Raphaël G. Git Repositories - youtubedl/blob - 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 (
   8     compat_str,
   9     compat_urllib_parse_unquote,
  10 )
  11 from ..utils import (
  12     determine_ext,
  13     ExtractorError,
  14     int_or_none,
  15     str_to_int,
  16     strip_or_none,
  17 )
  18
  19
  20 class KeezMoviesIE(InfoExtractor):
  21     _VALID_URL = r'https?://(?:www\.)?keezmovies\.com/video/(?:(?P<display_id>[^/]+)-)?(?P<id>\d+)'
  22     _TESTS = [{
  23         'url': 'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711',
  24         'md5': '1c1e75d22ffa53320f45eeb07bc4cdc0',
  25         'info_dict': {
  26             'id': '1214711',
  27             'display_id': 'petite-asian-lady-mai-playing-in-bathtub',
  28             'ext': 'mp4',
  29             'title': 'Petite Asian Lady Mai Playing In Bathtub',
  30             'thumbnail': r're:^https?://.*\.jpg$',
  31             'view_count': int,
  32             'age_limit': 18,
  33         }
  34     }, {
  35         'url': 'http://www.keezmovies.com/video/1214711',
  36         'only_matching': True,
  37     }]
  38
  39     def _extract_info(self, url):
  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')
  45
  46         webpage = self._download_webpage(
  47             url, display_id, headers={'Cookie': 'age_verified=1'})
  48
  49         formats = []
  50         format_urls = set()
  51
  52         title = None
  53         thumbnail = None
  54         duration = None
  55         encrypted = False
  56
  57         def extract_format(format_url, height=None):
  58             if not isinstance(format_url, compat_str) or not format_url.startswith('http'):
  59                 return
  60             if format_url in format_urls:
  61                 return
  62             format_urls.add(format_url)
  63             tbr = int_or_none(self._search_regex(
  64                 r'[/_](\d+)[kK][/_]', format_url, 'tbr', default=None))
  65             if not height:
  66                 height = int_or_none(self._search_regex(
  67                     r'[/_](\d+)[pP][/_]', format_url, 'height', default=None))
  68             if encrypted:
  69                 format_url = aes_decrypt_text(
  70                     video_url, title, 32).decode('utf-8')
  71             formats.append({
  72                 'url': format_url,
  73                 'format_id': '%dp' % height if height else None,
  74                 'height': height,
  75                 'tbr': tbr,
  76             })
  77
  78         flashvars = self._parse_json(
  79             self._search_regex(
  80                 r'flashvars\s*=\s*({.+?});', webpage,
  81                 'flashvars', default='{}'),
  82             display_id, fatal=False)
  83
  84         if flashvars:
  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)
  91                 if mobj:
  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)
  96
  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')
 100         if video_url:
 101             extract_format(compat_urllib_parse_unquote(video_url))
 102
 103         if not formats:
 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)
 107
 108         self._sort_formats(formats)
 109
 110         if not title:
 111             title = self._html_search_regex(
 112                 r'<h1[^>]*>([^<]+)', webpage, 'title')
 113
 114         return webpage, {
 115             'id': video_id,
 116             'display_id': display_id,
 117             'title': strip_or_none(title),
 118             'thumbnail': thumbnail,
 119             'duration': duration,
 120             'age_limit': 18,
 121             'formats': formats,
 122         }
 123
 124     def _real_extract(self, url):
 125         webpage, info = self._extract_info(url)
 126         info['view_count'] = str_to_int(self._search_regex(
 127             r'<b>([\d,.]+)</b> Views?', webpage, 'view count', fatal=False))
 128         return info