mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-15 21:03:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

[canalc2] fix info extraction

Browse source
This commit is contained in:
remitamine 2015-09-21 15:52:36 +01:00 committed by Sergey M․
parent dd67702a3e
commit b0f001a6cb
1 changed files with 18 additions and 12 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

30
youtube_dl/extractor/canalc2.py
View file

@ -8,34 +8,40 @@
class Canalc2IE(InfoExtractor): class Canalc2IE(InfoExtractor):
IE_NAME = 'canalc2.tv' IE_NAME = 'canalc2.tv'
_VALID_URL = r'http://.*?\.canalc2\.tv/video\.asp\?.*?idVideo=(?P<id>\d+)' _VALID_URL = r'https?://(www\.)?canalc2\.tv/video/(?P<id>\d+)'
_TEST = { _TEST = {
'url': 'http://www.canalc2.tv/video.asp?idVideo=12163&voir=oui', 'url': 'http://www.canalc2.tv/video/12163',
'md5': '060158428b650f896c542dfbb3d6487f', 'md5': '060158428b650f896c542dfbb3d6487f',
'info_dict': { 'info_dict': {
'id': '12163', 'id': '12163',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Terrasses du Numérique' 'title': 'Terrasses du Numérique'
},
'params': {
'skip_download': True, # Requires rtmpdump
} }
} }
def _real_extract(self, url): def _real_extract(self, url):
video_id = re.match(self._VALID_URL, url).group('id') video_id = self._match_id(url)
# We need to set the voir field for getting the file name
url = 'http://www.canalc2.tv/video.asp?idVideo=%s&voir=oui' % video_id
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
file_name = self._search_regex( video_url = self._search_regex(
r"so\.addVariable\('file','(.*?)'\);", r'jwplayer\("Player"\).setup\({[^}]*file: "([^"]+)"',
webpage, 'file name') webpage, 'video_url')
video_url = 'http://vod-flash.u-strasbg.fr:8080/' + file_name formats = [{'url': video_url}]
if video_url.startswith('rtmp://'):
rtmp = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>.+))/(?P<play_path>mp4:.+)$', video_url)
formats[0].update({
'app': rtmp.group('app'),
'play_path': rtmp.group('play_path'),
})
title = self._html_search_regex( title = self._html_search_regex(
r'class="evenement8">(.*?)</a>', webpage, 'title') r'(?s)class="[^"]*col_description[^"]*">.*?<h3>(.*?)</h3>', webpage, 'title')
return { return {
'id': video_id, 'id': video_id,
'ext': 'mp4', 'formats': formats,
'url': video_url,
'title': title, 'title': title,
} }