Raphaël G. Git Repositories - youtubedl/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         # 2 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         # multiple formats
  37         'url': 'http://www.bigflix.com/Malayalam-movies/Drama-movies/Indian-Rupee/15967',
  38         'only_matching': True,
  39     }]
  40
  41     def _real_extract(self, url):
  42         video_id = self._match_id(url)
  43
  44         webpage = self._download_webpage(url, video_id)
  45
  46         title = self._html_search_regex(
  47             r'<div[^>]+class=["\']pagetitle["\'][^>]*>(.+?)</div>',
  48             webpage, 'title')
  49
  50         def decode_url(quoted_b64_url):
  51             return base64.b64decode(compat_urllib_parse_unquote(
  52                 quoted_b64_url).encode('ascii')).decode('utf-8')
  53
  54         formats = []
  55         for height, encoded_url in re.findall(
  56                 r'ContentURL_(\d{3,4})[pP][^=]+=([^&]+)', webpage):
  57             video_url = decode_url(encoded_url)
  58             f = {
  59                 'url': video_url,
  60                 'format_id': '%sp' % height,
  61                 'height': int(height),
  62             }
  63             if video_url.startswith('rtmp'):
  64                 f['ext'] = 'flv'
  65             formats.append(f)
  66
  67         file_url = self._search_regex(
  68             r'file=([^&]+)', webpage, 'video url', default=None)
  69         if file_url:
  70             video_url = decode_url(file_url)
  71             if all(f['url'] != video_url for f in formats):
  72                 formats.append({
  73                     'url': decode_url(file_url),
  74                 })
  75
  76         self._sort_formats(formats)
  77
  78         description = self._html_search_meta('description', webpage)
  79
  80         return {
  81             'id': video_id,
  82             'title': title,
  83             'description': description,
  84             'formats': formats
  85         }