_ 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<show_path>[^/]+(?:/[^/]+){0,2})|movies/(?P<movie_display_id>[^/]+)/full-movie)'
  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         'url': 'http://www.mylifetime.com/movies/center-stage-on-pointe/full-movie',
  77         'only_matching': True
  78     }]
  79
  80     def _real_extract(self, url):
  81         show_path, movie_display_id = re.match(self._VALID_URL, url).groups()
  82         display_id = show_path or movie_display_id
  83         webpage = self._download_webpage(url, display_id)
  84         if show_path:
  85             url_parts = show_path.split('/')
  86             url_parts_len = len(url_parts)
  87             if url_parts_len == 1:
  88                 entries = []
  89                 for season_url_path in re.findall(r'(?s)<li[^>]+data-href="(/shows/%s/season-\d+)"' % url_parts[0], webpage):
  90                     entries.append(self.url_result(
  91                         compat_urlparse.urljoin(url, season_url_path), 'AENetworks'))
  92                 return self.playlist_result(
  93                     entries, self._html_search_meta('aetn:SeriesId', webpage),
  94                     self._html_search_meta('aetn:SeriesTitle', webpage))
  95             elif url_parts_len == 2:
  96                 entries = []
  97                 for episode_item in re.findall(r'(?s)<div[^>]+class="[^"]*episode-item[^"]*"[^>]*>', webpage):
  98                     episode_attributes = extract_attributes(episode_item)
  99                     episode_url = compat_urlparse.urljoin(
 100                         url, episode_attributes['data-canonical'])
 101                     entries.append(self.url_result(
 102                         episode_url, 'AENetworks',
 103                         episode_attributes['data-videoid']))
 104                 return self.playlist_result(
 105                     entries, self._html_search_meta('aetn:SeasonId', webpage))
 106         video_id = self._html_search_meta('aetn:VideoID', webpage)
 107         media_url = self._search_regex(
 108             r"media_url\s*=\s*'([^']+)'", webpage, 'video url')
 109
 110         info = self._search_json_ld(webpage, video_id, fatal=False)
 111         info.update(self.theplatform_url_result(
 112             media_url, video_id, {
 113                 'mbr': 'true',
 114                 'assetTypes': 'medium_video_s3'
 115             }))
 116         return info
 117
 118
 119 class HistoryTopicIE(AENetworksBaseIE):
 120     IE_NAME = 'history:topic'
 121     IE_DESC = 'History.com Topic'
 122     _VALID_URL = r'https?://(?:www\.)?history\.com/topics/(?:[^/]+/)?(?P<topic_id>[^/]+)/videos(?:/(?P<video_display_id>[^/?#]+))?'
 123     _TESTS = [{
 124         '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',
 125         'info_dict': {
 126             'id': '40700995724',
 127             'ext': 'mp4',
 128             'title': "Bet You Didn't Know: Valentine's Day",
 129             'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7',
 130             'timestamp': 1375819729,
 131             'upload_date': '20130806',
 132             'uploader': 'AENE-NEW',
 133         },
 134         'params': {
 135             # m3u8 download
 136             'skip_download': True,
 137         },
 138         'add_ie': ['ThePlatform'],
 139     }, {
 140         'url': 'http://www.history.com/topics/world-war-i/world-war-i-history/videos',
 141         'info_dict':
 142         {
 143             'id': 'world-war-i-history',
 144             'title': 'World War I History',
 145         },
 146         'playlist_mincount': 24,
 147     }, {
 148         'url': 'http://www.history.com/topics/world-war-i-history/videos',
 149         'only_matching': True,
 150     }]
 151
 152     def _real_extract(self, url):
 153         topic_id, video_display_id = re.match(self._VALID_URL, url).groups()
 154         if video_display_id:
 155             webpage = self._download_webpage(url, video_display_id)
 156             release_url, video_id = re.search(r"_videoPlayer.play\('([^']+)'\s*,\s*'[^']+'\s*,\s*'(\d+)'\)", webpage).groups()
 157             release_url = unescapeHTML(release_url)
 158
 159             return self.theplatform_url_result(
 160                 release_url, video_id, {
 161                     'mbr': 'true',
 162                     'switch': 'hls'
 163                 })
 164         else:
 165             webpage = self._download_webpage(url, topic_id)
 166             entries = []
 167             for episode_item in re.findall(r'<a.+?data-release-url="[^"]+"[^>]*>', webpage):
 168                 video_attributes = extract_attributes(episode_item)
 169                 entries.append(self.theplatform_url_result(
 170                     video_attributes['data-release-url'], video_attributes['data-id'], {
 171                         'mbr': 'true',
 172                         'switch': 'hls'
 173                     }))
 174             return self.playlist_result(entries, topic_id, get_element_by_attribute('class', 'show-title', webpage))