_ 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     extract_attributes,
   8     ExtractorError,
   9     int_or_none,
  10     smuggle_url,
  11     update_url_query,
  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     def _extract_aen_smil(self, smil_url, video_id, auth=None):
  23         query = {'mbr': 'true'}
  24         if auth:
  25             query['auth'] = auth
  26         TP_SMIL_QUERY = [{
  27             'assetTypes': 'high_video_ak',
  28             'switch': 'hls_high_ak'
  29         }, {
  30             'assetTypes': 'high_video_s3'
  31         }, {
  32             'assetTypes': 'high_video_s3',
  33             'switch': 'hls_ingest_fastly'
  34         }]
  35         formats = []
  36         subtitles = {}
  37         last_e = None
  38         for q in TP_SMIL_QUERY:
  39             q.update(query)
  40             m_url = update_url_query(smil_url, q)
  41             m_url = self._sign_url(m_url, self._THEPLATFORM_KEY, self._THEPLATFORM_SECRET)
  42             try:
  43                 tp_formats, tp_subtitles = self._extract_theplatform_smil(
  44                     m_url, video_id, 'Downloading %s SMIL data' % (q.get('switch') or q['assetTypes']))
  45             except ExtractorError as e:
  46                 last_e = e
  47                 continue
  48             formats.extend(tp_formats)
  49             subtitles = self._merge_subtitles(subtitles, tp_subtitles)
  50         if last_e and not formats:
  51             raise last_e
  52         self._sort_formats(formats)
  53         return {
  54             'id': video_id,
  55             'formats': formats,
  56             'subtitles': subtitles,
  57         }
  58
  59
  60 class AENetworksIE(AENetworksBaseIE):
  61     IE_NAME = 'aenetworks'
  62     IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network and History Vault'
  63     _VALID_URL = r'''(?x)
  64                     https?://
  65                         (?:www\.)?
  66                         (?P<domain>
  67                             (?:history(?:vault)?|aetv|mylifetime|lifetimemovieclub)\.com|
  68                             fyi\.tv
  69                         )/
  70                         (?:
  71                             shows/(?P<show_path>[^/]+(?:/[^/]+){0,2})|
  72                             movies/(?P<movie_display_id>[^/]+)(?:/full-movie)?|
  73                             specials/(?P<special_display_id>[^/]+)/(?:full-special|preview-)|
  74                             collections/[^/]+/(?P<collection_display_id>[^/]+)
  75                         )
  76                     '''
  77     _TESTS = [{
  78         'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
  79         'info_dict': {
  80             'id': '22253814',
  81             'ext': 'mp4',
  82             'title': 'Winter is Coming',
  83             'description': 'md5:641f424b7a19d8e24f26dea22cf59d74',
  84             'timestamp': 1338306241,
  85             'upload_date': '20120529',
  86             'uploader': 'AENE-NEW',
  87         },
  88         'params': {
  89             # m3u8 download
  90             'skip_download': True,
  91         },
  92         'add_ie': ['ThePlatform'],
  93     }, {
  94         'url': 'http://www.history.com/shows/ancient-aliens/season-1',
  95         'info_dict': {
  96             'id': '71889446852',
  97         },
  98         'playlist_mincount': 5,
  99     }, {
 100         'url': 'http://www.mylifetime.com/shows/atlanta-plastic',
 101         'info_dict': {
 102             'id': 'SERIES4317',
 103             'title': 'Atlanta Plastic',
 104         },
 105         'playlist_mincount': 2,
 106     }, {
 107         'url': 'http://www.aetv.com/shows/duck-dynasty/season-9/episode-1',
 108         'only_matching': True
 109     }, {
 110         'url': 'http://www.fyi.tv/shows/tiny-house-nation/season-1/episode-8',
 111         'only_matching': True
 112     }, {
 113         'url': 'http://www.mylifetime.com/shows/project-runway-junior/season-1/episode-6',
 114         'only_matching': True
 115     }, {
 116         'url': 'http://www.mylifetime.com/movies/center-stage-on-pointe/full-movie',
 117         'only_matching': True
 118     }, {
 119         'url': 'https://www.lifetimemovieclub.com/movies/a-killer-among-us',
 120         'only_matching': True
 121     }, {
 122         'url': 'http://www.history.com/specials/sniper-into-the-kill-zone/full-special',
 123         'only_matching': True
 124     }, {
 125         'url': 'https://www.historyvault.com/collections/america-the-story-of-us/westward',
 126         'only_matching': True
 127     }, {
 128         'url': 'https://www.aetv.com/specials/hunting-jonbenets-killer-the-untold-story/preview-hunting-jonbenets-killer-the-untold-story',
 129         'only_matching': True
 130     }]
 131     _DOMAIN_TO_REQUESTOR_ID = {
 132         'history.com': 'HISTORY',
 133         'aetv.com': 'AETV',
 134         'mylifetime.com': 'LIFETIME',
 135         'lifetimemovieclub.com': 'LIFETIMEMOVIECLUB',
 136         'fyi.tv': 'FYI',
 137     }
 138
 139     def _real_extract(self, url):
 140         domain, show_path, movie_display_id, special_display_id, collection_display_id = re.match(self._VALID_URL, url).groups()
 141         display_id = show_path or movie_display_id or special_display_id or collection_display_id
