yt_dlp/extractor/shemaroome.py

   1 from .common import InfoExtractor
   2 from ..aes import aes_cbc_decrypt, unpad_pkcs7
   3 from ..compat import (
   4     compat_b64decode,
   5 )
   6 from ..utils import (
   7     ExtractorError,
   8     bytes_to_intlist,
   9     intlist_to_bytes,
  10     unified_strdate,
  11 )
  12
  13
  14 class ShemarooMeIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?shemaroome\.com/(?:movies|shows)/(?P<id>[^?#]+)'
  16     _TESTS = [{
  17         'url': 'https://www.shemaroome.com/movies/dil-hai-tumhaara',
  18         'info_dict': {
  19             'id': 'dil-hai-tumhaara',
  20             'ext': 'mp4',
  21             'title': 'Dil Hai Tumhaara',
  22             'release_date': '20020906',
  23             'thumbnail': r're:^https?://.*\.jpg$',
  24             'description': 'md5:2782c4127807103cf5a6ae2ca33645ce',
  25         },
  26         'params': {
  27             'skip_download': True
  28         }
  29     }, {
  30         'url': 'https://www.shemaroome.com/shows/jurm-aur-jazbaat/laalach',
  31         'info_dict': {
  32             'id': 'jurm-aur-jazbaat_laalach',
  33             'ext': 'mp4',
  34             'title': 'Laalach',
  35             'description': 'md5:92b79c2dcb539b0ab53f9fa5a048f53c',
  36             'thumbnail': r're:^https?://.*\.jpg$',
  37             'release_date': '20210507',
  38         },
  39         'params': {
  40             'skip_download': True
  41         },
  42         'skip': 'Premium videos cannot be downloaded yet.'
  43     }, {
  44         'url': 'https://www.shemaroome.com/shows/jai-jai-jai-bajrang-bali/jai-jai-jai-bajrang-bali-episode-99',
  45         'info_dict': {
  46             'id': 'jai-jai-jai-bajrang-bali_jai-jai-jai-bajrang-bali-episode-99',
  47             'ext': 'mp4',
  48             'title': 'Jai Jai Jai Bajrang Bali Episode 99',
  49             'description': 'md5:850d127a18ee3f9529d7fbde2f49910d',
  50             'thumbnail': r're:^https?://.*\.jpg$',
  51             'release_date': '20110101',
  52         },
  53         'params': {
  54             'skip_download': True
  55         }
  56     }]
  57
  58     def _real_extract(self, url):
  59         video_id = self._match_id(url).replace('/', '_')
  60         webpage = self._download_webpage(url, video_id)
  61         title = self._search_regex(r'id=\"ma_title\" value=\"([^\"]+)', webpage, 'title')
  62         thumbnail = self._og_search_thumbnail(webpage)
  63         content_def = self._search_regex(r'id=\"content_definition\" value=\"([^\"]+)', webpage, 'content_def')
  64         catalog_id = self._search_regex(r'id=\"catalog_id\" value=\"([^\"]+)', webpage, 'catalog_id')
  65         item_category = self._search_regex(r'id=\"item_category\" value=\"([^\"]+)', webpage, 'item_category')
  66         content_id = self._search_regex(r'id=\"content_id\" value=\"([^\"]+)', webpage, 'content_id')
  67
  68         data = f'catalog_id={catalog_id}&content_id={content_id}&category={item_category}&content_def={content_def}'
  69         data_json = self._download_json('https://www.shemaroome.com/users/user_all_lists', video_id, data=data.encode())
  70         if not data_json.get('status'):
  71             raise ExtractorError('Premium videos cannot be downloaded yet.', expected=True)
  72         url_data = bytes_to_intlist(compat_b64decode(data_json['new_play_url']))
  73         key = bytes_to_intlist(compat_b64decode(data_json['key']))
  74         iv = [0] * 16
  75         m3u8_url = unpad_pkcs7(intlist_to_bytes(aes_cbc_decrypt(url_data, key, iv))).decode('ascii')
  76         headers = {'stream_key': data_json['stream_key']}
  77         formats, m3u8_subs = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, fatal=False, headers=headers)
  78         for fmt in formats:
  79             fmt['http_headers'] = headers
  80
  81         release_date = self._html_search_regex(
  82             (r'itemprop="uploadDate">\s*([\d-]+)', r'id="release_date" value="([\d-]+)'),
  83             webpage, 'release date', fatal=False)
  84
  85         subtitles = {}
  86         sub_url = data_json.get('subtitle')
  87         if sub_url:
  88             subtitles.setdefault('EN', []).append({
  89                 'url': self._proto_relative_url(sub_url),
  90             })
  91         subtitles = self._merge_subtitles(subtitles, m3u8_subs)
  92         description = self._html_search_regex(r'(?s)>Synopsis(</.+?)</', webpage, 'description', fatal=False)
  93
  94         return {
  95             'id': video_id,
  96             'formats': formats,
  97             'title': title,
  98             'thumbnail': thumbnail,
  99             'release_date': unified_strdate(release_date),
 100             'description': description,
 101             'subtitles': subtitles,
 102         }