logo

youtube-dl

[mirror] Download/Watch videos from video hostersgit clone https://hacktivis.me/git/mirror/youtube-dl.git

aenetworks.py (12634B)

    

  1. # coding: utf-8
  2. from __future__ import unicode_literals
  4. import re
  6. from .theplatform import ThePlatformIE
  7. from ..utils import (
  8.     ExtractorError,
  9.     GeoRestrictedError,
  10.     int_or_none,
  11.     remove_start,
  12.     traverse_obj,
  13.     update_url_query,
  14.     urlencode_postdata,
  15. )
  18. class AENetworksBaseIE(ThePlatformIE):
  19.     _BASE_URL_REGEX = r'''(?x)https?://
  20.         (?:(?:www|play|watch)\.)?
  21.         (?P<domain>
  22.             (?:history(?:vault)?|aetv|mylifetime|lifetimemovieclub)\.com|
  23.             fyi\.tv
  24.         )/'''
  25.     _THEPLATFORM_KEY = '43jXaGRQud'
  26.     _THEPLATFORM_SECRET = 'S10BPXHMlb'
  27.     _DOMAIN_MAP = {
  28.         'history.com': ('HISTORY', 'history'),
  29.         'aetv.com': ('AETV', 'aetv'),
  30.         'mylifetime.com': ('LIFETIME', 'lifetime'),
  31.         'lifetimemovieclub.com': ('LIFETIMEMOVIECLUB', 'lmc'),
  32.         'fyi.tv': ('FYI', 'fyi'),
  33.         'historyvault.com': (None, 'historyvault'),
  34.         'biography.com': (None, 'biography'),
  35.     }
  37.     def _extract_aen_smil(self, smil_url, video_id, auth=None):
  38.         query = {
  39.             'mbr': 'true',
  40.             'formats': 'M3U+none,MPEG-DASH+none,MPEG4,MP3',
  41.         }
  42.         if auth:
  43.             query['auth'] = auth
  44.         TP_SMIL_QUERY = [{
  45.             'assetTypes': 'high_video_ak',
  46.             'switch': 'hls_high_ak',
  47.         }, {
  48.             'assetTypes': 'high_video_s3',
  49.         }, {
  50.             'assetTypes': 'high_video_s3',
  51.             'switch': 'hls_high_fastly',
  52.         }]
  53.         formats = []
  54.         subtitles = {}
  55.         last_e = None
  56.         for q in TP_SMIL_QUERY:
  57.             q.update(query)
  58.             m_url = update_url_query(smil_url, q)
  59.             m_url = self._sign_url(m_url, self._THEPLATFORM_KEY, self._THEPLATFORM_SECRET)
  60.             try:
  61.                 tp_formats, tp_subtitles = self._extract_theplatform_smil(
  62.                     m_url, video_id, 'Downloading %s SMIL data' % (q.get('switch') or q['assetTypes']))
  63.             except ExtractorError as e:
  64.                 if isinstance(e, GeoRestrictedError):
  65.                     raise
  66.                 last_e = e
  67.                 continue
  68.             formats.extend(tp_formats)
  69.             subtitles = self._merge_subtitles(subtitles, tp_subtitles)
  70.         if last_e and not formats:
  71.             raise last_e
  72.         self._sort_formats(formats)
  73.         return {
  74.             'id': video_id,
  75.             'formats': formats,
  76.             'subtitles': subtitles,
  77.         }
  79.     def _extract_aetn_info(self, domain, filter_key, filter_value, url):
  80.         requestor_id, brand = self._DOMAIN_MAP[domain]
  81.         result = self._download_json(
  82.             'https://feeds.video.aetnd.com/api/v2/%s/videos' % brand,
  83.             filter_value, query={'filter[%s]' % filter_key: filter_value})
  84.         result = traverse_obj(
  85.             result, ('results',
  86.                      lambda k, v: k == 0 and v[filter_key] == filter_value),
  87.             get_all=False)
  88.         if not result:
  89.             raise ExtractorError('Show not found in A&E feed (too new?)', expected=True,
  90.                                  video_id=remove_start(filter_value, '/'))
