Mirror
/
youtube-dl
mirror of https://github.com/ytdl-org/youtube-dl.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

[francetv] Add support for non-numeric video IDs (Fixes #2927)

pull/2934/head
Philipp Hagemeister 2014-05-16 15:51:01 +02:00
parent f07b74fc18
commit 5c30b26846
1 changed files with 17 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
youtube_dl/extractor/francetv.py
View File

@ -48,24 +48,36 @@ class PluzzIE(FranceTVBaseInfoExtractor):
class FranceTvInfoIE(FranceTVBaseInfoExtractor): class FranceTvInfoIE(FranceTVBaseInfoExtractor):
IE_NAME = 'francetvinfo.fr' IE_NAME = 'francetvinfo.fr'
_VALID_URL = r'https?://www\.francetvinfo\.fr/replay.*/(?P<title>.+)\.html' _VALID_URL = r'https?://www\.francetvinfo\.fr/.*/(?P<title>.+)\.html'
_TEST = { _TESTS = [{
'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html', 'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
'file': '84981923.mp4',
'info_dict': { 'info_dict': {
'id': '84981923',
'ext': 'mp4',
'title': 'Soir 3', 'title': 'Soir 3',
}, },
'params': { 'params': {
'skip_download': True, 'skip_download': True,
}, },
} }, {
'url': 'http://www.francetvinfo.fr/elections/europeennes/direct-europeennes-regardez-le-debat-entre-les-candidats-a-la-presidence-de-la-commission_600639.html',
'info_dict': {
'id': 'EV_20019',
'ext': 'mp4',
'title': 'Débat des candidats à la Commission européenne',
'description': 'Débat des candidats à la Commission européenne',
},
'params': {
'skip_download': 'HLS (reqires ffmpeg)'
}
}]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
page_title = mobj.group('title') page_title = mobj.group('title')
webpage = self._download_webpage(url, page_title) webpage = self._download_webpage(url, page_title)
video_id = self._search_regex(r'id-video=(\d+?)[@"]', webpage, 'video id') video_id = self._search_regex(r'id-video=((?:[^0-9]*?_)?[0-9]+)[@"]', webpage, 'video id')
return self._extract_video(video_id) return self._extract_video(video_id)