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'''(?x)
  27                     https?://
  28                         (?:www\.)?
  29                         (?P<domain>
  30                             (?:history|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                         )
  38                     '''
  39     _TESTS = [{
  40         'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
  41         'md5': 'a97a65f7e823ae10e9244bc5433d5fe6',
  42         'info_dict': {
  43             'id': '22253814',
  44             'ext': 'mp4',
  45             'title': 'Winter Is Coming',
  46             'description': 'md5:641f424b7a19d8e24f26dea22cf59d74',
  47             'timestamp': 1338306241,
  48             'upload_date': '20120529',
  49             'uploader': 'AENE-NEW',
  50         },
  51         'add_ie': ['ThePlatform'],
  52     }, {
  53         'url': 'http://www.history.com/shows/ancient-aliens/season-1',
  54         'info_dict': {
  55             'id': '71889446852',
  56         },
  57         'playlist_mincount': 5,
  58     }, {
  59         'url': 'http://www.mylifetime.com/shows/atlanta-plastic',
  60         'info_dict': {
  61             'id': 'SERIES4317',
  62             'title': 'Atlanta Plastic',
  63         },
  64         'playlist_mincount': 2,
  65     }, {
  66         'url': 'http://www.aetv.com/shows/duck-dynasty/season-9/episode-1',
  67         'only_matching': True
  68     }, {
  69         'url': 'http://www.fyi.tv/shows/tiny-house-nation/season-1/episode-8',
  70         'only_matching': True
  71     }, {
  72         'url': 'http://www.mylifetime.com/shows/project-runway-junior/season-1/episode-6',
  73         'only_matching': True
  74     }, {
  75         'url': 'http://www.mylifetime.com/movies/center-stage-on-pointe/full-movie',
  76         'only_matching': True
  77     }, {
  78         'url': 'https://www.lifetimemovieclub.com/movies/a-killer-among-us',
  79         'only_matching': True
  80     }, {
  81         'url': 'http://www.history.com/specials/sniper-into-the-kill-zone/full-special',
  82         'only_matching': True
  83     }]
  84     _DOMAIN_TO_REQUESTOR_ID = {
  85         'history.com': 'HISTORY',
  86         'aetv.com': 'AETV',
  87         'mylifetime.com': 'LIFETIME',
  88         'lifetimemovieclub.com': 'LIFETIMEMOVIECLUB',
  89         'fyi.tv': 'FYI',
  90     }
  91
  92     def _real_extract(self, url):
  93         domain, show_path, movie_display_id, special_display_id = re.match(self._VALID_URL, url).groups()
  94         display_id = show_path or movie_display_id or special_display_id
  95         webpage = self._download_webpage(url, display_id)
  96         if show_path:
  97             url_parts = show_path.split('/')
  98             url_parts_len = len(url_parts)
  99             if url_parts_len == 1:
 100                 entries = []
 101                 for season_url_path in re.findall(r'(?s)<li[^>]+data-href="(/shows/%s/season-\d+)"' % url_parts[0], webpage):
 102                     entries.append(self.url_result(
 103                         compat_urlparse.urljoin(url, season_url_path), 'AENetworks'))
 104                 if entries:
 105                     return self.playlist_result(
 106                         entries, self._html_search_meta('aetn:SeriesId', webpage),
 107                         self._html_search_meta('aetn:SeriesTitle', webpage))
 108                 else:
 109                     # single season
 110                     url_parts_len = 2
 111             if url_parts_len == 2:
 112                 entries = []
 113                 for episode_item in re.findall(r'(?s)<[^>]+class="[^"]*(?:episode|program)-item[^"]*"[^>]*>', webpage):
 114                     episode_attributes = extract_attributes(episode_item)
 115                     episode_url = compat_urlparse.urljoin(
 116                         url, episode_attributes['data-canonical'])
 117                     entries.append(self.url_result(
 118                         episode_url, 'AENetworks',
 119                         episode_attributes.get('data-videoid') or episode_attributes.get('data-video-id')))
 120                 return self.playlist_result(
 121                     entries, self._html_search_meta('aetn:SeasonId', webpage))
 122
 123         query = {
 124             'mbr': 'true',
 125             'assetTypes': 'high_video_s3'
 126         }
 127         video_id = self._html_search_meta('aetn:VideoID', webpage)
 128         media_url = self._search_regex(
 129             [r"media_url\s*=\s*'(?P<url>[^']+)'",
 130              r'data-media-url=(?P<url>(?:https?:)?//[^\s>]+)',
 131              r'data-media-url=(["\'])(?P<url>(?:(?!\1).)+?)\1'],
 132             webpage, 'video url', group='url')
 133         theplatform_metadata = self._download_theplatform_metadata(self._search_regex(
