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'
  26     _VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:history|aetv|mylifetime)\.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     _DOMAIN_TO_REQUESTOR_ID = {
  67         'history.com': 'HISTORY',
  68         'aetv.com': 'AETV',
  69         'mylifetime.com': 'LIFETIME',
  70         'fyi.tv': 'FYI',
  71     }
  72
  73     def _real_extract(self, url):
  74         domain, show_path, movie_display_id = re.match(self._VALID_URL, url).groups()
  75         display_id = show_path or movie_display_id
  76         webpage = self._download_webpage(url, display_id)
  77         if show_path:
  78             url_parts = show_path.split('/')
  79             url_parts_len = len(url_parts)
  80             if url_parts_len == 1:
  81                 entries = []
  82                 for season_url_path in re.findall(r'(?s)<li[^>]+data-href="(/shows/%s/season-\d+)"' % url_parts[0], webpage):
  83                     entries.append(self.url_result(
  84                         compat_urlparse.urljoin(url, season_url_path), 'AENetworks'))
  85                 return self.playlist_result(
  86                     entries, self._html_search_meta('aetn:SeriesId', webpage),
  87                     self._html_search_meta('aetn:SeriesTitle', webpage))
  88             elif url_parts_len == 2:
  89                 entries = []
  90                 for episode_item in re.findall(r'(?s)<[^>]+class="[^"]*(?:episode|program)-item[^"]*"[^>]*>', webpage):
  91                     episode_attributes = extract_attributes(episode_item)
  92                     episode_url = compat_urlparse.urljoin(
  93                         url, episode_attributes['data-canonical'])
  94                     entries.append(self.url_result(
  95                         episode_url, 'AENetworks',
  96                         episode_attributes['data-videoid']))
  97                 return self.playlist_result(
  98                     entries, self._html_search_meta('aetn:SeasonId', webpage))
  99
 100         query = {
 101             'mbr': 'true',
 102             'assetTypes': 'high_video_s3'
 103         }
 104         video_id = self._html_search_meta('aetn:VideoID', webpage)
 105         media_url = self._search_regex(
 106             r"media_url\s*=\s*'([^']+)'", webpage, 'video url')
 107         theplatform_metadata = self._download_theplatform_metadata(self._search_regex(
 108             r'https?://link.theplatform.com/s/([^?]+)', media_url, 'theplatform_path'), video_id)
 109         info = self._parse_theplatform_metadata(theplatform_metadata)
 110         if theplatform_metadata.get('AETN$isBehindWall'):
 111             requestor_id = self._DOMAIN_TO_REQUESTOR_ID[domain]
 112             resource = self._get_mvpd_resource(
 113                 requestor_id, theplatform_metadata['title'],
 114                 theplatform_metadata.get('AETN$PPL_pplProgramId') or theplatform_metadata.get('AETN$PPL_pplProgramId_OLD'),
 115                 theplatform_metadata['ratings'][0]['rating'])
 116             query['auth'] = self._extract_mvpd_auth(
 117                 url, video_id, requestor_id, resource)
 118         info.update(self._search_json_ld(webpage, video_id, fatal=False))
 119         media_url = update_url_query(media_url, query)
 120         media_url = self._sign_url(media_url, self._THEPLATFORM_KEY, self._THEPLATFORM_SECRET)
 121         formats, subtitles = self._extract_theplatform_smil(media_url, video_id)
 122         self._sort_formats(formats)
 123         info.update({
 124             'id': video_id,
 125             'formats': formats,
 126             'subtitles': subtitles,
 127         })
 128         return info
 129
 130
 131 class HistoryTopicIE(AENetworksBaseIE):
 132     IE_NAME = 'history:topic'
 133     IE_DESC = 'History.com Topic'
 134     _VALID_URL = r'https?://(?:www\.)?history\.com/topics/(?:[^/]+/)?(?P<topic_id>[^/]+)(?:/[^/]+(?:/(?P<video_display_id>[^/?#]+))?)?'
 135     _TESTS = [{
 136         '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',
 137         'info_dict': {
 138             'id': '40700995724',
 139             'ext': 'mp4',
 140             'title': "Bet You Didn't Know: Valentine's Day",
 141             'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7',
 142             'timestamp': 1375819729,
 143             'upload_date': '20130806',
 144             'uploader': 'AENE-NEW',
 145         },
 146         'params': {
 147             # m3u8 download
 148             'skip_download': True,
 149         },
 150         'add_ie': ['ThePlatform'],
 151     }, {
 152         'url': 'http://www.history.com/topics/world-war-i/world-war-i-history/videos',
 153         'info_dict':
 154         {
 155             'id': 'world-war-i-history',
 156             'title': 'World War I History',
 157         },
 158         'playlist_mincount': 23,
 159     }, {
 160         'url': 'http://www.history.com/topics/world-war-i-history/videos',
 161         'only_matching': True,
 162     }, {
 163         'url': 'http://www.history.com/topics/world-war-i/world-war-i-history',
 164         'only_matching': True,
 165     }, {
 166         'url': 'http://www.history.com/topics/world-war-i/world-war-i-history/speeches',
 167         'only_matching': True,
 168     }]
 169
 170     def theplatform_url_result(self, theplatform_url, video_id, query):
 171         return {
 172             '_type': 'url_transparent',
 173             'id': video_id,
 174             'url': smuggle_url(
 175                 update_url_query(theplatform_url, query),
 176                 {
 177                     'sig': {
 178                         'key': self._THEPLATFORM_KEY,
 179                         'secret': self._THEPLATFORM_SECRET,
 180                     },
 181                     'force_smil_url': True
 182                 }),
 183             'ie_key': 'ThePlatform',
 184         }
 185
 186     def _real_extract(self, url):
 187         topic_id, video_display_id = re.match(self._VALID_URL, url).groups()
 188         if video_display_id:
 189             webpage = self._download_webpage(url, video_display_id)
 190             release_url, video_id = re.search(r"_videoPlayer.play\('([^']+)'\s*,\s*'[^']+'\s*,\s*'(\d+)'\)", webpage).groups()
 191             release_url = unescapeHTML(release_url)
 192
 193             return self.theplatform_url_result(
 194                 release_url, video_id, {
 195                     'mbr': 'true',
 196                     'switch': 'hls',
 197                     'assetTypes': 'high_video_ak',
 198                 })
 199         else:
 200             webpage = self._download_webpage(url, topic_id)
 201             entries = []
 202             for episode_item in re.findall(r'<a.+?data-release-url="[^"]+"[^>]*>', webpage):
 203                 video_attributes = extract_attributes(episode_item)
 204                 entries.append(self.theplatform_url_result(
 205                     video_attributes['data-release-url'], video_attributes['data-id'], {
 206                         'mbr': 'true',
 207                         'switch': 'hls',
 208                         'assetTypes': 'high_video_ak',
 209                     }))
 210             return self.playlist_result(entries, topic_id, get_element_by_attribute('class', 'show-title', webpage))