Raphaël G. Git Repositories - youtubedl/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 and History Vault'
  26     _VALID_URL = r'''(?x)
  27                     https?://
  28                         (?:www\.)?
  29                         (?P<domain>
  30                             (?:history(?:vault)?|aetv|mylifetime|lifetimemovieclub)\.com|
  31                             fyi\.tv
  32                         )/
  33                         (?:
  34                             shows/(?P<show_path>[^/]+(?:/[^/]+){0,2})|
  35                             movies/(?P<movie_display_id>[^/]+)(?:/full-movie)?|
  36                             specials/(?P<special_display_id>[^/]+)/full-special|
  37                             collections/[^/]+/(?P<collection_display_id>[^/]+)
  38                         )
  39                     '''
  40     _TESTS = [{
  41         'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
  42         'md5': 'a97a65f7e823ae10e9244bc5433d5fe6',
  43         'info_dict': {
  44             'id': '22253814',
  45             'ext': 'mp4',
  46             'title': 'Winter Is Coming',
  47             'description': 'md5:641f424b7a19d8e24f26dea22cf59d74',
  48             'timestamp': 1338306241,
  49             'upload_date': '20120529',
  50             'uploader': 'AENE-NEW',
  51         },
  52         'add_ie': ['ThePlatform'],
  53     }, {
  54         'url': 'http://www.history.com/shows/ancient-aliens/season-1',
  55         'info_dict': {
  56             'id': '71889446852',
  57         },
  58         'playlist_mincount': 5,
  59     }, {
  60         'url': 'http://www.mylifetime.com/shows/atlanta-plastic',
  61         'info_dict': {
  62             'id': 'SERIES4317',
  63             'title': 'Atlanta Plastic',
  64         },
  65         'playlist_mincount': 2,
  66     }, {
  67         'url': 'http://www.aetv.com/shows/duck-dynasty/season-9/episode-1',
  68         'only_matching': True
  69     }, {
  70         'url': 'http://www.fyi.tv/shows/tiny-house-nation/season-1/episode-8',
  71         'only_matching': True
  72     }, {
  73         'url': 'http://www.mylifetime.com/shows/project-runway-junior/season-1/episode-6',
  74         'only_matching': True
  75     }, {
  76         'url': 'http://www.mylifetime.com/movies/center-stage-on-pointe/full-movie',
  77         'only_matching': True
  78     }, {
  79         'url': 'https://www.lifetimemovieclub.com/movies/a-killer-among-us',
  80         'only_matching': True
  81     }, {
  82         'url': 'http://www.history.com/specials/sniper-into-the-kill-zone/full-special',
  83         'only_matching': True
  84     }, {
  85         'url': 'https://www.historyvault.com/collections/america-the-story-of-us/westward',
  86         'only_matching': True
  87     }]
  88     _DOMAIN_TO_REQUESTOR_ID = {
  89         'history.com': 'HISTORY',
  90         'aetv.com': 'AETV',
  91         'mylifetime.com': 'LIFETIME',
  92         'lifetimemovieclub.com': 'LIFETIMEMOVIECLUB',
  93         'fyi.tv': 'FYI',
  94     }
  95
  96     def _real_extract(self, url):
  97         domain, show_path, movie_display_id, special_display_id, collection_display_id = re.match(self._VALID_URL, url).groups()
  98         display_id = show_path or movie_display_id or special_display_id or collection_display_id
  99         webpage = self._download_webpage(url, display_id, headers=self.geo_verification_headers())
 100         if show_path:
 101             url_parts = show_path.split('/')
 102             url_parts_len = len(url_parts)
 103             if url_parts_len == 1:
 104                 entries = []
 105                 for season_url_path in re.findall(r'(?s)<li[^>]+data-href="(/shows/%s/season-\d+)"' % url_parts[0], webpage):
 106                     entries.append(self.url_result(
 107                         compat_urlparse.urljoin(url, season_url_path), 'AENetworks'))
 108                 if entries:
 109                     return self.playlist_result(
 110                         entries, self._html_search_meta('aetn:SeriesId', webpage),
 111                         self._html_search_meta('aetn:SeriesTitle', webpage))
 112                 else:
 113                     # single season
 114                     url_parts_len = 2
 115             if url_parts_len == 2:
 116                 entries = []
 117                 for episode_item in re.findall(r'(?s)<[^>]+class="[^"]*(?:episode|program)-item[^"]*"[^>]*>', webpage):
 118                     episode_attributes = extract_attributes(episode_item)
 119                     episode_url = compat_urlparse.urljoin(
 120                         url, episode_attributes['data-canonical'])
 121                     entries.append(self.url_result(
 122                         episode_url, 'AENetworks',
 123                         episode_attributes.get('data-videoid') or episode_attributes.get('data-video-id')))
 124                 return self.playlist_result(
 125                     entries, self._html_search_meta('aetn:SeasonId', webpage))
 126
 127         query = {
 128             'mbr': 'true',
 129             'assetTypes': 'high_video_ak',
 130             'switch': 'hls_high_ak',
 131         }
 132         video_id = self._html_search_meta('aetn:VideoID', webpage)
