youtube_dl/extractor/bigflix.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_b64decode,
   9     compat_urllib_parse_unquote,
  10 )
  11
  12
  13 class BigflixIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?bigflix\.com/.+/(?P<id>[0-9]+)'
  15     _TESTS = [{
  16         # 2 formats
  17         'url': 'http://www.bigflix.com/Tamil-movies/Drama-movies/Madarasapatinam/16070',
  18         'info_dict': {
  19             'id': '16070',
  20             'ext': 'mp4',
  21             'title': 'Madarasapatinam',
  22             'description': 'md5:9f0470b26a4ba8e824c823b5d95c2f6b',
  23             'formats': 'mincount:2',
  24         },
  25         'params': {
  26             'skip_download': True,
  27         }
  28     }, {
  29         # multiple formats
  30         'url': 'http://www.bigflix.com/Malayalam-movies/Drama-movies/Indian-Rupee/15967',
  31         'only_matching': True,
  32     }]
  33
  34     def _real_extract(self, url):
  35         video_id = self._match_id(url)
  36
  37         webpage = self._download_webpage(url, video_id)
  38
  39         title = self._html_search_regex(
  40             r'<div[^>]+class=["\']pagetitle["\'][^>]*>(.+?)</div>',
  41             webpage, 'title')
  42
  43         def decode_url(quoted_b64_url):
  44             return compat_b64decode(compat_urllib_parse_unquote(
  45                 quoted_b64_url)).decode('utf-8')
  46
  47         formats = []
  48         for height, encoded_url in re.findall(
  49                 r'ContentURL_(\d{3,4})[pP][^=]+=([^&]+)', webpage):
  50             video_url = decode_url(encoded_url)
  51             f = {
  52                 'url': video_url,
  53                 'format_id': '%sp' % height,
  54                 'height': int(height),
  55             }
  56             if video_url.startswith('rtmp'):
  57                 f['ext'] = 'flv'
  58             formats.append(f)
  59
  60         file_url = self._search_regex(
  61             r'file=([^&]+)', webpage, 'video url', default=None)
  62         if file_url:
  63             video_url = decode_url(file_url)
  64             if all(f['url'] != video_url for f in formats):
  65                 formats.append({
  66                     'url': decode_url(file_url),
  67                 })
  68
  69         self._sort_formats(formats)
  70
  71         description = self._html_search_meta('description', webpage)
  72
  73         return {
  74             'id': video_id,
  75             'title': title,
  76             'description': description,
  77             'formats': formats
  78         }