1 from __future__ import unicode_literals
5 from .common import InfoExtractor
6 from ..aes import aes_decrypt_text
9 compat_urllib_parse_unquote,
20 class KeezMoviesIE(InfoExtractor):
21 _VALID_URL = r'https?://(?:www\.)?keezmovies\.com/video/(?:(?P<display_id>[^/]+)-)?(?P<id>\d+)'
23 'url': 'https://www.keezmovies.com/video/arab-wife-want-it-so-bad-i-see-she-thirsty-and-has-tiny-money-18070681',
24 'md5': '2ac69cdb882055f71d82db4311732a1a',
27 'display_id': 'arab-wife-want-it-so-bad-i-see-she-thirsty-and-has-tiny-money',
29 'title': 'Arab wife want it so bad I see she thirsty and has tiny money.',
35 'url': 'http://www.keezmovies.com/video/18070681',
36 'only_matching': True,
39 def _extract_info(self, url, fatal=True):
40 mobj = re.match(self._VALID_URL, url)
41 video_id = mobj.group('id')
42 display_id = (mobj.group('display_id')
43 if 'display_id' in mobj.groupdict()
44 else None) or mobj.group('id')
46 webpage = self._download_webpage(
47 url, display_id, headers={'Cookie': 'age_verified=1'})
57 def extract_format(format_url, height=None):
58 if not isinstance(format_url, compat_str) or not format_url.startswith(('http', '//')):
60 if format_url in format_urls:
62 format_urls.add(format_url)
63 tbr = int_or_none(self._search_regex(
64 r'[/_](\d+)[kK][/_]', format_url, 'tbr', default=None))
66 height = int_or_none(self._search_regex(
67 r'[/_](\d+)[pP][/_]', format_url, 'height', default=None))
69 format_url = aes_decrypt_text(
70 video_url, title, 32).decode('utf-8')
73 'format_id': '%dp' % height if height else None,
78 flashvars = self._parse_json(
80 r'flashvars\s*=\s*({.+?});', webpage,
81 'flashvars', default='{}'),
82 display_id, fatal=False)
85 title = flashvars.get('video_title')
86 thumbnail = flashvars.get('image_url')
87 duration = int_or_none(flashvars.get('video_duration'))
88 encrypted = flashvars.get('encrypted') is True
89 for key, value in flashvars.items():
90 mobj = re.search(r'quality_(\d+)[pP]', key)
92 extract_format(value, int(mobj.group(1)))
93 video_url = flashvars.get('video_url')
94 if video_url and determine_ext(video_url, None):
95 extract_format(video_url)
97 video_url = self._html_search_regex(
98 r'flashvars\.video_url\s*=\s*(["\'])(?P<url>http.+?)\1',
99 webpage, 'video url', default=None, group='url')
101 extract_format(compat_urllib_parse_unquote(video_url))
104 if 'title="This video is no longer available"' in webpage:
105 raise ExtractorError(
106 'Video %s is no longer available' % video_id, expected=True)
109 self._sort_formats(formats)
110 except ExtractorError:
115 title = self._html_search_regex(
116 r'<h1[^>]*>([^<]+)', webpage, 'title')
120 'display_id': display_id,
121 'title': strip_or_none(title),
122 'thumbnail': thumbnail,
123 'duration': duration,
128 def _real_extract(self, url):
129 webpage, info = self._extract_info(url, fatal=False)
130 if not info['formats']:
131 return self.url_result(url, 'Generic')
132 info['view_count'] = str_to_int(self._search_regex(
133 r'<b>([\d,.]+)</b> Views?', webpage, 'view count', fatal=False))