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         # 2 formats
  15         'url': 'http://www.bigflix.com/Tamil-movies/Drama-movies/Madarasapatinam/16070',
  16         'info_dict': {
  17             'id': '16070',
  18             'ext': 'mp4',
  19             'title': 'Madarasapatinam',
  20             'description': 'md5:9f0470b26a4ba8e824c823b5d95c2f6b',
  21             'formats': 'mincount:2',
  22         },
  23         'params': {
  24             'skip_download': True,
  25         }
  26     }, {
  27         # multiple formats
  28         'url': 'http://www.bigflix.com/Malayalam-movies/Drama-movies/Indian-Rupee/15967',
  29         'only_matching': True,
  30     }]
  31
  32     def _real_extract(self, url):
  33         video_id = self._match_id(url)
  34
  35         webpage = self._download_webpage(url, video_id)
  36
  37         title = self._html_search_regex(
  38             r'<div[^>]+class=["\']pagetitle["\'][^>]*>(.+?)</div>',
  39             webpage, 'title')
  40
  41         def decode_url(quoted_b64_url):
  42             return base64.b64decode(compat_urllib_parse_unquote(
  43                 quoted_b64_url).encode('ascii')).decode('utf-8')
  44
  45         formats = []
  46         for height, encoded_url in re.findall(
  47                 r'ContentURL_(\d{3,4})[pP][^=]+=([^&]+)', webpage):
  48             video_url = decode_url(encoded_url)
  49             f = {
  50                 'url': video_url,
  51                 'format_id': '%sp' % height,
  52                 'height': int(height),
  53             }
  54             if video_url.startswith('rtmp'):
  55                 f['ext'] = 'flv'
  56             formats.append(f)
  57
  58         file_url = self._search_regex(
  59             r'file=([^&]+)', webpage, 'video url', default=None)
  60         if file_url:
  61             video_url = decode_url(file_url)
  62             if all(f['url'] != video_url for f in formats):
  63                 formats.append({
  64                     'url': decode_url(file_url),
  65                 })
  66
  67         self._sort_formats(formats)
  68
  69         description = self._html_search_meta('description', webpage)
  70
  71         return {
  72             'id': video_id,
  73             'title': title,
  74             'description': description,
  75             'formats': formats
  76         }