youtube_dl/extractor/keezmovies.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..aes import aes_decrypt_text
   7 from ..compat import compat_urllib_parse_unquote
   8 from ..utils import (
   9     determine_ext,
  10     ExtractorError,
  11     int_or_none,
  12     str_to_int,
  13     strip_or_none,
  14     url_or_none,
  15 )
  16
  17
  18 class KeezMoviesIE(InfoExtractor):
  19     _VALID_URL = r'https?://(?:www\.)?keezmovies\.com/video/(?:(?P<display_id>[^/]+)-)?(?P<id>\d+)'
  20     _TESTS = [{
  21         'url': 'https://www.keezmovies.com/video/arab-wife-want-it-so-bad-i-see-she-thirsty-and-has-tiny-money-18070681',
  22         'md5': '2ac69cdb882055f71d82db4311732a1a',
  23         'info_dict': {
  24             'id': '18070681',
  25             'display_id': 'arab-wife-want-it-so-bad-i-see-she-thirsty-and-has-tiny-money',
  26             'ext': 'mp4',
  27             'title': 'Arab wife want it so bad I see she thirsty and has tiny money.',
  28             'thumbnail': None,
  29             'view_count': int,
  30             'age_limit': 18,
  31         }
  32     }, {
  33         'url': 'http://www.keezmovies.com/video/18070681',
  34         'only_matching': True,
  35     }]
  36
  37     def _extract_info(self, url, fatal=True):
  38         mobj = re.match(self._VALID_URL, url)
  39         video_id = mobj.group('id')
  40         display_id = (mobj.group('display_id')
  41                       if 'display_id' in mobj.groupdict()
  42                       else None) or mobj.group('id')
  43
  44         webpage = self._download_webpage(
  45             url, display_id, headers={'Cookie': 'age_verified=1'})
  46
  47         formats = []
  48         format_urls = set()
  49
  50         title = None
  51         thumbnail = None
  52         duration = None
  53         encrypted = False
  54
  55         def extract_format(format_url, height=None):
  56             format_url = url_or_none(format_url)
  57             if not format_url or not format_url.startswith(('http', '//')):
  58                 return
  59             if format_url in format_urls:
  60                 return
  61             format_urls.add(format_url)
  62             tbr = int_or_none(self._search_regex(
  63                 r'[/_](\d+)[kK][/_]', format_url, 'tbr', default=None))
  64             if not height:
  65                 height = int_or_none(self._search_regex(
  66                     r'[/_](\d+)[pP][/_]', format_url, 'height', default=None))
  67             if encrypted:
  68                 format_url = aes_decrypt_text(
  69                     video_url, title, 32).decode('utf-8')
  70             formats.append({
  71                 'url': format_url,
  72                 'format_id': '%dp' % height if height else None,
  73                 'height': height,
  74                 'tbr': tbr,
  75             })
  76
  77         flashvars = self._parse_json(
  78             self._search_regex(
  79                 r'flashvars\s*=\s*({.+?});', webpage,
  80                 'flashvars', default='{}'),
  81             display_id, fatal=False)
  82
  83         if flashvars:
  84             title = flashvars.get('video_title')
  85             thumbnail = flashvars.get('image_url')
  86             duration = int_or_none(flashvars.get('video_duration'))
  87             encrypted = flashvars.get('encrypted') is True
  88             for key, value in flashvars.items():
  89                 mobj = re.search(r'quality_(\d+)[pP]', key)
  90                 if mobj:
  91                     extract_format(value, int(mobj.group(1)))
  92             video_url = flashvars.get('video_url')
  93             if video_url and determine_ext(video_url, None):
  94                 extract_format(video_url)
  95
  96         video_url = self._html_search_regex(
  97             r'flashvars\.video_url\s*=\s*(["\'])(?P<url>http.+?)\1',
  98             webpage, 'video url', default=None, group='url')
  99         if video_url:
 100             extract_format(compat_urllib_parse_unquote(video_url))
 101
 102         if not formats:
 103             if 'title="This video is no longer available"' in webpage:
 104                 raise ExtractorError(
 105                     'Video %s is no longer available' % video_id, expected=True)
 106
 107         try:
 108             self._sort_formats(formats)
 109         except ExtractorError:
 110             if fatal:
 111                 raise
 112
 113         if not title:
 114             title = self._html_search_regex(
 115                 r'<h1[^>]*>([^<]+)', webpage, 'title')
 116
 117         return webpage, {
 118             'id': video_id,
 119             'display_id': display_id,
 120             'title': strip_or_none(title),
 121             'thumbnail': thumbnail,
 122             'duration': duration,
 123             'age_limit': 18,
 124             'formats': formats,
 125         }
 126
 127     def _real_extract(self, url):
 128         webpage, info = self._extract_info(url, fatal=False)
 129         if not info['formats']:
 130             return self.url_result(url, 'Generic')
 131         info['view_count'] = str_to_int(self._search_regex(
 132             r'<b>([\d,.]+)</b> Views?', webpage, 'view count', fatal=False))
 133         return info