aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/rts.py
diff options
context:
space:
mode:
authorSergey M․ <dstftw@gmail.com>2015-07-23 22:50:59 +0600
committerSergey M․ <dstftw@gmail.com>2015-07-23 22:50:59 +0600
commitba911137fa53737b663cb2879d357bc8a35ab558 (patch)
treedd3756b6ab0c7fe8eb4708167d68991083ebfdff /youtube_dl/extractor/rts.py
parentd3f007af183a0f5ed278602128e6bba3cc1350b3 (diff)
[rts] Add support for articles with videos on rhs (Closes #6332)
Diffstat (limited to 'youtube_dl/extractor/rts.py')
-rw-r--r--youtube_dl/extractor/rts.py31
1 files 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 @@ from ..utils import (
class RTSIE(InfoExtractor):
IE_DESC = 'RTS.ch'
- _VALID_URL = r'https?://(?:www\.)?rts\.ch/(?:(?:[^/]+/){2,}(?P<id>[0-9]+)-(?P<display_id>.+?)\.html|play/tv/[^/]+/video/(?P<display_id_new>.+?)\?id=(?P<id_new>[0-9]+))'
+ _VALID_URL = r'''(?x)
+ (?:
+ rts:(?P<rts_id>\d+)|
+ https?://
+ (?:www\.)?rts\.ch/
+ (?:
+ (?:[^/]+/){2,}(?P<id>[0-9]+)-(?P<display_id>.+?)\.html|
+ play/tv/[^/]+/video/(?P<display_id_new>.+?)\?id=(?P<id_new>[0-9]+)
+ )
+ )'''
_TESTS = [
{
@@ -123,6 +132,15 @@ class RTSIE(InfoExtractor):
},
},
{
+ # 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 @@ class RTSIE(InfoExtractor):
# 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'<article[^>]+class="content-item"[^>]*>\s*<a[^>]+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')