+
+ presumptive_id = mobj.group('presumptive_id')
+ display_id = presumptive_id
+ if presumptive_id:
+ webpage = self._download_webpage(url, display_id)
+
+ upload_date = unified_strdate(self._search_regex(
+ r'<input type="hidden" id="air_date_[0-9]+" value="([^"]+)"',
+ webpage, 'upload date', default=None))
+
+ # tabbed frontline videos
+ tabbed_videos = re.findall(
+ r'<div[^>]+class="videotab[^"]*"[^>]+vid="(\d+)"', webpage)
+ if tabbed_videos:
+ return tabbed_videos, presumptive_id, upload_date
+
+ MEDIA_ID_REGEXES = [
+ r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'", # frontline video embed
+ r'class="coveplayerid">([^<]+)<', # coveplayer
+ r'<input type="hidden" id="pbs_video_id_[0-9]+" value="([0-9]+)"/>', # jwplayer
+ ]
+
+ media_id = self._search_regex(
+ MEDIA_ID_REGEXES, webpage, 'media ID', fatal=False, default=None)
+ if media_id:
+ return media_id, presumptive_id, upload_date
+
+ # Fronline video embedded via flp
+ video_id = self._search_regex(
+ r'videoid\s*:\s*"([\d+a-z]{7,})"', webpage, 'videoid', default=None)
+ if video_id:
+ # pkg_id calculation is reverse engineered from
+ # http://www.pbs.org/wgbh/pages/frontline/js/flp2012.js
+ prg_id = self._search_regex(
+ r'videoid\s*:\s*"([\d+a-z]{7,})"', webpage, 'videoid')[7:]
+ if 'q' in prg_id:
+ prg_id = prg_id.split('q')[1]
+ prg_id = int(prg_id, 16)
+ getdir = self._download_json(
+ 'http://www.pbs.org/wgbh/pages/frontline/.json/getdir/getdir%d.json' % prg_id,
+ presumptive_id, 'Downloading getdir JSON',
+ transform_source=strip_jsonp)
+ return getdir['mid'], presumptive_id, upload_date
+
+ for iframe in re.findall(r'(?s)<iframe(.+?)></iframe>', webpage):
+ url = self._search_regex(
+ r'src=(["\'])(?P<url>.+?partnerplayer.+?)\1', iframe,
+ 'player URL', default=None, group='url')
+ if url:
+ break
+
+ mobj = re.match(self._VALID_URL, url)
+
+ player_id = mobj.group('player_id')
+ if not display_id:
+ display_id = player_id
+ if player_id:
+ player_page = self._download_webpage(
+ url, display_id, note='Downloading player page',
+ errnote='Could not download player page')
+ video_id = self._search_regex(
+ r'<div\s+id="video_([0-9]+)"', player_page, 'video ID')
+ else:
+ video_id = mobj.group('id')
+ display_id = video_id
+
+ return video_id, display_id, None
+
+ def _real_extract(self, url):
+ video_id, display_id, upload_date = self._extract_webpage(url)
+
+ if isinstance(video_id, list):
+ entries = [self.url_result(
+ 'http://video.pbs.org/video/%s' % vid_id, 'PBS', vid_id)
+ for vid_id in video_id]
+ return self.playlist_result(entries, display_id)
+
+ info = self._download_json(
+ 'http://video.pbs.org/videoInfo/%s?format=json&type=partner' % video_id,
+ display_id)
+
+ formats = []
+ for encoding_name in ('recommended_encoding', 'alternate_encoding'):
+ redirect = info.get(encoding_name)
+ if not redirect:
+ continue
+ redirect_url = redirect.get('url')
+ if not redirect_url:
+ continue
+
+ redirect_info = self._download_json(
+ redirect_url + '?format=json', display_id,
+ 'Downloading %s video url info' % encoding_name)
+
+ if redirect_info['status'] == 'error':
+ raise ExtractorError(
+ '%s said: %s' % (
+ self.IE_NAME,
+ self._ERRORS.get(redirect_info['http_code'], redirect_info['message'])),
+ expected=True)
+
+ format_url = redirect_info.get('url')
+ if not format_url:
+ continue
+
+ if determine_ext(format_url) == 'm3u8':
+ formats.extend(self._extract_m3u8_formats(
+ format_url, display_id, 'mp4', preference=1, m3u8_id='hls'))
+ else:
+ formats.append({
+ 'url': format_url,
+ 'format_id': redirect.get('eeid'),
+ })
+ self._sort_formats(formats)
+
+ rating_str = info.get('rating')
+ if rating_str is not None:
+ rating_str = rating_str.rpartition('-')[2]
+ age_limit = US_RATINGS.get(rating_str)
+
+ subtitles = {}
+ closed_captions_url = info.get('closed_captions_url')
+ if closed_captions_url:
+ subtitles['en'] = [{
+ 'ext': 'ttml',
+ 'url': closed_captions_url,
+ }]
+
+ # info['title'] is often incomplete (e.g. 'Full Episode', 'Episode 5', etc)
+ # Try turning it to 'program - title' naming scheme if possible
+ alt_title = info.get('program', {}).get('title')
+ if alt_title:
+ info['title'] = alt_title + ' - ' + re.sub(r'^' + alt_title + '[\s\-:]+', '', info['title'])
+
+ return {
+ 'id': video_id,
+ 'display_id': display_id,
+ 'title': info['title'],
+ 'description': info['program'].get('description'),
+ 'thumbnail': info.get('image_url'),
+ 'duration': int_or_none(info.get('duration')),
+ 'age_limit': age_limit,
+ 'upload_date': upload_date,
+ 'formats': formats,
+ 'subtitles': subtitles,
+ }
Rapsys Git / youtubedl / blobdiff