_ Git - youtube-dl/blob - youtube_dl/extractor/bigflix.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import base64
   5 import re
   6
   7 from .common import InfoExtractor
   8 from ..compat import compat_urllib_parse_unquote
   9
  10
  11 class BigflixIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?bigflix\.com/.+/(?P<id>[0-9]+)'
  13     _TESTS = [{
  14         'url': 'http://www.bigflix.com/Hindi-movies/Action-movies/Singham-Returns/16537',
  15         'md5': 'ec76aa9b1129e2e5b301a474e54fab74',
  16         'info_dict': {
  17             'id': '16537',
  18             'ext': 'mp4',
  19             'title': 'Singham Returns',
  20             'description': 'md5:3d2ba5815f14911d5cc6a501ae0cf65d',
  21         }
  22     }, {
  23         # multiple formats
  24         'url': 'http://www.bigflix.com/Tamil-movies/Drama-movies/Madarasapatinam/16070',
  25         'info_dict': {
  26             'id': '16070',
  27             'ext': 'mp4',
  28             'title': 'Madarasapatinam',
  29             'description': 'md5:63b9b8ed79189c6f0418c26d9a3452ca',
  30             'formats': 'mincount:2',
  31         },
  32         'params': {
  33             'skip_download': True,
  34         }
  35     }]
  36
  37     def _real_extract(self, url):
  38         video_id = self._match_id(url)
  39
  40         webpage = self._download_webpage(url, video_id)
  41
  42         title = self._html_search_regex(
  43             r'<div[^>]+class=["\']pagetitle["\'][^>]*>(.+?)</div>',
  44             webpage, 'title')
  45
  46         def decode_url(quoted_b64_url):
  47             return base64.b64decode(compat_urllib_parse_unquote(
  48                 quoted_b64_url)).encode('ascii').decode('utf-8')
  49
  50         formats = [{
  51             'url': decode_url(encoded_url),
  52             'format_id': '%sp' % height,
  53             'height': int(height),
  54         } for height, encoded_url in re.findall(
  55             r'ContentURL_(\d{3,4})[pP][^=]+=([^&]+)', webpage)]
  56
  57         if not formats:
  58             formats.append({
  59                 'url': decode_url(self._search_regex(
  60                     r'file=([^&]+)', webpage, 'video url')),
  61             })
  62
  63         description = self._html_search_meta('description', webpage)
  64
  65         return {
  66             'id': video_id,
  67             'title': title,
  68             'description': description,
  69             'formats': formats
  70         }