youtube-dl

Another place where youtube-dl lives on
git clone git://git.oshgnacknak.de/youtube-dl.git
Log | Files | Refs | README | LICENSE

commit ddde91952f4eec796b14eb258c0cb33dda3935bc
parent 63c583eb2c9a906ba1075da289afdde29b385fff
Author: Sergey M․ <dstftw@gmail.com>
Date:   Sun, 25 Sep 2016 05:36:18 +0700

[prosiebensat1] Fix playlist support (Closes #10745)

Diffstat:
Myoutube_dl/extractor/prosiebensat1.py | 39++++++++++++++++++++++++++-------------
1 file changed, 26 insertions(+), 13 deletions(-)

diff --git a/youtube_dl/extractor/prosiebensat1.py b/youtube_dl/extractor/prosiebensat1.py @@ -310,6 +310,10 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE): 'url': 'http://www.sat1gold.de/tv/edel-starck/video/11-staffel-1-episode-1-partner-wider-willen-ganze-folge', 'only_matching': True, }, + { + 'url': 'http://www.sat1gold.de/tv/edel-starck/playlist/die-gesamte-1-staffel', + 'only_matching': True, + }, ] _TOKEN = 'prosieben' @@ -381,19 +385,28 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE): def _extract_playlist(self, url, webpage): playlist_id = self._html_search_regex( self._PLAYLIST_ID_REGEXES, webpage, 'playlist id') - for regex in self._PLAYLIST_CLIP_REGEXES: - playlist_clips = re.findall(regex, webpage) - if playlist_clips: - title = self._html_search_regex( - self._TITLE_REGEXES, webpage, 'title') - description = self._html_search_regex( - self._DESCRIPTION_REGEXES, webpage, 'description', fatal=False) - entries = [ - self.url_result( - re.match('(.+?//.+?)/', url).group(1) + clip_path, - 'ProSiebenSat1') - for clip_path in playlist_clips] - return self.playlist_result(entries, playlist_id, title, description) + playlist = self._parse_json( + self._search_regex( + 'var\s+contentResources\s*=\s*(\[.+?\]);\s*</script', + webpage, 'playlist'), + playlist_id) + entries = [] + for item in playlist: + clip_id = item.get('id') or item.get('upc') + if not clip_id: + continue + info = self._extract_video_info(url, clip_id) + info.update({ + 'id': clip_id, + 'title': item.get('title') or item.get('teaser', {}).get('headline'), + 'description': item.get('teaser', {}).get('description'), + 'thumbnail': item.get('poster'), + 'duration': float_or_none(item.get('duration')), + 'series': item.get('tvShowTitle'), + 'uploader': item.get('broadcastPublisher'), + }) + entries.append(info) + return self.playlist_result(entries, playlist_id) def _real_extract(self, url): video_id = self._match_id(url)