yt_dlp/extractor/freetv.py

   1 import itertools
   2 import re
   3
   4 from .common import InfoExtractor
   5 from ..utils import int_or_none, traverse_obj, urlencode_postdata
   6
   7
   8 class FreeTvBaseIE(InfoExtractor):
   9     def _get_api_response(self, content_id, resource_type, postdata):
  10         return self._download_json(
  11             'https://www.freetv.com/wordpress/wp-admin/admin-ajax.php',
  12             content_id, data=urlencode_postdata(postdata),
  13             note=f'Downloading {content_id} {resource_type} JSON')['data']
  14
  15
  16 class FreeTvMoviesIE(FreeTvBaseIE):
  17     _VALID_URL = r'https?://(?:www\.)?freetv\.com/peliculas/(?P<id>[^/]+)'
  18     _TESTS = [{
  19         'url': 'https://www.freetv.com/peliculas/atrapame-si-puedes/',
  20         'md5': 'dc62d5abf0514726640077cd1591aa92',
  21         'info_dict': {
  22             'id': '428021',
  23             'title': 'Atrápame Si Puedes',
  24             'description': 'md5:ca63bc00898aeb2f64ec87c6d3a5b982',
  25             'ext': 'mp4',
  26         },
  27     }, {
  28         'url': 'https://www.freetv.com/peliculas/monstruoso/',
  29         'md5': '509c15c68de41cb708d1f92d071f20aa',
  30         'info_dict': {
  31             'id': '377652',
  32             'title': 'Monstruoso',
  33             'description': 'md5:333fc19ee327b457b980e54a911ea4a3',
  34             'ext': 'mp4',
  35         },
  36     }]
  37
  38     def _extract_video(self, content_id, action='olyott_video_play'):
  39         api_response = self._get_api_response(content_id, 'video', {
  40             'action': action,
  41             'contentID': content_id,
  42         })
  43
  44         video_id, video_url = api_response['displayMeta']['contentID'], api_response['displayMeta']['streamURLVideo']
  45         formats, subtitles = self._extract_m3u8_formats_and_subtitles(video_url, video_id, 'mp4')
  46
  47         return {
  48             'id': video_id,
  49             'title': traverse_obj(api_response, ('displayMeta', 'title')),
  50             'description': traverse_obj(api_response, ('displayMeta', 'desc')),
  51             'formats': formats,
  52             'subtitles': subtitles,
  53         }
  54
  55     def _real_extract(self, url):
  56         display_id = self._match_id(url)
  57         webpage = self._download_webpage(url, display_id)
  58
  59         return self._extract_video(
  60             self._search_regex((
  61                 r'class=["\'][^>]+postid-(?P<video_id>\d+)',
  62                 r'<link[^>]+freetv.com/\?p=(?P<video_id>\d+)',
  63                 r'<div[^>]+data-params=["\'][^>]+post_id=(?P<video_id>\d+)',
  64             ), webpage, 'video id', group='video_id'))
  65
  66
  67 class FreeTvIE(FreeTvBaseIE):
  68     IE_NAME = 'freetv:series'
  69     _VALID_URL = r'https?://(?:www\.)?freetv\.com/series/(?P<id>[^/]+)'
  70     _TESTS = [{
  71         'url': 'https://www.freetv.com/series/el-detective-l/',
  72         'info_dict': {
  73             'id': 'el-detective-l',
  74             'title': 'El Detective L',
  75             'description': 'md5:f9f1143bc33e9856ecbfcbfb97a759be',
  76         },
  77         'playlist_count': 24,
  78     }, {
  79         'url': 'https://www.freetv.com/series/esmeraldas/',
  80         'info_dict': {
  81             'id': 'esmeraldas',
  82             'title': 'Esmeraldas',
  83             'description': 'md5:43d7ec45bd931d8268a4f5afaf4c77bf',
  84         },
  85         'playlist_count': 62,
  86     }, {
  87         'url': 'https://www.freetv.com/series/las-aventuras-de-leonardo/',
  88         'info_dict': {
  89             'id': 'las-aventuras-de-leonardo',
  90             'title': 'Las Aventuras de Leonardo',
  91             'description': 'md5:0c47130846c141120a382aca059288f6',
  92         },
  93         'playlist_count': 13,
  94     },
  95     ]
  96
  97     def _extract_series_season(self, season_id, series_title):
  98         episodes = self._get_api_response(season_id, 'series', {
  99             'contentID': season_id,
 100             'action': 'olyott_get_dynamic_series_content',
 101             'type': 'list',
 102             'perPage': '1000',
 103         })['1']
 104
 105         for episode in episodes:
 106             video_id = str(episode['contentID'])
 107             formats, subtitles = self._extract_m3u8_formats_and_subtitles(episode['streamURL'], video_id, 'mp4')
 108
 109             yield {
 110                 'id': video_id,
 111                 'title': episode.get('fullTitle'),
 112                 'description': episode.get('description'),
 113                 'formats': formats,
 114                 'subtitles': subtitles,
 115                 'thumbnail': episode.get('thumbnail'),
 116                 'series': series_title,
 117                 'series_id': traverse_obj(episode, ('contentMeta', 'displayMeta', 'seriesID')),
 118                 'season_id': traverse_obj(episode, ('contentMeta', 'displayMeta', 'seasonID')),
 119                 'season_number': traverse_obj(
 120                     episode, ('contentMeta', 'displayMeta', 'seasonNum'), expected_type=int_or_none),
 121                 'episode_number': traverse_obj(
 122                     episode, ('contentMeta', 'displayMeta', 'episodeNum'), expected_type=int_or_none),
 123             }
 124
 125     def _real_extract(self, url):
 126         display_id = self._match_id(url)
 127         webpage = self._download_webpage(url, display_id)
 128
 129         title = self._html_search_regex(
 130             r'<h1[^>]+class=["\']synopis[^>]>(?P<title>[^<]+)', webpage, 'title', group='title', fatal=False)
 131         description = self._html_search_regex(
 132             r'<div[^>]+class=["\']+synopis content[^>]><p>(?P<description>[^<]+)',
 133             webpage, 'description', group='description', fatal=False)
 134
 135         return self.playlist_result(
 136             itertools.chain.from_iterable(
 137                 self._extract_series_season(season_id, title)
 138                 for season_id in re.findall(r'<option[^>]+value=["\'](\d+)["\']', webpage)),
 139             display_id, title, description)