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'https?://(www\.)?canalc2\.tv/video/(?P<id>\d+)'
  12
  13     _TEST = {
  14         'url': 'http://www.canalc2.tv/video/12163',
  15         'md5': '060158428b650f896c542dfbb3d6487f',
  16         'info_dict': {
  17             'id': '12163',
  18             'ext': 'mp4',
  19             'title': 'Terrasses du Numérique'
  20         },
  21         'params': {
  22             'skip_download': True,  # Requires rtmpdump
  23         }
  24     }
  25
  26     def _real_extract(self, url):
  27         video_id = self._match_id(url)
  28         webpage = self._download_webpage(url, video_id)
  29         video_url = self._search_regex(
  30             r'jwplayer\("Player"\).setup\({[^}]*file: "([^"]+)"',
  31             webpage, 'video_url')
  32         formats = [{'url': video_url}]
  33         if video_url.startswith('rtmp://'):
  34             rtmp = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>.+))/(?P<play_path>mp4:.+)$', video_url)
  35             formats[0].update({
  36                 'app': rtmp.group('app'),
  37                 'play_path': rtmp.group('play_path'),
  38             })
  39
  40         title = self._html_search_regex(
  41             r'(?s)class="[^"]*col_description[^"]*">.*?<h3>(.*?)</h3>', webpage, 'title')
  42
  43         return {
  44             'id': video_id,
  45             'formats': formats,
  46             'title': title,
  47         }