yt_dlp/extractor/bigflix.py

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