_ Git - youtube-dl/blob - youtube_dl/extractor/aenetworks.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .theplatform import ThePlatformIE
   6 from ..utils import (
   7     smuggle_url,
   8     update_url_query,
   9     unescapeHTML,
  10     extract_attributes,
  11     get_element_by_attribute,
  12 )
  13 from ..compat import (
  14     compat_urlparse,
  15 )
  16
  17
  18 class AENetworksBaseIE(ThePlatformIE):
  19     _THEPLATFORM_KEY = 'crazyjava'
  20     _THEPLATFORM_SECRET = 's3cr3t'
  21
  22
  23 class AENetworksIE(AENetworksBaseIE):
  24     IE_NAME = 'aenetworks'
  25     IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network'
  26     _VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:history|aetv|mylifetime|lifetimemovieclub)\.com|fyi\.tv)/(?:shows/(?P<show_path>[^/]+(?:/[^/]+){0,2})|movies/(?P<movie_display_id>[^/]+)(?:/full-movie)?)'
  27     _TESTS = [{
  28         'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
  29         'md5': 'a97a65f7e823ae10e9244bc5433d5fe6',
  30         'info_dict': {
  31             'id': '22253814',
  32             'ext': 'mp4',
  33             'title': 'Winter Is Coming',
  34             'description': 'md5:641f424b7a19d8e24f26dea22cf59d74',
  35             'timestamp': 1338306241,
  36             'upload_date': '20120529',
  37             'uploader': 'AENE-NEW',
  38         },
  39         'add_ie': ['ThePlatform'],
  40     }, {
  41         'url': 'http://www.history.com/shows/ancient-aliens/season-1',
  42         'info_dict': {
  43             'id': '71889446852',
  44         },
  45         'playlist_mincount': 5,
  46     }, {
  47         'url': 'http://www.mylifetime.com/shows/atlanta-plastic',
  48         'info_dict': {
  49             'id': 'SERIES4317',
  50             'title': 'Atlanta Plastic',
  51         },
  52         'playlist_mincount': 2,
  53     }, {
  54         'url': 'http://www.aetv.com/shows/duck-dynasty/season-9/episode-1',
  55         'only_matching': True
  56     }, {
  57         'url': 'http://www.fyi.tv/shows/tiny-house-nation/season-1/episode-8',
  58         'only_matching': True
  59     }, {
  60         'url': 'http://www.mylifetime.com/shows/project-runway-junior/season-1/episode-6',
  61         'only_matching': True
  62     }, {
  63         'url': 'http://www.mylifetime.com/movies/center-stage-on-pointe/full-movie',
  64         'only_matching': True
  65     }, {
  66         'url': 'https://www.lifetimemovieclub.com/movies/a-killer-among-us',
  67         'only_matching': True
  68     }]
  69     _DOMAIN_TO_REQUESTOR_ID = {
  70         'history.com': 'HISTORY',
  71         'aetv.com': 'AETV',
  72         'mylifetime.com': 'LIFETIME',
  73         'lifetimemovieclub.com': 'LIFETIMEMOVIECLUB',
  74         'fyi.tv': 'FYI',
  75     }
  76
  77     def _real_extract(self, url):
  78         domain, show_path, movie_display_id = re.match(self._VALID_URL, url).groups()
  79         display_id = show_path or movie_display_id
  80         webpage = self._download_webpage(url, display_id)
  81         if show_path:
  82             url_parts = show_path.split('/')
  83             url_parts_len = len(url_parts)
  84             if url_parts_len == 1:
  85                 entries = []
  86                 for season_url_path in re.findall(r'(?s)<li[^>]+data-href="(/shows/%s/season-\d+)"' % url_parts[0], webpage):
  87                     entries.append(self.url_result(
  88                         compat_urlparse.urljoin(url, season_url_path), 'AENetworks'))
  89                 return self.playlist_result(
  90                     entries, self._html_search_meta('aetn:SeriesId', webpage),
  91                     self._html_search_meta('aetn:SeriesTitle', webpage))
  92             elif url_parts_len == 2:
  93                 entries = []
  94                 for episode_item in re.findall(r'(?s)<[^>]+class="[^"]*(?:episode|program)-item[^"]*"[^>]*>', webpage):
  95                     episode_attributes = extract_attributes(episode_item)
  96                     episode_url = compat_urlparse.urljoin(
  97                         url, episode_attributes['data-canonical'])
  98                     entries.append(self.url_result(
  99                         episode_url, 'AENetworks',
 100                         episode_attributes['data-videoid']))
 101                 return self.playlist_result(
 102                     entries, self._html_search_meta('aetn:SeasonId', webpage))
 103
 104         query = {
 105             'mbr': 'true',
 106             'assetTypes': 'high_video_s3'
 107         }
 108         video_id = self._html_search_meta('aetn:VideoID', webpage)
 109         media_url = self._search_regex(
 110             r"media_url\s*=\s*'([^']+)'", webpage, 'video url')
 111         theplatform_metadata = self._download_theplatform_metadata(self._search_regex(
