xZero707/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-23 19:33:59 +01:00
Code Issues Packages Projects Releases Wiki Activity

[canalc2] Fix extraction (Closes #8191)

Browse Source
This commit is contained in:
Sergey M․ 2016-01-10 01:37:10 +06:00
parent 27783821af
commit 7a34302e95
1 changed files with 29 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
youtube_dl/extractor/canalc2.py
View File

@ -9,9 +9,9 @@
class Canalc2IE(InfoExtractor):
IE_NAME = 'canalc2.tv'
_VALID_URL = r'https?://(?:www\.)?canalc2\.tv/video/(?P<id>\d+)'
_VALID_URL = r'https?://(?:(?:www\.)?canalc2\.tv/video/|archives-canalc2\.u-strasbg\.fr/video\.asp\?.*\bidVideo=)(?P<id>\d+)'
_TEST = {
_TESTS = [{
'url': 'http://www.canalc2.tv/video/12163',
'md5': '060158428b650f896c542dfbb3d6487f',
'info_dict': {
@ -23,24 +23,36 @@ class Canalc2IE(InfoExtractor):
'params': {
'skip_download': True, # Requires rtmpdump
}
}
}, {
'url': 'http://archives-canalc2.u-strasbg.fr/video.asp?idVideo=11427&voir=oui',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_url = self._search_regex(
r'jwplayer\((["\'])Player\1\)\.setup\({[^}]*file\s*:\s*(["\'])(?P<file>.+?)\2',
webpage, 'video_url', group='file')
formats = [{'url': video_url}]
webpage = self._download_webpage(
'http://www.canalc2.tv/video/%s' % video_id, video_id)
formats = []
for _, video_url in re.findall(r'file\s*=\s*(["\'])(.+?)\1', webpage):
if video_url.startswith('rtmp://'):
rtmp = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>.+/))(?P<play_path>mp4:.+)$', video_url)
formats[0].update({
rtmp = re.search(
r'^(?P<url>rtmp://[^/]+/(?P<app>.+/))(?P<play_path>mp4:.+)$', video_url)
formats.append({
'url': rtmp.group('url'),
'format_id': 'rtmp',
'ext': 'flv',
'app': rtmp.group('app'),
'play_path': rtmp.group('play_path'),
'page_url': url,
})
else:
formats.append({
'url': video_url,
'format_id': 'http',
})
self._sort_formats(formats)
title = self._html_search_regex(
r'(?s)class="[^"]*col_description[^"]*">.*?<h3>(.*?)</h3>', webpage, 'title')