yt_dlp/extractor/shemaroome.py

   1 import base64
   2
   3 from .common import InfoExtractor
   4 from ..aes import aes_cbc_decrypt, unpad_pkcs7
   5 from ..utils import (
   6     ExtractorError,
   7     bytes_to_intlist,
   8     intlist_to_bytes,
   9     unified_strdate,
  10 )
  11
  12
  13 class ShemarooMeIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?shemaroome\.com/(?:movies|shows)/(?P<id>[^?#]+)'
  15     _TESTS = [{
  16         'url': 'https://www.shemaroome.com/movies/dil-hai-tumhaara',
  17         'info_dict': {
  18             'id': 'dil-hai-tumhaara',
  19             'ext': 'mp4',
  20             'title': 'Dil Hai Tumhaara',
  21             'release_date': '20020906',
  22             'thumbnail': r're:^https?://.*\.jpg$',
  23             'description': 'md5:2782c4127807103cf5a6ae2ca33645ce',
  24         },
  25         'params': {
  26             'skip_download': True,
  27         },
  28     }, {
  29         'url': 'https://www.shemaroome.com/shows/jurm-aur-jazbaat/laalach',
  30         'info_dict': {
  31             'id': 'jurm-aur-jazbaat_laalach',
  32             'ext': 'mp4',
  33             'title': 'Laalach',
  34             'description': 'md5:92b79c2dcb539b0ab53f9fa5a048f53c',
  35             'thumbnail': r're:^https?://.*\.jpg$',
  36             'release_date': '20210507',
  37         },
  38         'params': {
  39             'skip_download': True,
  40         },
  41         'skip': 'Premium videos cannot be downloaded yet.',
  42     }, {
  43         'url': 'https://www.shemaroome.com/shows/jai-jai-jai-bajrang-bali/jai-jai-jai-bajrang-bali-episode-99',
  44         'info_dict': {
  45             'id': 'jai-jai-jai-bajrang-bali_jai-jai-jai-bajrang-bali-episode-99',
  46             'ext': 'mp4',
  47             'title': 'Jai Jai Jai Bajrang Bali Episode 99',
  48             'description': 'md5:850d127a18ee3f9529d7fbde2f49910d',
  49             'thumbnail': r're:^https?://.*\.jpg$',
  50             'release_date': '20110101',
  51         },
  52         'params': {
  53             'skip_download': True,
  54         },
  55     }]
  56
  57     def _real_extract(self, url):
  58         video_id = self._match_id(url).replace('/', '_')
  59         webpage = self._download_webpage(url, video_id)
  60         title = self._search_regex(r'id=\"ma_title\" value=\"([^\"]+)', webpage, 'title')
  61         thumbnail = self._og_search_thumbnail(webpage)
  62         content_def = self._search_regex(r'id=\"content_definition\" value=\"([^\"]+)', webpage, 'content_def')
  63         catalog_id = self._search_regex(r'id=\"catalog_id\" value=\"([^\"]+)', webpage, 'catalog_id')
  64         item_category = self._search_regex(r'id=\"item_category\" value=\"([^\"]+)', webpage, 'item_category')
  65         content_id = self._search_regex(r'id=\"content_id\" value=\"([^\"]+)', webpage, 'content_id')
  66
  67         data = f'catalog_id={catalog_id}&content_id={content_id}&category={item_category}&content_def={content_def}'
  68         data_json = self._download_json('https://www.shemaroome.com/users/user_all_lists', video_id, data=data.encode())
  69         if not data_json.get('status'):
  70             raise ExtractorError('Premium videos cannot be downloaded yet.', expected=True)
  71         url_data = bytes_to_intlist(base64.b64decode(data_json['new_play_url']))
  72         key = bytes_to_intlist(base64.b64decode(data_json['key']))
  73         iv = [0] * 16
  74         m3u8_url = unpad_pkcs7(intlist_to_bytes(aes_cbc_decrypt(url_data, key, iv))).decode('ascii')
  75         headers = {'stream_key': data_json['stream_key']}
  76         formats, m3u8_subs = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, fatal=False, headers=headers)
  77         for fmt in formats:
  78             fmt['http_headers'] = headers
  79
  80         release_date = self._html_search_regex(
  81             (r'itemprop="uploadDate">\s*([\d-]+)', r'id="release_date" value="([\d-]+)'),
  82             webpage, 'release date', fatal=False)
  83
  84         subtitles = {}
  85         sub_url = data_json.get('subtitle')
  86         if sub_url:
  87             subtitles.setdefault('EN', []).append({
  88                 'url': self._proto_relative_url(sub_url),
  89             })
  90         subtitles = self._merge_subtitles(subtitles, m3u8_subs)
  91         description = self._html_search_regex(r'(?s)>Synopsis(</.+?)</', webpage, 'description', fatal=False)
  92
  93         return {
  94             'id': video_id,
  95             'formats': formats,
  96             'title': title,
  97             'thumbnail': thumbnail,
  98             'release_date': unified_strdate(release_date),
  99             'description': description,
 100             'subtitles': subtitles,
 101         }