 142         webpage = self._download_webpage(url, display_id, headers=self.geo_verification_headers())
 143         if show_path:
 144             url_parts = show_path.split('/')
 145             url_parts_len = len(url_parts)
 146             if url_parts_len == 1:
 147                 entries = []
 148                 for season_url_path in re.findall(r'(?s)<li[^>]+data-href="(/shows/%s/season-\d+)"' % url_parts[0], webpage):
 149                     entries.append(self.url_result(
 150                         compat_urlparse.urljoin(url, season_url_path), 'AENetworks'))
 151                 if entries:
 152                     return self.playlist_result(
 153                         entries, self._html_search_meta('aetn:SeriesId', webpage),
 154                         self._html_search_meta('aetn:SeriesTitle', webpage))
 155                 else:
 156                     # single season
 157                     url_parts_len = 2
 158             if url_parts_len == 2:
 159                 entries = []
 160                 for episode_item in re.findall(r'(?s)<[^>]+class="[^"]*(?:episode|program)-item[^"]*"[^>]*>', webpage):
 161                     episode_attributes = extract_attributes(episode_item)
 162                     episode_url = compat_urlparse.urljoin(
 163                         url, episode_attributes['data-canonical'])
 164                     entries.append(self.url_result(
 165                         episode_url, 'AENetworks',
 166                         episode_attributes.get('data-videoid') or episode_attributes.get('data-video-id')))
 167                 return self.playlist_result(
 168                     entries, self._html_search_meta('aetn:SeasonId', webpage))
 169
 170         video_id = self._html_search_meta('aetn:VideoID', webpage)
 171         media_url = self._search_regex(
 172             [r"media_url\s*=\s*'(?P<url>[^']+)'",
 173              r'data-media-url=(?P<url>(?:https?:)?//[^\s>]+)',
 174              r'data-media-url=(["\'])(?P<url>(?:(?!\1).)+?)\1'],
 175             webpage, 'video url', group='url')
 176         theplatform_metadata = self._download_theplatform_metadata(self._search_regex(
 177             r'https?://link\.theplatform\.com/s/([^?]+)', media_url, 'theplatform_path'), video_id)
 178         info = self._parse_theplatform_metadata(theplatform_metadata)
 179         auth = None
 180         if theplatform_metadata.get('AETN$isBehindWall'):
 181             requestor_id = self._DOMAIN_TO_REQUESTOR_ID[domain]
 182             resource = self._get_mvpd_resource(
 183                 requestor_id, theplatform_metadata['title'],
 184                 theplatform_metadata.get('AETN$PPL_pplProgramId') or theplatform_metadata.get('AETN$PPL_pplProgramId_OLD'),
 185                 theplatform_metadata['ratings'][0]['rating'])
 186             auth = self._extract_mvpd_auth(
 187                 url, video_id, requestor_id, resource)
 188         info.update(self._search_json_ld(webpage, video_id, fatal=False))
 189         info.update(self._extract_aen_smil(media_url, video_id, auth))
 190         return info
 191
 192
 193 class HistoryTopicIE(AENetworksBaseIE):
 194     IE_NAME = 'history:topic'
 195     IE_DESC = 'History.com Topic'
 196     _VALID_URL = r'https?://(?:www\.)?history\.com/topics/[^/]+/(?P<id>[\w+-]+?)-video'
 197     _TESTS = [{
 198         'url': 'https://www.history.com/topics/valentines-day/history-of-valentines-day-video',
 199         'info_dict': {
 200             'id': '40700995724',
 201             'ext': 'mp4',
 202             'title': "History of Valentine’s Day",
 203             'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7',
 204             'timestamp': 1375819729,
 205             'upload_date': '20130806',
 206         },
 207         'params': {
 208             # m3u8 download
 209             'skip_download': True,
 210         },
 211         'add_ie': ['ThePlatform'],
 212     }]
 213
 214     def theplatform_url_result(self, theplatform_url, video_id, query):
 215         return {
 216             '_type': 'url_transparent',
 217             'id': video_id,
 218             'url': smuggle_url(
 219                 update_url_query(theplatform_url, query),
 220                 {
 221                     'sig': {
 222                         'key': self._THEPLATFORM_KEY,
 223                         'secret': self._THEPLATFORM_SECRET,
 224                     },
 225                     'force_smil_url': True
 226                 }),
 227             'ie_key': 'ThePlatform',
 228         }
 229
 230     def _real_extract(self, url):
 231         display_id = self._match_id(url)
 232         webpage = self._download_webpage(url, display_id)
 233         video_id = self._search_regex(
 234             r'<phoenix-iframe[^>]+src="[^"]+\btpid=(\d+)', webpage, 'tpid')
 235         result = self._download_json(
 236             'https://feeds.video.aetnd.com/api/v2/history/videos',
 237             video_id, query={'filter[id]': video_id})['results'][0]
 238         title = result['title']
 239         info = self._extract_aen_smil(result['publicUrl'], video_id)
 240         info.update({
 241             'title': title,
 242             'description': result.get('description'),
 243             'duration': int_or_none(result.get('duration')),
 244             'timestamp': int_or_none(result.get('added'), 1000),
 245         })
 246         return info