ytdl/youtube_dl/extractor/canalc2.py

57 lines
1.8 KiB
Python
Raw Normal View History

2013-08-22 13:54:23 +02:00
# coding: utf-8
2014-02-22 14:27:09 +01:00
from __future__ import unicode_literals
2013-08-22 13:54:23 +02:00
import re
from .common import InfoExtractor
2015-10-18 15:27:05 +02:00
from ..utils import parse_duration
2013-08-22 13:54:23 +02:00
2013-08-27 10:35:20 +02:00
2013-08-22 13:54:23 +02:00
class Canalc2IE(InfoExtractor):
2013-09-10 12:13:22 +02:00
IE_NAME = 'canalc2.tv'
2015-10-18 15:23:31 +02:00
_VALID_URL = r'https?://(?:www\.)?canalc2\.tv/video/(?P<id>\d+)'
2013-08-22 13:54:23 +02:00
_TEST = {
2015-09-21 16:52:36 +02:00
'url': 'http://www.canalc2.tv/video/12163',
2014-02-22 14:27:09 +01:00
'md5': '060158428b650f896c542dfbb3d6487f',
'info_dict': {
'id': '12163',
2015-10-18 15:27:22 +02:00
'ext': 'flv',
'title': 'Terrasses du Numérique',
'duration': 122,
2015-09-21 16:52:36 +02:00
},
'params': {
'skip_download': True, # Requires rtmpdump
2013-08-22 13:54:23 +02:00
}
}
def _real_extract(self, url):
2015-09-21 16:52:36 +02:00
video_id = self._match_id(url)
2013-08-22 13:54:23 +02:00
webpage = self._download_webpage(url, video_id)
2015-09-21 16:52:36 +02:00
video_url = self._search_regex(
2015-10-18 15:23:31 +02:00
r'jwplayer\((["\'])Player\1\)\.setup\({[^}]*file\s*:\s*(["\'])(?P<file>.+?)\2',
webpage, 'video_url', group='file')
2015-09-21 16:52:36 +02:00
formats = [{'url': video_url}]
if video_url.startswith('rtmp://'):
2015-10-18 15:19:43 +02:00
rtmp = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>.+/))(?P<play_path>mp4:.+)$', video_url)
2015-09-21 16:52:36 +02:00
formats[0].update({
2015-10-18 15:19:43 +02:00
'url': rtmp.group('url'),
2015-10-18 15:23:52 +02:00
'ext': 'flv',
2015-09-21 16:52:36 +02:00
'app': rtmp.group('app'),
'play_path': rtmp.group('play_path'),
2015-10-18 15:19:43 +02:00
'page_url': url,
2015-09-21 16:52:36 +02:00
})
2013-08-27 10:35:20 +02:00
title = self._html_search_regex(
2015-09-21 16:52:36 +02:00
r'(?s)class="[^"]*col_description[^"]*">.*?<h3>(.*?)</h3>', webpage, 'title')
2015-10-18 15:27:05 +02:00
duration = parse_duration(self._search_regex(
r'id=["\']video_duree["\'][^>]*>([^<]+)',
webpage, 'duration', fatal=False))
2014-02-22 14:27:09 +01:00
return {
'id': video_id,
'title': title,
2015-10-18 15:27:05 +02:00
'duration': duration,
'formats': formats,
2014-02-22 14:27:09 +01:00
}