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 ..utils import (
   7     sanitized_Request,
   8     url_basename,
   9 )
  10
  11
  12 class KeezMoviesIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?keezmovies\.com/video/.+?(?P<id>[0-9]+)(?:[/?&]|$)'
  14     _TEST = {
  15         'url': 'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711',
  16         'md5': '1c1e75d22ffa53320f45eeb07bc4cdc0',
  17         'info_dict': {
  18             'id': '1214711',
  19             'ext': 'mp4',
  20             'title': 'Petite Asian Lady Mai Playing In Bathtub',
  21             'age_limit': 18,
  22             'thumbnail': 're:^https?://.*\.jpg$',
  23         }
  24     }
  25
  26     def _real_extract(self, url):
  27         video_id = self._match_id(url)
  28
  29         req = sanitized_Request(url)
  30         req.add_header('Cookie', 'age_verified=1')
  31         webpage = self._download_webpage(req, video_id)
  32
  33         # embedded video
  34         mobj = re.search(r'href="([^"]+)"></iframe>', webpage)
  35         if mobj:
  36             embedded_url = mobj.group(1)
  37             return self.url_result(embedded_url)
  38
  39         video_title = self._html_search_regex(
  40             r'<h1 [^>]*>([^<]+)', webpage, 'title')
  41         flashvars = self._parse_json(self._search_regex(
  42             r'var\s+flashvars\s*=\s*([^;]+);', webpage, 'flashvars'), video_id)
  43
  44         formats = []
  45         for height in (180, 240, 480):
  46             if flashvars.get('quality_%dp' % height):
  47                 video_url = flashvars['quality_%dp' % height]
  48                 a_format = {
  49                     'url': video_url,
  50                     'height': height,
  51                     'format_id': '%dp' % height,
  52                 }
  53                 filename_parts = url_basename(video_url).split('_')
  54                 if len(filename_parts) >= 2 and re.match(r'\d+[Kk]', filename_parts[1]):
  55                     a_format['tbr'] = int(filename_parts[1][:-1])
  56                 formats.append(a_format)
  57
  58         age_limit = self._rta_search(webpage)
  59
  60         return {
  61             'id': video_id,
  62             'title': video_title,
  63             'formats': formats,
  64             'age_limit': age_limit,
  65             'thumbnail': flashvars.get('image_url')
  66         }