yt_dlp/extractor/keezmovies.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..aes import aes_decrypt_text
   5 from ..compat import compat_urllib_parse_unquote
   6 from ..utils import (
   7     determine_ext,
   8     format_field,
   9     int_or_none,
  10     str_to_int,
  11     strip_or_none,
  12     url_or_none,
  13 )
  14
  15
  16 class KeezMoviesIE(InfoExtractor):
  17     _VALID_URL = r'https?://(?:www\.)?keezmovies\.com/video/(?:(?P<display_id>[^/]+)-)?(?P<id>\d+)'
  18     _TESTS = [{
  19         'url': 'https://www.keezmovies.com/video/arab-wife-want-it-so-bad-i-see-she-thirsty-and-has-tiny-money-18070681',
  20         'md5': '2ac69cdb882055f71d82db4311732a1a',
  21         'info_dict': {
  22             'id': '18070681',
  23             'display_id': 'arab-wife-want-it-so-bad-i-see-she-thirsty-and-has-tiny-money',
  24             'ext': 'mp4',
  25             'title': 'Arab wife want it so bad I see she thirsty and has tiny money.',
  26             'thumbnail': None,
  27             'view_count': int,
  28             'age_limit': 18,
  29         }
  30     }, {
  31         'url': 'http://www.keezmovies.com/video/18070681',
  32         'only_matching': True,
  33     }]
  34
  35     def _extract_info(self, url, fatal=True):
  36         mobj = self._match_valid_url(url)
  37         video_id = mobj.group('id')
  38         display_id = (mobj.group('display_id')
  39                       if 'display_id' in mobj.groupdict()
  40                       else None) or mobj.group('id')
  41
  42         webpage = self._download_webpage(
  43             url, display_id, headers={'Cookie': 'age_verified=1'})
  44
  45         formats = []
  46         format_urls = set()
  47
  48         title = None
  49         thumbnail = None
  50         duration = None
  51         encrypted = False
  52
  53         def extract_format(format_url, height=None):
  54             format_url = url_or_none(format_url)
  55             if not format_url or not format_url.startswith(('http', '//')):
  56                 return
  57             if format_url in format_urls:
  58                 return
  59             format_urls.add(format_url)
  60             tbr = int_or_none(self._search_regex(
  61                 r'[/_](\d+)[kK][/_]', format_url, 'tbr', default=None))
  62             if not height:
  63                 height = int_or_none(self._search_regex(
  64                     r'[/_](\d+)[pP][/_]', format_url, 'height', default=None))
  65             if encrypted:
  66                 format_url = aes_decrypt_text(
  67                     video_url, title, 32).decode('utf-8')
  68             formats.append({
  69                 'url': format_url,
  70                 'format_id': format_field(height, None, '%dp'),
  71                 'height': height,
  72                 'tbr': tbr,
  73             })
  74
  75         flashvars = self._parse_json(
  76             self._search_regex(
  77                 r'flashvars\s*=\s*({.+?});', webpage,
  78                 'flashvars', default='{}'),
  79             display_id, fatal=False)
  80
  81         if flashvars:
  82             title = flashvars.get('video_title')
  83             thumbnail = flashvars.get('image_url')
  84             duration = int_or_none(flashvars.get('video_duration'))
  85             encrypted = flashvars.get('encrypted') is True
  86             for key, value in flashvars.items():
  87                 mobj = re.search(r'quality_(\d+)[pP]', key)
  88                 if mobj:
  89                     extract_format(value, int(mobj.group(1)))
  90             video_url = flashvars.get('video_url')
  91             if video_url and determine_ext(video_url, None):
  92                 extract_format(video_url)
  93
  94         video_url = self._html_search_regex(
  95             r'flashvars\.video_url\s*=\s*(["\'])(?P<url>http.+?)\1',
  96             webpage, 'video url', default=None, group='url')
  97         if video_url:
  98             extract_format(compat_urllib_parse_unquote(video_url))
  99
 100         if not formats:
 101             if 'title="This video is no longer available"' in webpage:
 102                 self.raise_no_formats(
 103                     'Video %s is no longer available' % video_id, expected=True)
 104
 105         if not title:
 106             title = self._html_search_regex(
 107                 r'<h1[^>]*>([^<]+)', webpage, 'title')
 108
 109         return webpage, {
 110             'id': video_id,
 111             'display_id': display_id,
 112             'title': strip_or_none(title),
 113             'thumbnail': thumbnail,
 114             'duration': duration,
 115             'age_limit': 18,
 116             'formats': formats,
 117         }
 118
 119     def _real_extract(self, url):
 120         webpage, info = self._extract_info(url, fatal=False)
 121         if not info['formats']:
 122             return self.url_result(url, 'Generic')
 123         info['view_count'] = str_to_int(self._search_regex(
 124             r'<b>([\d,.]+)</b> Views?', webpage, 'view count', fatal=False))
 125         return info