 133         media_url = self._search_regex(
 134             [r"media_url\s*=\s*'(?P<url>[^']+)'",
 135              r'data-media-url=(?P<url>(?:https?:)?//[^\s>]+)',
 136              r'data-media-url=(["\'])(?P<url>(?:(?!\1).)+?)\1'],
 137             webpage, 'video url', group='url')
 138         theplatform_metadata = self._download_theplatform_metadata(self._search_regex(
 139             r'https?://link\.theplatform\.com/s/([^?]+)', media_url, 'theplatform_path'), video_id)
 140         info = self._parse_theplatform_metadata(theplatform_metadata)
 141         if theplatform_metadata.get('AETN$isBehindWall'):
 142             requestor_id = self._DOMAIN_TO_REQUESTOR_ID[domain]
 143             resource = self._get_mvpd_resource(
 144                 requestor_id, theplatform_metadata['title'],
 145                 theplatform_metadata.get('AETN$PPL_pplProgramId') or theplatform_metadata.get('AETN$PPL_pplProgramId_OLD'),
 146                 theplatform_metadata['ratings'][0]['rating'])
 147             query['auth'] = self._extract_mvpd_auth(
 148                 url, video_id, requestor_id, resource)
 149         info.update(self._search_json_ld(webpage, video_id, fatal=False))
 150         media_url = update_url_query(media_url, query)
 151         media_url = self._sign_url(media_url, self._THEPLATFORM_KEY, self._THEPLATFORM_SECRET)
 152         formats, subtitles = self._extract_theplatform_smil(media_url, video_id)
 153         self._sort_formats(formats)
 154         info.update({
 155             'id': video_id,
 156             'formats': formats,
 157             'subtitles': subtitles,
 158         })
 159         return info
 160
 161
 162 class HistoryTopicIE(AENetworksBaseIE):
 163     IE_NAME = 'history:topic'
 164     IE_DESC = 'History.com Topic'
 165     _VALID_URL = r'https?://(?:www\.)?history\.com/topics/(?:[^/]+/)?(?P<topic_id>[^/]+)(?:/[^/]+(?:/(?P<video_display_id>[^/?#]+))?)?'
 166     _TESTS = [{
 167         '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',
 168         'info_dict': {
 169             'id': '40700995724',
 170             'ext': 'mp4',
 171             'title': "Bet You Didn't Know: Valentine's Day",
 172             'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7',
 173             'timestamp': 1375819729,
 174             'upload_date': '20130806',
 175             'uploader': 'AENE-NEW',
 176         },
 177         'params': {
 178             # m3u8 download
 179             'skip_download': True,
 180         },
 181         'add_ie': ['ThePlatform'],
 182     }, {
 183         'url': 'http://www.history.com/topics/world-war-i/world-war-i-history/videos',
 184         'info_dict':
 185         {
 186             'id': 'world-war-i-history',
 187             'title': 'World War I History',
 188         },
 189         'playlist_mincount': 23,
 190     }, {
 191         'url': 'http://www.history.com/topics/world-war-i-history/videos',
 192         'only_matching': True,
 193     }, {
 194         'url': 'http://www.history.com/topics/world-war-i/world-war-i-history',
 195         'only_matching': True,
 196     }, {
 197         'url': 'http://www.history.com/topics/world-war-i/world-war-i-history/speeches',
 198         'only_matching': True,
 199     }]
 200
 201     def theplatform_url_result(self, theplatform_url, video_id, query):
 202         return {
 203             '_type': 'url_transparent',
 204             'id': video_id,
 205             'url': smuggle_url(
 206                 update_url_query(theplatform_url, query),
 207                 {
 208                     'sig': {
 209                         'key': self._THEPLATFORM_KEY,
 210                         'secret': self._THEPLATFORM_SECRET,
 211                     },
 212                     'force_smil_url': True
 213                 }),
 214             'ie_key': 'ThePlatform',
 215         }
 216
 217     def _real_extract(self, url):
 218         topic_id, video_display_id = re.match(self._VALID_URL, url).groups()
 219         if video_display_id:
 220             webpage = self._download_webpage(url, video_display_id)
 221             release_url, video_id = re.search(r"_videoPlayer.play\('([^']+)'\s*,\s*'[^']+'\s*,\s*'(\d+)'\)", webpage).groups()
 222             release_url = unescapeHTML(release_url)
 223
 224             return self.theplatform_url_result(
 225                 release_url, video_id, {
 226                     'mbr': 'true',
 227                     'switch': 'hls',
 228                     'assetTypes': 'high_video_ak',
 229                 })
 230         else:
 231             webpage = self._download_webpage(url, topic_id)
 232             entries = []
 233             for episode_item in re.findall(r'<a.+?data-release-url="[^"]+"[^>]*>', webpage):
 234                 video_attributes = extract_attributes(episode_item)
 235                 entries.append(self.theplatform_url_result(
 236                     video_attributes['data-release-url'], video_attributes['data-id'], {
 237                         'mbr': 'true',
 238                         'switch': 'hls',
 239                         'assetTypes': 'high_video_ak',
 240                     }))
 241             return self.playlist_result(entries, topic_id, get_element_by_attribute('class', 'show-title', webpage))