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 )
  12 from ..compat import (
  13     compat_urlparse,
  14 )
  15
  16
  17 class AENetworksBaseIE(InfoExtractor):
  18     def theplatform_url_result(self, theplatform_url, video_id, query):
  19         return {
  20             '_type': 'url_transparent',
  21             'id': video_id,
  22             'url': smuggle_url(
  23                 update_url_query(theplatform_url, query),
  24                 {
  25                     'sig': {
  26                         'key': 'crazyjava',
  27                         'secret': 's3cr3t'
  28                     },
  29                     'force_smil_url': True
  30                 }),
  31             'ie_key': 'ThePlatform',
  32         }
  33
  34
  35 class AENetworksIE(AENetworksBaseIE):
  36     IE_NAME = 'aenetworks'
  37     IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network'
  38     _VALID_URL = r'https?://(?:www\.)?(?:(?:history|aetv|mylifetime)\.com|fyi\.tv)/shows/(?P<id>[^/]+(?:/[^/]+){0,2})'
  39     _TESTS = [{
  40         'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
  41         'md5': '8ff93eb073449f151d6b90c0ae1ef0c7',
  42         'info_dict': {
  43             'id': '22253814',
  44             'ext': 'mp4',
  45             'title': 'Winter Is Coming',
  46             'description': 'md5:641f424b7a19d8e24f26dea22cf59d74',
  47             'timestamp': 1338306241,
  48             'upload_date': '20120529',
  49             'uploader': 'AENE-NEW',
  50         },
  51         'add_ie': ['ThePlatform'],
  52     }, {
  53         'url': 'http://www.history.com/shows/ancient-aliens/season-1',
  54         'info_dict': {
  55             'id': '71889446852',
  56         },
  57         'playlist_mincount': 5,
  58     }, {
  59         'url': 'http://www.mylifetime.com/shows/atlanta-plastic',
  60         'info_dict': {
  61             'id': 'SERIES4317',
  62             'title': 'Atlanta Plastic',
  63         },
  64         'playlist_mincount': 2,
  65     }, {
  66         'url': 'http://www.aetv.com/shows/duck-dynasty/season-9/episode-1',
  67         'only_matching': True
  68     }, {
  69         'url': 'http://www.fyi.tv/shows/tiny-house-nation/season-1/episode-8',
  70         'only_matching': True
  71     }, {
  72         'url': 'http://www.mylifetime.com/shows/project-runway-junior/season-1/episode-6',
  73         'only_matching': True
  74     }]
  75
  76     def _real_extract(self, url):
  77         display_id = self._match_id(url)
  78         webpage = self._download_webpage(url, display_id)
  79         url_parts = display_id.split('/')
  80         url_parts_len = len(url_parts)
  81         if url_parts_len == 1:
  82             entries = []
  83             for season_url_path in re.findall(r'(?s)<li[^>]+data-href="(/shows/%s/season-\d+)"' % url_parts[0], webpage):
  84                 entries.append(self.url_result(
  85                     compat_urlparse.urljoin(url, season_url_path), 'AENetworks'))
  86             return self.playlist_result(
  87                 entries, self._html_search_meta('aetn:SeriesId', webpage),
  88                 self._html_search_meta('aetn:SeriesTitle', webpage))
  89         elif url_parts_len == 2:
  90             entries = []
  91             for episode_item in re.findall(r'(?s)<div[^>]+class="[^"]*episode-item[^"]*"[^>]*>', webpage):
  92                 episode_attributes = extract_attributes(episode_item)
  93                 episode_url = compat_urlparse.urljoin(
  94                     url, episode_attributes['data-canonical'])
  95                 entries.append(self.url_result(
  96                     episode_url, 'AENetworks',
  97                     episode_attributes['data-videoid']))
  98             return self.playlist_result(
  99                 entries, self._html_search_meta('aetn:SeasonId', webpage))
 100         else:
 101             video_id = self._html_search_meta('aetn:VideoID', webpage)
 102             media_url = self._search_regex(
 103                 r"media_url\s*=\s*'([^']+)'", webpage, 'video url')
 104
 105             info = self._search_json_ld(webpage, video_id, fatal=False)
 106             info.update(self.theplatform_url_result(
 107                 media_url, video_id, {
 108                     'mbr': 'true',
 109                     'assetTypes': 'medium_video_s3'
 110                 }))
 111             return info
 112
 113
 114 class HistoryTopicIE(AENetworksBaseIE):
 115     IE_NAME = 'history:topic'
 116     IE_DESC = 'History.com Topic'
 117     _VALID_URL = r'https?://(?:www\.)?history\.com/topics/(?:[^/]+/)?(?P<topic_id>[^/]+)/videos(?:/(?P<display_id>[^/?#]+))?'
 118     _TESTS = [{
 119         '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',
 120         'info_dict': {
 121             'id': '40700995724',
 122             'ext': 'mp4',
 123             'title': "Bet You Didn't Know: Valentine's Day",
 124             'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7',
 125             'timestamp': 1375819729,
 126             'upload_date': '20130806',
 127             'uploader': 'AENE-NEW',
 128         },
 129         'params': {
 130             # m3u8 download
 131             'skip_download': True,
 132         },
 133         'add_ie': ['ThePlatform'],
 134     }, {
 135         'url': 'http://www.history.com/topics/world-war-i/world-war-i-history/videos',
 136         'info_dict':
 137         {
 138             'id': 'world-war-i-history',
 139         },
 140         'playlist_mincount': 24,
 141     }, {
 142         'url': 'http://www.history.com/topics/world-war-i-history/videos',
 143         'only_matching': True,
 144     }]
 145
 146     def _real_extract(self, url):
 147         topic_id, display_id = re.match(self._VALID_URL, url).groups()
 148         if display_id:
 149             webpage = self._download_webpage(url, display_id)
 150             release_url, video_id = re.search(r"_videoPlayer.play\('([^']+)'\s*,\s*'[^']+'\s*,\s*'(\d+)'\)", webpage).groups()
 151             release_url = unescapeHTML(release_url)
 152
 153             return self.theplatform_url_result(
 154                 release_url, video_id, {
 155                     'mbr': 'true',
 156                     'switch': 'hls'
 157                 })
 158         else:
 159             webpage = self._download_webpage(url, topic_id)
 160             entries = []
 161             for episode_item in re.findall(r'<a.+?data-release-url="[^"]+"[^>]*>', webpage):
 162                 video_attributes = extract_attributes(episode_item)
 163                 entries.append(self.theplatform_url_result(
 164                     video_attributes['data-release-url'], video_attributes['data-id'], {
 165                         'mbr': 'true',
 166                         'switch': 'hls'
 167                     }))
 168             return self.playlist_result(entries, topic_id)