  91.         title = result['title']
  92.         video_id = result['id']
  93.         media_url = result['publicUrl']
  94.         theplatform_metadata = self._download_theplatform_metadata(self._search_regex(
  95.             r'https?://link\.theplatform\.com/s/([^?]+)', media_url, 'theplatform_path'), video_id)
  96.         info = self._parse_theplatform_metadata(theplatform_metadata)
  97.         auth = None
  98.         if theplatform_metadata.get('AETN$isBehindWall'):
  99.             resource = self._get_mvpd_resource(
  100.                 requestor_id, theplatform_metadata['title'],
  101.                 theplatform_metadata.get('AETN$PPL_pplProgramId') or theplatform_metadata.get('AETN$PPL_pplProgramId_OLD'),
  102.                 theplatform_metadata['ratings'][0]['rating'])
  103.             auth = self._extract_mvpd_auth(
  104.                 url, video_id, requestor_id, resource)
  105.         info.update(self._extract_aen_smil(media_url, video_id, auth))
  106.         info.update({
  107.             'title': title,
  108.             'series': result.get('seriesName'),
  109.             'season_number': int_or_none(result.get('tvSeasonNumber')),
  110.             'episode_number': int_or_none(result.get('tvSeasonEpisodeNumber')),
  111.         })
  112.         return info
  115. class AENetworksIE(AENetworksBaseIE):
  116.     IE_NAME = 'aenetworks'
  117.     IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network and History Vault'
  118.     _VALID_URL = AENetworksBaseIE._BASE_URL_REGEX + r'''(?P<id>
  119.         shows/[^/]+/season-\d+/episode-\d+|
  120.         (?:
  121.             (?:movie|special)s/[^/]+|
  122.             (?:shows/[^/]+/)?videos
  123.         )/[^/?#&]+
  124.     )'''
  125.     _TESTS = [{
  126.         'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
  127.         'info_dict': {
  128.             'id': '22253814',
  129.             'ext': 'mp4',
  130.             'title': 'Winter is Coming',
  131.             'description': 'md5:641f424b7a19d8e24f26dea22cf59d74',
  132.             'timestamp': 1338306241,
  133.             'upload_date': '20120529',
  134.             'uploader': 'AENE-NEW',
  135.         },
  136.         'params': {
  137.             # m3u8 download
  138.             'skip_download': True,
  139.         },
  140.         'add_ie': ['ThePlatform'],
  141.         'skip': 'Geo-restricted - This content is not available in your location.'
  142.     }, {
  143.         'url': 'http://www.aetv.com/shows/duck-dynasty/season-9/episode-1',
  144.         'info_dict': {
  145.             'id': '600587331957',
  146.             'ext': 'mp4',
  147.             'title': 'Inlawful Entry',
  148.             'description': 'md5:57c12115a2b384d883fe64ca50529e08',
  149.             'timestamp': 1452634428,
  150.             'upload_date': '20160112',
  151.             'uploader': 'AENE-NEW',
  152.         },
  153.         'params': {
  154.             # m3u8 download
  155.             'skip_download': True,
  156.         },
  157.         'add_ie': ['ThePlatform'],
  158.         'skip': 'This video is only available for users of participating TV providers.',
  159.     }, {
  160.         'url': 'http://www.fyi.tv/shows/tiny-house-nation/season-1/episode-8',
  161.         'only_matching': True
  162.     }, {
  163.         'url': 'http://www.mylifetime.com/shows/project-runway-junior/season-1/episode-6',
  164.         'only_matching': True
  165.     }, {
  166.         'url': 'http://www.mylifetime.com/movies/center-stage-on-pointe/full-movie',
  167.         'only_matching': True
  168.     }, {
  169.         'url': 'https://watch.lifetimemovieclub.com/movies/10-year-reunion/full-movie',
