MarcoBuster/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-24 21:56:53 +01:00
Code Issues Projects Releases Wiki Activity

[rts] Add support for articles with videos on rhs (Closes #6332)

Browse Source
This commit is contained in:
Sergey M․ 2015-07-23 22:50:59 +06:00
parent d3f007af18
commit ba911137fa
1 changed files with 29 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
youtube_dl/extractor/rts.py
View File

@ -19,7 +19,16 @@
class RTSIE(InfoExtractor): class RTSIE(InfoExtractor):
IE_DESC = 'RTS.ch' 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 = [ _TESTS = [
{ {
@ -122,6 +131,15 @@ class RTSIE(InfoExtractor):
'view_count': int, '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', '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, 'only_matching': True,
@ -130,7 +148,7 @@ class RTSIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
m = re.match(self._VALID_URL, 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') display_id = m.group('display_id') or m.group('display_id_new')
def download_json(internal_id): 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 # video_id extracted out of URL is not always a real id
if 'video' not in all_info and 'audio' not in all_info: if 'video' not in all_info and 'audio' not in all_info:
page = self._download_webpage(url, display_id) 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( internal_id = self._html_search_regex(
r'<(?:video|audio) data-id="([0-9]+)"', page, r'<(?:video|audio) data-id="([0-9]+)"', page,
'internal video id') 'internal video id')