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

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3 import re
   4
   5 from .common import InfoExtractor
   6 from .brightcove import BrightcoveLegacyIE
   7 from .discovery import DiscoveryIE
   8 from ..compat import compat_urlparse
   9
  10
  11 class TlcIE(DiscoveryIE):
  12     IE_NAME = 'tlc.com'
  13     _VALID_URL = r'http://www\.tlc\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9\-]*)(.htm)?'
  14
  15     # DiscoveryIE has _TESTS
  16     _TESTS = [{
  17         'url': 'http://www.tlc.com/tv-shows/cake-boss/videos/too-big-to-fly.htm',
  18         'info_dict': {
  19             'id': '104493',
  20             'ext': 'mp4',
  21             'title': 'Too Big to Fly',
  22             'description': 'Buddy has taken on a high flying task.',
  23             'duration': 119,
  24             'timestamp': 1393365060,
  25             'upload_date': '20140225',
  26         },
  27         'params': {
  28             'skip_download': True,  # requires ffmpef
  29         },
  30     }]
  31
  32
  33 class TlcDeIE(InfoExtractor):
  34     IE_NAME = 'tlc.de'
  35     _VALID_URL = r'http://www\.tlc\.de/sendungen/[^/]+/videos/(?P<title>[^/?]+)'
  36
  37     _TEST = {
  38         'url': 'http://www.tlc.de/sendungen/breaking-amish/videos/#3235167922001',
  39         'info_dict': {
  40             'id': '3235167922001',
  41             'ext': 'mp4',
  42             'title': 'Breaking Amish: Die Welt da draußen',
  43             'uploader': 'Discovery Networks - Germany',
  44             'description': (
  45                 'Vier Amische und eine Mennonitin wagen in New York'
  46                 '  den Sprung in ein komplett anderes Leben. Begleitet sie auf'
  47                 ' ihrem spannenden Weg.'),
  48         },
  49     }
  50
  51     def _real_extract(self, url):
  52         mobj = re.match(self._VALID_URL, url)
  53         title = mobj.group('title')
  54         webpage = self._download_webpage(url, title)
  55         iframe_url = self._search_regex(
  56             '<iframe src="(http://www\.tlc\.de/wp-content/.+?)"', webpage,
  57             'iframe url')
  58         # Otherwise we don't get the correct 'BrightcoveExperience' element,
  59         # example: http://www.tlc.de/sendungen/cake-boss/videos/cake-boss-cannoli-drama/
  60         iframe_url = iframe_url.replace('.htm?', '.php?')
  61         url_fragment = compat_urlparse.urlparse(url).fragment
  62         if url_fragment:
  63             # Since the fragment is not send to the server, we always get the same iframe
  64             iframe_url = re.sub(r'playlist=(\d+)', 'playlist=%s' % url_fragment, iframe_url)
  65         iframe = self._download_webpage(iframe_url, title)
  66
  67         return {
  68             '_type': 'url',
  69             'url': BrightcoveLegacyIE._extract_brightcove_url(iframe),
  70             'ie': BrightcoveLegacyIE.ie_key(),
  71         }