  170.         'only_matching': True
  171.     }, {
  172.         'url': 'http://www.history.com/specials/sniper-into-the-kill-zone/full-special',
  173.         'only_matching': True
  174.     }, {
  175.         'url': 'https://www.aetv.com/specials/hunting-jonbenets-killer-the-untold-story/preview-hunting-jonbenets-killer-the-untold-story',
  176.         'only_matching': True
  177.     }, {
  178.         'url': 'http://www.history.com/videos/history-of-valentines-day',
  179.         'only_matching': True
  180.     }, {
  181.         'url': 'https://play.aetv.com/shows/duck-dynasty/videos/best-of-duck-dynasty-getting-quack-in-shape',
  182.         'only_matching': True
  183.     }]
  185.     def _real_extract(self, url):
  186.         domain, canonical = re.match(self._VALID_URL, url).groups()
  187.         return self._extract_aetn_info(domain, 'canonical', '/' + canonical, url)
  190. class AENetworksListBaseIE(AENetworksBaseIE):
  191.     def _call_api(self, resource, slug, brand, fields):
  192.         return self._download_json(
  193.             'https://yoga.appsvcs.aetnd.com/graphql',
  194.             slug, query={'brand': brand}, data=urlencode_postdata({
  195.                 'query': '''{
  196.   %s(slug: "%s") {
  197.     %s
  198.   }
  199. }''' % (resource, slug, fields),
  200.             }))['data'][resource]
  202.     def _real_extract(self, url):
  203.         domain, slug = re.match(self._VALID_URL, url).groups()
  204.         _, brand = self._DOMAIN_MAP[domain]
  205.         playlist = self._call_api(self._RESOURCE, slug, brand, self._FIELDS)
  206.         base_url = 'http://watch.%s' % domain
  208.         entries = []
  209.         for item in (playlist.get(self._ITEMS_KEY) or []):
  210.             doc = self._get_doc(item)
  211.             canonical = doc.get('canonical')
  212.             if not canonical:
  213.                 continue
  214.             entries.append(self.url_result(
  215.                 base_url + canonical, AENetworksIE.ie_key(), doc.get('id')))
  217.         description = None
  218.         if self._PLAYLIST_DESCRIPTION_KEY:
  219.             description = playlist.get(self._PLAYLIST_DESCRIPTION_KEY)
  221.         return self.playlist_result(
  222.             entries, playlist.get('id'),
  223.             playlist.get(self._PLAYLIST_TITLE_KEY), description)
  226. class AENetworksCollectionIE(AENetworksListBaseIE):
  227.     IE_NAME = 'aenetworks:collection'
  228.     _VALID_URL = AENetworksBaseIE._BASE_URL_REGEX + r'(?:[^/]+/)*(?:list|collections)/(?P<id>[^/?#&]+)/?(?:[?#&]|$)'
  229.     _TESTS = [{
  230.         'url': 'https://watch.historyvault.com/list/america-the-story-of-us',
  231.         'info_dict': {
  232.             'id': '282',
  233.             'title': 'America The Story of Us',
  234.         },
  235.         'playlist_mincount': 12,
  236.     }, {
  237.         'url': 'https://watch.historyvault.com/shows/america-the-story-of-us-2/season-1/list/america-the-story-of-us',
  238.         'only_matching': True
  239.     }, {
  240.         'url': 'https://www.historyvault.com/collections/mysteryquest',
  241.         'only_matching': True
  242.     }]
  243.     _RESOURCE = 'list'
  244.     _ITEMS_KEY = 'items'
  245.     _PLAYLIST_TITLE_KEY = 'display_title'
  246.     _PLAYLIST_DESCRIPTION_KEY = None
  247.     _FIELDS = '''id
  248.     display_title
  249.     items {
  250.       ... on ListVideoItem {
  251.         doc {
  252.           canonical
  253.           id
  254.         }
  255.       }
  256.     }'''
  258.     def _get_doc(self, item):
  259.         return item.get('doc') or {}
