From ba911137fa53737b663cb2879d357bc8a35ab558 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 23 Jul 2015 22:50:59 +0600 Subject: [PATCH] [rts] Add support for articles with videos on rhs (Closes #6332) --- youtube_dl/extractor/rts.py | 31 +++++++++++++++++++++++++++++-- 1 file changed, 29 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/rts.py b/youtube_dl/extractor/rts.py index 9fbe239d8..12639f08b 100644 --- a/youtube_dl/extractor/rts.py +++ b/youtube_dl/extractor/rts.py @@ -19,7 +19,16 @@ class RTSIE(InfoExtractor): IE_DESC = 'RTS.ch' - _VALID_URL = r'https?://(?:www\.)?rts\.ch/(?:(?:[^/]+/){2,}(?P[0-9]+)-(?P.+?)\.html|play/tv/[^/]+/video/(?P.+?)\?id=(?P[0-9]+))' + _VALID_URL = r'''(?x) + (?: + rts:(?P\d+)| + https?:// + (?:www\.)?rts\.ch/ + (?: + (?:[^/]+/){2,}(?P[0-9]+)-(?P.+?)\.html| + play/tv/[^/]+/video/(?P.+?)\?id=(?P[0-9]+) + ) + )''' _TESTS = [ { @@ -122,6 +131,15 @@ class RTSIE(InfoExtractor): 'view_count': int, }, }, + { + # article with videos on rhs + 'url': 'http://www.rts.ch/sport/hockey/6693917-hockey-davos-decroche-son-31e-titre-de-champion-de-suisse.html', + 'info_dict': { + 'id': '6693917', + 'title': 'Hockey: Davos décroche son 31e titre de champion de Suisse', + }, + 'playlist_mincount': 5, + }, { 'url': 'http://www.rts.ch/play/tv/le-19h30/video/le-chantier-du-nouveau-parlement-vaudois-a-permis-une-trouvaille-historique?id=6348280', 'only_matching': True, @@ -130,7 +148,7 @@ class RTSIE(InfoExtractor): def _real_extract(self, url): m = re.match(self._VALID_URL, url) - video_id = m.group('id') or m.group('id_new') + video_id = m.group('rts_id') or m.group('id') or m.group('id_new') display_id = m.group('display_id') or m.group('display_id_new') def download_json(internal_id): @@ -143,6 +161,15 @@ def download_json(internal_id): # video_id extracted out of URL is not always a real id if 'video' not in all_info and 'audio' not in all_info: page = self._download_webpage(url, display_id) + + # article with videos on rhs + videos = re.findall( + r']+class="content-item"[^>]*>\s*]+data-video-urn="urn:rts:video:(\d+)"', + page) + if videos: + entries = [self.url_result('rts:%s' % video_urn, 'RTS') for video_urn in videos] + return self.playlist_result(entries, video_id, self._og_search_title(page)) + internal_id = self._html_search_regex( r'<(?:video|audio) data-id="([0-9]+)"', page, 'internal video id')