Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/canalc2.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8
   9 class Canalc2IE(InfoExtractor):
  10     IE_NAME = 'canalc2.tv'
  11     _VALID_URL = r'http://.*?\.canalc2\.tv/video\.asp\?.*?idVideo=(?P<id>\d+)'
  12
  13     _TEST = {
  14         'url': 'http://www.canalc2.tv/video.asp?idVideo=12163&voir=oui',
  15         'md5': '060158428b650f896c542dfbb3d6487f',
  16         'info_dict': {
  17             'id': '12163',
  18             'ext': 'mp4',
  19             'title': 'Terrasses du Numérique'
  20         }
  21     }
  22
  23     def _real_extract(self, url):
  24         video_id = re.match(self._VALID_URL, url).group('id')
  25         # We need to set the voir field for getting the file name
  26         url = 'http://www.canalc2.tv/video.asp?idVideo=%s&voir=oui' % video_id
  27         webpage = self._download_webpage(url, video_id)
  28         file_name = self._search_regex(
  29             r"so\.addVariable\('file','(.*?)'\);",
  30             webpage, 'file name')
  31         video_url = 'http://vod-flash.u-strasbg.fr:8080/' + file_name
  32
  33         title = self._html_search_regex(
  34             r'class="evenement8">(.*?)</a>', webpage, 'title')
  35
  36         return {
  37             'id': video_id,
  38             'ext': 'mp4',
  39             'url': video_url,
  40             'title': title,
  41         }