yt_dlp/extractor/popcorntimes.py

   1 from .common import InfoExtractor
   2 from ..compat import compat_b64decode
   3 from ..utils import int_or_none
   4
   5
   6 class PopcorntimesIE(InfoExtractor):
   7     _VALID_URL = r'https?://popcorntimes\.tv/[^/]+/m/(?P<id>[^/]+)/(?P<display_id>[^/?#&]+)'
   8     _TEST = {
   9         'url': 'https://popcorntimes.tv/de/m/A1XCFvz/haensel-und-gretel-opera-fantasy',
  10         'md5': '93f210991ad94ba8c3485950a2453257',
  11         'info_dict': {
  12             'id': 'A1XCFvz',
  13             'display_id': 'haensel-und-gretel-opera-fantasy',
  14             'ext': 'mp4',
  15             'title': 'Hänsel und Gretel',
  16             'description': 'md5:1b8146791726342e7b22ce8125cf6945',
  17             'thumbnail': r're:^https?://.*\.jpg$',
  18             'creator': 'John Paul',
  19             'release_date': '19541009',
  20             'duration': 4260,
  21             'tbr': 5380,
  22             'width': 720,
  23             'height': 540,
  24         },
  25     }
  26
  27     def _real_extract(self, url):
  28         mobj = self._match_valid_url(url)
  29         video_id, display_id = mobj.group('id', 'display_id')
  30
  31         webpage = self._download_webpage(url, display_id)
  32
  33         title = self._search_regex(
  34             r'<h1>([^<]+)', webpage, 'title',
  35             default=None) or self._html_search_meta(
  36             'ya:ovs:original_name', webpage, 'title', fatal=True)
  37
  38         loc = self._search_regex(
  39             r'PCTMLOC\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage, 'loc',
  40             group='value')
  41
  42         loc_b64 = ''
  43         for c in loc:
  44             c_ord = ord(c)
  45             if ord('a') <= c_ord <= ord('z') or ord('A') <= c_ord <= ord('Z'):
  46                 upper = ord('Z') if c_ord <= ord('Z') else ord('z')
  47                 c_ord += 13
  48                 if upper < c_ord:
  49                     c_ord -= 26
  50             loc_b64 += chr(c_ord)
  51
  52         video_url = compat_b64decode(loc_b64).decode('utf-8')
  53
  54         description = self._html_search_regex(
  55             r'(?s)<div[^>]+class=["\']pt-movie-desc[^>]+>(.+?)</div>', webpage,
  56             'description', fatal=False)
  57
  58         thumbnail = self._search_regex(
  59             r'<img[^>]+class=["\']video-preview[^>]+\bsrc=(["\'])(?P<value>(?:(?!\1).)+)\1',
  60             webpage, 'thumbnail', default=None,
  61             group='value') or self._og_search_thumbnail(webpage)
  62
  63         creator = self._html_search_meta(
  64             'video:director', webpage, 'creator', default=None)
  65
  66         release_date = self._html_search_meta(
  67             'video:release_date', webpage, default=None)
  68         if release_date:
  69             release_date = release_date.replace('-', '')
  70
  71         def int_meta(name):
  72             return int_or_none(self._html_search_meta(
  73                 name, webpage, default=None))
  74
  75         return {
  76             'id': video_id,
  77             'display_id': display_id,
  78             'url': video_url,
  79             'title': title,
  80             'description': description,
  81             'thumbnail': thumbnail,
  82             'creator': creator,
  83             'release_date': release_date,
  84             'duration': int_meta('video:duration'),
  85             'tbr': int_meta('ya:ovs:bitrate'),
  86             'width': int_meta('og:video:width'),
  87             'height': int_meta('og:video:height'),
  88             'http_headers': {
  89                 'Referer': url,
  90             },
  91         }