yt_dlp/extractor/epicon.py

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