_ Git - youtube-dl/blob - youtube_dl/extractor/aenetworks.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   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(InfoExtractor):
  19     def theplatform_url_result(self, theplatform_url, video_id, query):
  20         return {
  21             '_type': 'url_transparent',
  22             'id': video_id,
  23             'url': smuggle_url(
  24                 update_url_query(theplatform_url, query),
  25                 {
  26                     'sig': {
  27                         'key': 'crazyjava',
  28                         'secret': 's3cr3t'
  29                     },
  30                     'force_smil_url': True
  31                 }),
  32             'ie_key': 'ThePlatform',
  33         }
  34
  35
  36 class AENetworksIE(AENetworksBaseIE):
  37     IE_NAME = 'aenetworks'
  38     IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network'
  39     _VALID_URL = r'https?://(?:www\.)?(?:(?:history|aetv|mylifetime)\.com|fyi\.tv)/shows/(?P<id>[^/]+(?:/[^/]+){0,2})'
  40     _TESTS = [{
  41         'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
  42         'md5': '8ff93eb073449f151d6b90c0ae1ef0c7',
  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
  77     def _real_extract(self, url):
  78         display_id = self._match_id(url)
  79         webpage = self._download_webpage(url, display_id)
  80         url_parts = display_id.split('/')
  81         url_parts_len = len(url_parts)
  82         if url_parts_len == 1:
  83             entries = []
  84             for season_url_path in re.findall(r'(?s)<li[^>]+data-href="(/shows/%s/season-\d+)"' % url_parts[0], webpage):
  85                 entries.append(self.url_result(
  86                     compat_urlparse.urljoin(url, season_url_path), 'AENetworks'))
  87             return self.playlist_result(
  88                 entries, self._html_search_meta('aetn:SeriesId', webpage),
  89                 self._html_search_meta('aetn:SeriesTitle', webpage))
  90         elif url_parts_len == 2:
  91             entries = []
  92             for episode_item in re.findall(r'(?s)<div[^>]+class="[^"]*episode-item[^"]*"[^>]*>', webpage):
  93                 episode_attributes = extract_attributes(episode_item)
  94                 episode_url = compat_urlparse.urljoin(
  95                     url, episode_attributes['data-canonical'])
  96                 entries.append(self.url_result(
  97                     episode_url, 'AENetworks',
  98                     episode_attributes['data-videoid']))
  99             return self.playlist_result(
 100                 entries, self._html_search_meta('aetn:SeasonId', webpage))
 101         else:
 102             video_id = self._html_search_meta('aetn:VideoID', webpage)
 103             media_url = self._search_regex(
 104                 r"media_url\s*=\s*'([^']+)'", webpage, 'video url')
 105
 106             info = self._search_json_ld(webpage, video_id, fatal=False)
 107             info.update(self.theplatform_url_result(
 108                 media_url, video_id, {
 109                     'mbr': 'true',
 110                     'assetTypes': 'medium_video_s3'
 111                 }))
 112             return info
 113
 114
 115 class HistoryTopicIE(AENetworksBaseIE):
 116     IE_NAME = 'history:topic'
 117     IE_DESC = 'History.com Topic'
 118     _VALID_URL = r'https?://(?:www\.)?history\.com/topics/(?:[^/]+/)?(?P<topic_id>[^/]+)/videos(?:/(?P<display_id>[^/?#]+))?'
 119     _TESTS = [{
 120         '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',
 121         'info_dict': {
 122             'id': '40700995724',
 123             'ext': 'mp4',
 124             'title': "Bet You Didn't Know: Valentine's Day",
 125             'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7',
 126             'timestamp': 1375819729,
 127             'upload_date': '20130806',
 128             'uploader': 'AENE-NEW',
 129         },
 130         'params': {
 131             # m3u8 download
 132             'skip_download': True,
 133         },
 134         'add_ie': ['ThePlatform'],
 135     }, {
 136         'url': 'http://www.history.com/topics/world-war-i/world-war-i-history/videos',
 137         'info_dict':
 138         {
 139             'id': 'world-war-i-history',
 140             'title': 'World War I History',
 141         },
 142         'playlist_mincount': 24,
 143     }, {
 144         'url': 'http://www.history.com/topics/world-war-i-history/videos',
 145         'only_matching': True,
 146     }]
 147
 148     def _real_extract(self, url):
 149         topic_id, display_id = re.match(self._VALID_URL, url).groups()
 150         if display_id:
 151             webpage = self._download_webpage(url, display_id)
 152             release_url, video_id = re.search(r"_videoPlayer.play\('([^']+)'\s*,\s*'[^']+'\s*,\s*'(\d+)'\)", webpage).groups()
 153             release_url = unescapeHTML(release_url)
 154
 155             return self.theplatform_url_result(
 156                 release_url, video_id, {
 157                     'mbr': 'true',
 158                     'switch': 'hls'
 159                 })
 160         else:
 161             webpage = self._download_webpage(url, topic_id)
 162             entries = []
 163             for episode_item in re.findall(r'<a.+?data-release-url="[^"]+"[^>]*>', webpage):
 164                 video_attributes = extract_attributes(episode_item)
 165                 entries.append(self.theplatform_url_result(
 166                     video_attributes['data-release-url'], video_attributes['data-id'], {
 167                         'mbr': 'true',
 168                         'switch': 'hls'
 169                     }))
 170             return self.playlist_result(entries, topic_id, get_element_by_attribute('class', 'show-title', webpage))