yt_dlp/extractor/shemaroome.py

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