Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/etonline.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 ETOnlineIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?etonline\.com/(?:[^/]+/)*(?P<id>[^/?#&]+)'
  11     _TESTS = [{
  12         'url': 'http://www.etonline.com/tv/211130_dove_cameron_liv_and_maddie_emotional_episode_series_finale/',
  13         'info_dict': {
  14             'id': '211130_dove_cameron_liv_and_maddie_emotional_episode_series_finale',
  15             'title': 'md5:a21ec7d3872ed98335cbd2a046f34ee6',
  16             'description': 'md5:8b94484063f463cca709617c79618ccd',
  17         },
  18         'playlist_count': 2,
  19     }, {
  20         'url': 'http://www.etonline.com/media/video/here_are_the_stars_who_love_bringing_their_moms_as_dates_to_the_oscars-211359/',
  21         'only_matching': True,
  22     }]
  23     BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1242911076001/default_default/index.html?videoId=ref:%s'
  24
  25     def _real_extract(self, url):
  26         playlist_id = self._match_id(url)
  27
  28         webpage = self._download_webpage(url, playlist_id)
  29
  30         entries = [
  31             self.url_result(
  32                 self.BRIGHTCOVE_URL_TEMPLATE % video_id, 'BrightcoveNew', video_id)
  33             for video_id in re.findall(
  34                 r'site\.brightcove\s*\([^,]+,\s*["\'](title_\d+)', webpage)]
  35
  36         return self.playlist_result(
  37             entries, playlist_id,
  38             self._og_search_title(webpage, fatal=False),
  39             self._og_search_description(webpage))