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': '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') or video_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             if not isinstance(format_url, compat_str) 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': '%dp' % height if height else None,
  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                 raise ExtractorError(
 104                     'Video %s is no longer available' % video_id, expected=True)
 105
 106         self._sort_formats(formats)
 107
 108         if not title:
 109             title = self._html_search_regex(
 110                 r'<h1[^>]*>([^<]+)', webpage, 'title')
 111
 112         return webpage, {
 113             'id': video_id,
 114             'display_id': display_id,
 115             'title': strip_or_none(title),
 116             'thumbnail': thumbnail,
 117             'duration': duration,
 118             'age_limit': 18,
 119             'formats': formats,
 120         }
 121
 122     def _real_extract(self, url):
 123         webpage, info = self._extract_info(url)
 124         info['view_count'] = str_to_int(self._search_regex(
 125             r'<b>([\d,.]+)</b> Views?', webpage, 'view count', fatal=False))
 126         return info