_ Git - youtube-dl/blob - 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         'expected_warnings': ['JSON-LD'],
  24     }, {
  25         'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
  26         'info_dict': {
  27             'id': 'eg47EERs_JsZ',
  28             'ext': 'mp4',
  29             'title': "Winter Is Coming",
  30             'description': 'md5:641f424b7a19d8e24f26dea22cf59d74',
  31         },
  32         'params': {
  33             # m3u8 download
  34             'skip_download': True,
  35         },
  36         'add_ie': ['ThePlatform'],
  37     }, {
  38         'url': 'http://www.aetv.com/shows/duck-dynasty/video/inlawful-entry',
  39         'only_matching': True
  40     }, {
  41         'url': 'http://www.fyi.tv/shows/tiny-house-nation/videos/207-sq-ft-minnesota-prairie-cottage',
  42         'only_matching': True
  43     }, {
  44         'url': 'http://www.mylifetime.com/shows/project-runway-junior/video/season-1/episode-6/superstar-clients',
  45         'only_matching': True
  46     }]
  47
  48     def _real_extract(self, url):
  49         video_id = self._match_id(url)
  50
  51         webpage = self._download_webpage(url, video_id)
  52
  53         video_url_re = [
  54             r'data-href="[^"]*/%s"[^>]+data-release-url="([^"]+)"' % video_id,
  55             r"media_url\s*=\s*'([^']+)'"
  56         ]
  57         video_url = self._search_regex(video_url_re, webpage, 'video url')
  58
  59         info = self._search_json_ld(webpage, video_id, fatal=False)
  60         info.update({
  61             '_type': 'url_transparent',
  62             'url': smuggle_url(video_url, {'sig': {'key': 'crazyjava', 'secret': 's3cr3t'}}),
  63         })
  64         return info