yt_dlp/extractor/epicon.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import ExtractorError
   5
   6
   7 class EpiconIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?epicon\.in/(?:documentaries|movies|tv-shows/[^/?#]+/[^/?#]+)/(?P<id>[^/?#]+)'
   9     _TESTS = [{
  10         'url': 'https://www.epicon.in/documentaries/air-battle-of-srinagar',
  11         'info_dict': {
  12             'id': 'air-battle-of-srinagar',
  13             'ext': 'mp4',
  14             'title': 'Air Battle of Srinagar',
  15             'description': 'md5:c4de2013af9bc05ae4392e4115d518d7',
  16             'thumbnail': r're:^https?://.*\.jpg$',
  17         },
  18     }, {
  19         'url': 'https://www.epicon.in/movies/krit',
  20         'info_dict': {
  21             'id': 'krit',
  22             'ext': 'mp4',
  23             'title': 'Krit',
  24             'description': 'md5:c12b35dad915d48ccff7f013c79bab4a',
  25             'thumbnail': r're:^https?://.*\.jpg$',
  26         },
  27     }, {
  28         'url': 'https://www.epicon.in/tv-shows/paapnaashini-ganga/season-1/vardaan',
  29         'info_dict': {
  30             'id': 'vardaan',
  31             'ext': 'mp4',
  32             'title': 'Paapnaashini Ganga - Season 1 - Ep 1 - VARDAAN',
  33             'description': 'md5:f517058c3d0402398eefa6242f4dd6ae',
  34             'thumbnail': r're:^https?://.*\.jpg$',
  35         },
  36     }, {
  37         'url': 'https://www.epicon.in/movies/jayadev',
  38         'info_dict': {
  39             'id': 'jayadev',
  40             'ext': 'mp4',
  41             'title': 'Jayadev',
  42             'description': 'md5:09e349eecd8e585a3b6466904f19df6c',
  43             'thumbnail': r're:^https?://.*\.jpg$',
  44         },
  45     }]
  46
  47     def _real_extract(self, url):
  48         video_id = self._match_id(url)
  49         webpage = self._download_webpage(url, video_id)
  50         cid = self._search_regex(r'class=\"mylist-icon\ iconclick\"\ id=\"(\d+)', webpage, 'cid')
  51         headers = {'content-type': 'application/x-www-form-urlencoded; charset=UTF-8'}
  52         data = f'cid={cid}&action=st&type=video'.encode()
  53         data_json = self._parse_json(
  54             self._download_json('https://www.epicon.in/ajaxplayer/', video_id, headers=headers, data=data), video_id)
  55
  56         if not data_json['success']:
  57             raise ExtractorError(data_json['message'], expected=True)
  58
  59         title = self._search_regex(r'setplaytitle=\"([^\"]+)', webpage, 'title')
  60         description = self._og_search_description(webpage) or None
  61         thumbnail = self._og_search_thumbnail(webpage) or None
  62         formats = self._extract_m3u8_formats(data_json['url']['video_url'], video_id)
  63
  64         subtitles = {}
  65         for subtitle in data_json.get('subtitles', []):
  66             sub_url = subtitle.get('file')
  67             if not sub_url:
  68                 continue
  69             subtitles.setdefault(subtitle.get('lang', 'English'), []).append({
  70                 'url': self._proto_relative_url(sub_url),
  71             })
  72
  73         return {
  74             'id': video_id,
  75             'formats': formats,
  76             'title': title,
  77             'description': description,
  78             'thumbnail': thumbnail,
  79             'subtitles': subtitles,
  80         }
  81
  82
  83 class EpiconSeriesIE(InfoExtractor):
  84     _VALID_URL = r'(?!.*season)https?://(?:www\.)?epicon\.in/tv-shows/(?P<id>[^/?#]+)'
  85     _TESTS = [{
  86         'url': 'https://www.epicon.in/tv-shows/1-of-something',
  87         'playlist_mincount': 5,
  88         'info_dict': {
  89             'id': '1-of-something',
  90         },
  91     }, {
  92         'url': 'https://www.epicon.in/tv-shows/eco-india-english',
  93         'playlist_mincount': 76,
  94         'info_dict': {
  95             'id': 'eco-india-english',
  96         },
  97     }, {
  98         'url': 'https://www.epicon.in/tv-shows/s/',
  99         'playlist_mincount': 25,
 100         'info_dict': {
 101             'id': 's',
 102         },
 103     }, {
 104         'url': 'https://www.epicon.in/tv-shows/ekaant',
 105         'playlist_mincount': 38,
 106         'info_dict': {
 107             'id': 'ekaant',
 108         },
 109     }]
 110
 111     def _real_extract(self, url):
 112         playlist_id = self._match_id(url)
 113         webpage = self._download_webpage(url, playlist_id)
 114         episodes = re.findall(rf'ct-tray-url=\"(tv-shows/{playlist_id}/[^\"]+)', webpage)
 115         entries = [self.url_result(f'https://www.epicon.in/{episode}', EpiconIE) for episode in episodes]
 116         return self.playlist_result(entries, playlist_id=playlist_id)