 112             r'https?://link.theplatform.com/s/([^?]+)', media_url, 'theplatform_path'), video_id)
 113         info = self._parse_theplatform_metadata(theplatform_metadata)
 114         if theplatform_metadata.get('AETN$isBehindWall'):
 115             requestor_id = self._DOMAIN_TO_REQUESTOR_ID[domain]
 116             resource = self._get_mvpd_resource(
 117                 requestor_id, theplatform_metadata['title'],
 118                 theplatform_metadata.get('AETN$PPL_pplProgramId') or theplatform_metadata.get('AETN$PPL_pplProgramId_OLD'),
 119                 theplatform_metadata['ratings'][0]['rating'])
 120             query['auth'] = self._extract_mvpd_auth(
 121                 url, video_id, requestor_id, resource)
 122         info.update(self._search_json_ld(webpage, video_id, fatal=False))
 123         media_url = update_url_query(media_url, query)
 124         media_url = self._sign_url(media_url, self._THEPLATFORM_KEY, self._THEPLATFORM_SECRET)
 125         formats, subtitles = self._extract_theplatform_smil(media_url, video_id)
 126         self._sort_formats(formats)
 127         info.update({
 128             'id': video_id,
 129             'formats': formats,
 130             'subtitles': subtitles,
 131         })
 132         return info
 133
 134
 135 class HistoryTopicIE(AENetworksBaseIE):
 136     IE_NAME = 'history:topic'
 137     IE_DESC = 'History.com Topic'
 138     _VALID_URL = r'https?://(?:www\.)?history\.com/topics/(?:[^/]+/)?(?P<topic_id>[^/]+)(?:/[^/]+(?:/(?P<video_display_id>[^/?#]+))?)?'
 139     _TESTS = [{
 140         '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',
 141         'info_dict': {
 142             'id': '40700995724',
 143             'ext': 'mp4',
 144             'title': "Bet You Didn't Know: Valentine's Day",
 145             'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7',
 146             'timestamp': 1375819729,
 147             'upload_date': '20130806',
 148             'uploader': 'AENE-NEW',
 149         },
 150         'params': {
 151             # m3u8 download
 152             'skip_download': True,
 153         },
 154         'add_ie': ['ThePlatform'],
 155     }, {
 156         'url': 'http://www.history.com/topics/world-war-i/world-war-i-history/videos',
 157         'info_dict':
 158         {
 159             'id': 'world-war-i-history',
 160             'title': 'World War I History',
 161         },
 162         'playlist_mincount': 23,
 163     }, {
 164         'url': 'http://www.history.com/topics/world-war-i-history/videos',
 165         'only_matching': True,
 166     }, {
 167         'url': 'http://www.history.com/topics/world-war-i/world-war-i-history',
 168         'only_matching': True,
 169     }, {
 170         'url': 'http://www.history.com/topics/world-war-i/world-war-i-history/speeches',
 171         'only_matching': True,
 172     }]
 173
 174     def theplatform_url_result(self, theplatform_url, video_id, query):
 175         return {
 176             '_type': 'url_transparent',
 177             'id': video_id,
 178             'url': smuggle_url(
 179                 update_url_query(theplatform_url, query),
 180                 {
 181                     'sig': {
 182                         'key': self._THEPLATFORM_KEY,
 183                         'secret': self._THEPLATFORM_SECRET,
 184                     },
 185                     'force_smil_url': True
 186                 }),
 187             'ie_key': 'ThePlatform',
 188         }
 189
 190     def _real_extract(self, url):
 191         topic_id, video_display_id = re.match(self._VALID_URL, url).groups()
 192         if video_display_id:
 193             webpage = self._download_webpage(url, video_display_id)
 194             release_url, video_id = re.search(r"_videoPlayer.play\('([^']+)'\s*,\s*'[^']+'\s*,\s*'(\d+)'\)", webpage).groups()
 195             release_url = unescapeHTML(release_url)
 196
 197             return self.theplatform_url_result(
 198                 release_url, video_id, {
 199                     'mbr': 'true',
 200                     'switch': 'hls',
 201                     'assetTypes': 'high_video_ak',
 202                 })
 203         else:
 204             webpage = self._download_webpage(url, topic_id)
 205             entries = []
 206             for episode_item in re.findall(r'<a.+?data-release-url="[^"]+"[^>]*>', webpage):
 207                 video_attributes = extract_attributes(episode_item)
 208                 entries.append(self.theplatform_url_result(
 209                     video_attributes['data-release-url'], video_attributes['data-id'], {
 210                         'mbr': 'true',
 211                         'switch': 'hls',
 212                         'assetTypes': 'high_video_ak',
 213                     }))
 214             return self.playlist_result(entries, topic_id, get_element_by_attribute('class', 'show-title', webpage))