 134             r'https?://link.theplatform.com/s/([^?]+)', media_url, 'theplatform_path'), video_id)
 135         info = self._parse_theplatform_metadata(theplatform_metadata)
 136         if theplatform_metadata.get('AETN$isBehindWall'):
 137             requestor_id = self._DOMAIN_TO_REQUESTOR_ID[domain]
 138             resource = self._get_mvpd_resource(
 139                 requestor_id, theplatform_metadata['title'],
 140                 theplatform_metadata.get('AETN$PPL_pplProgramId') or theplatform_metadata.get('AETN$PPL_pplProgramId_OLD'),
 141                 theplatform_metadata['ratings'][0]['rating'])
 142             query['auth'] = self._extract_mvpd_auth(
 143                 url, video_id, requestor_id, resource)
 144         info.update(self._search_json_ld(webpage, video_id, fatal=False))
 145         media_url = update_url_query(media_url, query)
 146         media_url = self._sign_url(media_url, self._THEPLATFORM_KEY, self._THEPLATFORM_SECRET)
 147         formats, subtitles = self._extract_theplatform_smil(media_url, video_id)
 148         self._sort_formats(formats)
 149         info.update({
 150             'id': video_id,
 151             'formats': formats,
 152             'subtitles': subtitles,
 153         })
 154         return info
 155
 156
 157 class HistoryTopicIE(AENetworksBaseIE):
 158     IE_NAME = 'history:topic'
 159     IE_DESC = 'History.com Topic'
 160     _VALID_URL = r'https?://(?:www\.)?history\.com/topics/(?:[^/]+/)?(?P<topic_id>[^/]+)(?:/[^/]+(?:/(?P<video_display_id>[^/?#]+))?)?'
 161     _TESTS = [{
 162         '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',
 163         'info_dict': {
 164             'id': '40700995724',
 165             'ext': 'mp4',
 166             'title': "Bet You Didn't Know: Valentine's Day",
 167             'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7',
 168             'timestamp': 1375819729,
 169             'upload_date': '20130806',
 170             'uploader': 'AENE-NEW',
 171         },
 172         'params': {
 173             # m3u8 download
 174             'skip_download': True,
 175         },
 176         'add_ie': ['ThePlatform'],
 177     }, {
 178         'url': 'http://www.history.com/topics/world-war-i/world-war-i-history/videos',
 179         'info_dict':
 180         {
 181             'id': 'world-war-i-history',
 182             'title': 'World War I History',
 183         },
 184         'playlist_mincount': 23,
 185     }, {
 186         'url': 'http://www.history.com/topics/world-war-i-history/videos',
 187         'only_matching': True,
 188     }, {
 189         'url': 'http://www.history.com/topics/world-war-i/world-war-i-history',
 190         'only_matching': True,
 191     }, {
 192         'url': 'http://www.history.com/topics/world-war-i/world-war-i-history/speeches',
 193         'only_matching': True,
 194     }]
 195
 196     def theplatform_url_result(self, theplatform_url, video_id, query):
 197         return {
 198             '_type': 'url_transparent',
 199             'id': video_id,
 200             'url': smuggle_url(
 201                 update_url_query(theplatform_url, query),
 202                 {
 203                     'sig': {
 204                         'key': self._THEPLATFORM_KEY,
 205                         'secret': self._THEPLATFORM_SECRET,
 206                     },
 207                     'force_smil_url': True
 208                 }),
 209             'ie_key': 'ThePlatform',
 210         }
 211
 212     def _real_extract(self, url):
 213         topic_id, video_display_id = re.match(self._VALID_URL, url).groups()
 214         if video_display_id:
 215             webpage = self._download_webpage(url, video_display_id)
 216             release_url, video_id = re.search(r"_videoPlayer.play\('([^']+)'\s*,\s*'[^']+'\s*,\s*'(\d+)'\)", webpage).groups()
 217             release_url = unescapeHTML(release_url)
 218
 219             return self.theplatform_url_result(
 220                 release_url, video_id, {
 221                     'mbr': 'true',
 222                     'switch': 'hls',
 223                     'assetTypes': 'high_video_ak',
 224                 })
 225         else:
 226             webpage = self._download_webpage(url, topic_id)
 227             entries = []
 228             for episode_item in re.findall(r'<a.+?data-release-url="[^"]+"[^>]*>', webpage):
 229                 video_attributes = extract_attributes(episode_item)
 230                 entries.append(self.theplatform_url_result(
 231                     video_attributes['data-release-url'], video_attributes['data-id'], {
 232                         'mbr': 'true',
 233                         'switch': 'hls',
 234                         'assetTypes': 'high_video_ak',
 235                     }))
 236             return self.playlist_result(entries, topic_id, get_element_by_attribute('class', 'show-title', webpage))