  262. class AENetworksShowIE(AENetworksListBaseIE):
  263.     IE_NAME = 'aenetworks:show'
  264.     _VALID_URL = AENetworksBaseIE._BASE_URL_REGEX + r'shows/(?P<id>[^/?#&]+)/?(?:[?#&]|$)'
  265.     _TESTS = [{
  266.         'url': 'http://www.history.com/shows/ancient-aliens',
  267.         'info_dict': {
  268.             'id': 'SERIES1574',
  269.             'title': 'Ancient Aliens',
  270.             'description': 'md5:3f6d74daf2672ff3ae29ed732e37ea7f',
  271.         },
  272.         'playlist_mincount': 150,
  273.     }]
  274.     _RESOURCE = 'series'
  275.     _ITEMS_KEY = 'episodes'
  276.     _PLAYLIST_TITLE_KEY = 'title'
  277.     _PLAYLIST_DESCRIPTION_KEY = 'description'
  278.     _FIELDS = '''description
  279.     id
  280.     title
  281.     episodes {
  282.       canonical
  283.       id
  284.     }'''
  286.     def _get_doc(self, item):
  287.         return item
  290. class HistoryTopicIE(AENetworksBaseIE):
  291.     IE_NAME = 'history:topic'
  292.     IE_DESC = 'History.com Topic'
  293.     _VALID_URL = r'https?://(?:www\.)?history\.com/topics/[^/]+/(?P<id>[\w+-]+?)-video'
  294.     _TESTS = [{
  295.         'url': 'https://www.history.com/topics/valentines-day/history-of-valentines-day-video',
  296.         'info_dict': {
  297.             'id': '40700995724',
  298.             'ext': 'mp4',
  299.             'title': "History of Valentine’s Day",
  300.             'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7',
  301.             'timestamp': 1375819729,
  302.             'upload_date': '20130806',
  303.             'uploader': 'AENE-NEW',
  304.         },
  305.         'params': {
  306.             # m3u8 download
  307.             'skip_download': True,
  308.         },
  309.         'add_ie': ['ThePlatform'],
  310.     }]
  312.     def _real_extract(self, url):
  313.         display_id = self._match_id(url)
  314.         return self.url_result(
  315.             'http://www.history.com/videos/' + display_id,
  316.             AENetworksIE.ie_key())
  319. class HistoryPlayerIE(AENetworksBaseIE):
  320.     IE_NAME = 'history:player'
  321.     _VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:history|biography)\.com)/player/(?P<id>\d+)'
  322.     _TESTS = []
  324.     def _real_extract(self, url):
  325.         domain, video_id = re.match(self._VALID_URL, url).groups()
  326.         return self._extract_aetn_info(domain, 'id', video_id, url)
  329. class BiographyIE(AENetworksBaseIE):
  330.     _VALID_URL = r'https?://(?:www\.)?biography\.com/video/(?P<id>[^/?#&]+)'
  331.     _TESTS = [{
  332.         'url': 'https://www.biography.com/video/vincent-van-gogh-full-episode-2075049808',
  333.         'info_dict': {
  334.             'id': '30322987',
  335.             'ext': 'mp4',
  336.             'title': 'Vincent Van Gogh - Full Episode',
  337.             'description': 'A full biography about the most influential 20th century painter, Vincent Van Gogh.',
  338.             'timestamp': 1311970571,
  339.             'upload_date': '20110729',
  340.             'uploader': 'AENE-NEW',
  341.         },
  342.         'params': {
  343.             # m3u8 download
  344.             'skip_download': True,
  345.         },
  346.         'add_ie': ['ThePlatform'],
  347.     }]
  349.     def _real_extract(self, url):
  350.         display_id = self._match_id(url)
  351.         webpage = self._download_webpage(url, display_id)
  352.         player_url = self._search_regex(
  353.             r'<phoenix-iframe[^>]+src="(%s)' % HistoryPlayerIE._VALID_URL,
  354.             webpage, 'player URL')
  355.         return self.url_result(player_url, HistoryPlayerIE.ie_key())