yt_dlp/extractor/bigflix.py

   1 import base64
   2 import re
   3 import urllib.parse
   4
   5 from .common import InfoExtractor
   6
   7
   8 class BigflixIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?bigflix\.com/.+/(?P<id>[0-9]+)'
  10     _TESTS = [{
  11         # 2 formats
  12         'url': 'http://www.bigflix.com/Tamil-movies/Drama-movies/Madarasapatinam/16070',
  13         'info_dict': {
  14             'id': '16070',
  15             'ext': 'mp4',
  16             'title': 'Madarasapatinam',
  17             'description': 'md5:9f0470b26a4ba8e824c823b5d95c2f6b',
  18             'formats': 'mincount:2',
  19         },
  20         'params': {
  21             'skip_download': True,
  22         },
  23     }, {
  24         # multiple formats
  25         'url': 'http://www.bigflix.com/Malayalam-movies/Drama-movies/Indian-Rupee/15967',
  26         'only_matching': True,
  27     }]
  28
  29     def _real_extract(self, url):
  30         video_id = self._match_id(url)
  31
  32         webpage = self._download_webpage(url, video_id)
  33
  34         title = self._html_search_regex(
  35             r'<div[^>]+class=["\']pagetitle["\'][^>]*>(.+?)</div>',
  36             webpage, 'title')
  37
  38         def decode_url(quoted_b64_url):
  39             return base64.b64decode(urllib.parse.unquote(
  40                 quoted_b64_url)).decode('utf-8')
  41
  42         formats = []
  43         for height, encoded_url in re.findall(
  44                 r'ContentURL_(\d{3,4})[pP][^=]+=([^&]+)', webpage):
  45             video_url = decode_url(encoded_url)
  46             f = {
  47                 'url': video_url,
  48                 'format_id': f'{height}p',
  49                 'height': int(height),
  50             }
  51             if video_url.startswith('rtmp'):
  52                 f['ext'] = 'flv'
  53             formats.append(f)
  54
  55         file_url = self._search_regex(
  56             r'file=([^&]+)', webpage, 'video url', default=None)
  57         if file_url:
  58             video_url = decode_url(file_url)
  59             if all(f['url'] != video_url for f in formats):
  60                 formats.append({
  61                     'url': decode_url(file_url),
  62                 })
  63
  64         description = self._html_search_meta('description', webpage)
  65
  66         return {
  67             'id': video_id,
  68             'title': title,
  69             'description': description,
  70             'formats': formats,
  71         }