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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from .brightcove import BrightcoveLegacyIE
   8 from ..compat import (
   9     compat_parse_qs,
  10     compat_urlparse,
  11 )
  12
  13
  14 class TlcDeIE(InfoExtractor):
  15     IE_NAME = 'tlc.de'
  16     _VALID_URL = r'https?://(?:www\.)?tlc\.de/(?:[^/]+/)*videos/(?P<title>[^/?#]+)?(?:.*#(?P<id>\d+))?'
  17
  18     _TEST = {
  19         'url': 'http://www.tlc.de/sendungen/breaking-amish/videos/#3235167922001',
  20         'info_dict': {
  21             'id': '3235167922001',
  22             'ext': 'mp4',
  23             'title': 'Breaking Amish: Die Welt da draußen',
  24             'description': (
  25                 'Vier Amische und eine Mennonitin wagen in New York'
  26                 '  den Sprung in ein komplett anderes Leben. Begleitet sie auf'
  27                 ' ihrem spannenden Weg.'),
  28             'timestamp': 1396598084,
  29             'upload_date': '20140404',
  30             'uploader_id': '1659832546',
  31         },
  32     }
  33     BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1659832546/default_default/index.html?videoId=%s'
  34
  35     def _real_extract(self, url):
  36         mobj = re.match(self._VALID_URL, url)
  37         brightcove_id = mobj.group('id')
  38         if not brightcove_id:
  39             title = mobj.group('title')
  40             webpage = self._download_webpage(url, title)
  41             brightcove_legacy_url = BrightcoveLegacyIE._extract_brightcove_url(webpage)
  42             brightcove_id = compat_parse_qs(compat_urlparse.urlparse(brightcove_legacy_url).query)['@videoPlayer'][0]
  43         return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id)