yt_dlp/extractor/popcorntimes.py

   1 import base64
   2
   3 from .common import InfoExtractor
   4 from ..utils import int_or_none
   5
   6
   7 class PopcorntimesIE(InfoExtractor):
   8     _VALID_URL = r'https?://popcorntimes\.tv/[^/]+/m/(?P<id>[^/]+)/(?P<display_id>[^/?#&]+)'
   9     _TEST = {
  10         'url': 'https://popcorntimes.tv/de/m/A1XCFvz/haensel-und-gretel-opera-fantasy',
  11         'md5': '93f210991ad94ba8c3485950a2453257',
  12         'info_dict': {
  13             'id': 'A1XCFvz',
  14             'display_id': 'haensel-und-gretel-opera-fantasy',
  15             'ext': 'mp4',
  16             'title': 'Hänsel und Gretel',
  17             'description': 'md5:1b8146791726342e7b22ce8125cf6945',
  18             'thumbnail': r're:^https?://.*\.jpg$',
  19             'creator': 'John Paul',
  20             'release_date': '19541009',
  21             'duration': 4260,
  22             'tbr': 5380,
  23             'width': 720,
  24             'height': 540,
  25         },
  26     }
  27
  28     def _real_extract(self, url):
  29         mobj = self._match_valid_url(url)
  30         video_id, display_id = mobj.group('id', 'display_id')
  31
  32         webpage = self._download_webpage(url, display_id)
  33
  34         title = self._search_regex(
  35             r'<h1>([^<]+)', webpage, 'title',
  36             default=None) or self._html_search_meta(
  37             'ya:ovs:original_name', webpage, 'title', fatal=True)
  38
  39         loc = self._search_regex(
  40             r'PCTMLOC\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage, 'loc',
  41             group='value')
  42
  43         loc_b64 = ''
  44         for c in loc:
  45             c_ord = ord(c)
  46             if ord('a') <= c_ord <= ord('z') or ord('A') <= c_ord <= ord('Z'):
  47                 upper = ord('Z') if c_ord <= ord('Z') else ord('z')
  48                 c_ord += 13
  49                 if upper < c_ord:
  50                     c_ord -= 26
  51             loc_b64 += chr(c_ord)
  52
  53         video_url = base64.b64decode(loc_b64).decode('utf-8')
  54
  55         description = self._html_search_regex(
  56             r'(?s)<div[^>]+class=["\']pt-movie-desc[^>]+>(.+?)</div>', webpage,
  57             'description', fatal=False)
  58
  59         thumbnail = self._search_regex(
  60             r'<img[^>]+class=["\']video-preview[^>]+\bsrc=(["\'])(?P<value>(?:(?!\1).)+)\1',
  61             webpage, 'thumbnail', default=None,
  62             group='value') or self._og_search_thumbnail(webpage)
  63
  64         creator = self._html_search_meta(
  65             'video:director', webpage, 'creator', default=None)
  66
  67         release_date = self._html_search_meta(
  68             'video:release_date', webpage, default=None)
  69         if release_date:
  70             release_date = release_date.replace('-', '')
  71
  72         def int_meta(name):
  73             return int_or_none(self._html_search_meta(
  74                 name, webpage, default=None))
  75
  76         return {
  77             'id': video_id,
  78             'display_id': display_id,
  79             'url': video_url,
  80             'title': title,
  81             'description': description,
  82             'thumbnail': thumbnail,
  83             'creator': creator,
  84             'release_date': release_date,
  85             'duration': int_meta('video:duration'),
  86             'tbr': int_meta('ya:ovs:bitrate'),
  87             'width': int_meta('og:video:width'),
  88             'height': int_meta('og:video:height'),
  89             'http_headers': {
  90                 'Referer': url,
  91             },
  92         }