0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-23 02:25:11 +00:00
yt-dlp/youtube_dl/extractor/canalc2.py

69 lines
2.2 KiB
Python
Raw Normal View History

2013-08-22 11:54:23 +00:00
# coding: utf-8
2014-02-22 13:27:09 +00:00
from __future__ import unicode_literals
2013-08-22 11:54:23 +00:00
import re
from .common import InfoExtractor
2015-10-18 13:27:05 +00:00
from ..utils import parse_duration
2013-08-22 11:54:23 +00:00
2013-08-27 08:35:20 +00:00
2013-08-22 11:54:23 +00:00
class Canalc2IE(InfoExtractor):
2013-09-10 10:13:22 +00:00
IE_NAME = 'canalc2.tv'
_VALID_URL = r'https?://(?:(?:www\.)?canalc2\.tv/video/|archives-canalc2\.u-strasbg\.fr/video\.asp\?.*\bidVideo=)(?P<id>\d+)'
2013-08-22 11:54:23 +00:00
_TESTS = [{
2015-09-21 14:52:36 +00:00
'url': 'http://www.canalc2.tv/video/12163',
2014-02-22 13:27:09 +00:00
'md5': '060158428b650f896c542dfbb3d6487f',
'info_dict': {
'id': '12163',
2015-10-18 13:27:22 +00:00
'ext': 'flv',
'title': 'Terrasses du Numérique',
'duration': 122,
2015-09-21 14:52:36 +00:00
},
'params': {
'skip_download': True, # Requires rtmpdump
2013-08-22 11:54:23 +00:00
}
}, {
'url': 'http://archives-canalc2.u-strasbg.fr/video.asp?idVideo=11427&voir=oui',
'only_matching': True,
}]
2013-08-22 11:54:23 +00:00
def _real_extract(self, url):
2015-09-21 14:52:36 +00:00
video_id = self._match_id(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.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)
2013-08-27 08:35:20 +00:00
title = self._html_search_regex(
2015-09-21 14:52:36 +00:00
r'(?s)class="[^"]*col_description[^"]*">.*?<h3>(.*?)</h3>', webpage, 'title')
2015-10-18 13:27:05 +00:00
duration = parse_duration(self._search_regex(
r'id=["\']video_duree["\'][^>]*>([^<]+)',
webpage, 'duration', fatal=False))
2014-02-22 13:27:09 +00:00
return {
'id': video_id,
'title': title,
2015-10-18 13:27:05 +00:00
'duration': duration,
'formats': formats,
2014-02-22 13:27:09 +00:00
}