youtube_dl/extractor/ae.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import smuggle_url
   5
   6
   7 class AEIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?(?:(?:history|aetv|mylifetime)\.com|fyi\.tv)/(?:[^/]+/)+(?P<id>[^/]+?)(?:$|[?#])'
   9
  10     _TESTS = [{
  11         'url': 'http://www.history.com/topics/valentines-day/history-of-valentines-day/videos/bet-you-didnt-know-valentines-day?m=528e394da93ae&s=undefined&f=1&free=false',
  12         'info_dict': {
  13             'id': 'g12m5Gyt3fdR',
  14             'ext': 'mp4',
  15             'title': "Bet You Didn't Know: Valentine's Day",
  16             'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7',
  17         },
  18         'params': {
  19             # m3u8 download
  20             'skip_download': True,
  21         },
  22         'add_ie': ['ThePlatform'],
  23     }, {
  24         'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
  25         'info_dict': {
  26             'id': 'eg47EERs_JsZ',
  27             'ext': 'mp4',
  28             'title': "Winter Is Coming",
  29             'description': 'md5:a40e370925074260b1c8a633c632c63a',
  30         },
  31         'params': {
  32             # m3u8 download
  33             'skip_download': True,
  34         },
  35         'add_ie': ['ThePlatform'],
  36     }, {
  37         'url': 'http://www.aetv.com/shows/duck-dynasty/video/inlawful-entry',
  38         'only_matching': True
  39     }, {
  40         'url': 'http://www.fyi.tv/shows/tiny-house-nation/videos/207-sq-ft-minnesota-prairie-cottage',
  41         'only_matching': True
  42     }, {
  43         'url': 'http://www.mylifetime.com/shows/project-runway-junior/video/season-1/episode-6/superstar-clients',
  44         'only_matching': True
  45     }]
  46
  47     def _real_extract(self, url):
  48         video_id = self._match_id(url)
  49
  50         webpage = self._download_webpage(url, video_id)
  51
  52         video_url_re = [
  53             r'data-href="[^"]*/%s"[^>]+data-release-url="([^"]+)"' % video_id,
  54             r"media_url\s*=\s*'([^']+)'"
  55         ]
  56         video_url = self._search_regex(video_url_re, webpage, 'video url')
  57
  58         info = self._search_json_ld(webpage, video_id, fatal=False)
  59         info.update({
  60             '_type': 'url_transparent',
  61             'url': smuggle_url(video_url, {'sig': {'key': 'crazyjava', 'secret': 's3cr3t'}}),
  62         })
  63         return info