstring(indexXml) itemEls = idoc.findall('.//item') - for itemEl in itemEls: + for partNum,itemEl in enumerate(itemEls): mediaId = itemEl.findall('./guid')[0].text shortMediaId = mediaId.split(':')[-1] showId = mediaId.split(':')[-2].replace('.com', '') @@ -2469,7 +2456,7 @@ class ComedyCentralIE(InfoExtractor): configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' + compat_urllib_parse.urlencode({'uri': mediaId})) configReq = compat_urllib_request.Request(configUrl) - self.report_config_download(epTitle) + self.report_config_download(epTitle, shortMediaId) try: configXml = compat_urllib_request.urlopen(configReq).read() except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: @@ -2491,7 +2478,7 @@ class ComedyCentralIE(InfoExtractor): return # For now, just pick the highest bitrate - format,video_url = turls[-1] + format,rtmp_video_url = turls[-1] # Get the format arg from the arg stream req_format = self._downloader.params.get('format', None) @@ -2499,18 +2486,16 @@ class ComedyCentralIE(InfoExtractor): # Select format if we can find one for f,v in turls: if f == req_format: - format, video_url = f, v + format, rtmp_video_url = f, v break - # Patch to download from alternative CDN, which does not - # break on current RTMPDump builds - broken_cdn = "rtmpe://viacomccstrmfs.fplive.net/viacomccstrm/gsp.comedystor/" - better_cdn = "rtmpe://cp10740.edgefcs.net/ondemand/mtvnorigin/gsp.comedystor/" - - if video_url.startswith(broken_cdn): - video_url = video_url.replace(broken_cdn, better_cdn) + m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp.comedystor/.*)$', rtmp_video_url) + if not m: + raise ExtractorError(u'Cannot transform RTMP url') + base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/' + video_url = base + m.group('finalid') - effTitle = showId + u'-' + epTitle + effTitle = showId + u'-' + epTitle + u' part ' + compat_str(partNum+1) info = { 'id': shortMediaId, 'url': video_url, @@ -2521,9 +2506,7 @@ class ComedyCentralIE(InfoExtractor): 'format': format, 'thumbnail': None, 'description': officialTitle, - 'player_url': None #playerUrl } - results.append(info) return results @@ -2603,7 +2586,6 @@ class EscapistIE(InfoExtractor): return [info] - class CollegeHumorIE(InfoExtractor): """Information extractor for collegehumor.com""" @@ -3542,17 +3524,23 @@ class JustinTVIE(InfoExtractor): return response = json.loads(webpage) + if type(response) != list: + error_text = response.get('error', 'unknown error') + self._downloader.trouble(u'ERROR: Justin.tv API: %s' % error_text) + return 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['created_on'][:10]) + video_date = re.sub('-', '', clip['start_time'][:10]) + video_uploader_id = clip.get('user_id', clip.get('channel_id')) info.append({ 'id': clip['id'], 'url': video_url, 'title': clip['title'], - 'uploader': clip.get('user_id', clip.get('channel_id')), + 'uploader': clip.get('channel_name', video_uploader_id), + 'uploader_id': video_uploader_id, 'upload_date': video_date, 'ext': video_extension, }) @@ -3571,7 +3559,7 @@ class JustinTVIE(InfoExtractor): paged = True api += '/channel/archives/%s.json' else: - api += '/clip/show/%s.json' + api += '/broadcast/by_archive/%s.json' api = api % (video_id,) self.report_extraction(video_id) @@ -3711,11 +3699,11 @@ class SteamIE(InfoExtractor): } videos.append(info) return videos - + class UstreamIE(InfoExtractor): - _VALID_URL = r'http://www.ustream.tv/recorded/(?P<videoID>\d+)' + _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') |