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