yt_dlp/extractor/dotsub.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     float_or_none,
   4     int_or_none,
   5 )
   6
   7
   8 class DotsubIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?dotsub\.com/view/(?P<id>[^/]+)'
  10     _TESTS = [{
  11         'url': 'https://dotsub.com/view/9c63db2a-fa95-4838-8e6e-13deafe47f09',
  12         'md5': '21c7ff600f545358134fea762a6d42b6',
  13         'info_dict': {
  14             'id': '9c63db2a-fa95-4838-8e6e-13deafe47f09',
  15             'ext': 'flv',
  16             'title': 'MOTIVATION - "It\'s Possible" Best Inspirational Video Ever',
  17             'description': 'md5:41af1e273edbbdfe4e216a78b9d34ac6',
  18             'thumbnail': 're:^https?://dotsub.com/media/9c63db2a-fa95-4838-8e6e-13deafe47f09/p',
  19             'duration': 198,
  20             'uploader': 'liuxt',
  21             'timestamp': 1385778501.104,
  22             'upload_date': '20131130',
  23             'view_count': int,
  24         }
  25     }, {
  26         'url': 'https://dotsub.com/view/747bcf58-bd59-45b7-8c8c-ac312d084ee6',
  27         'md5': '2bb4a83896434d5c26be868c609429a3',
  28         'info_dict': {
  29             'id': '168006778',
  30             'ext': 'mp4',
  31             'title': 'Apartments and flats in Raipur the white symphony',
  32             'description': 'md5:784d0639e6b7d1bc29530878508e38fe',
  33             'thumbnail': 're:^https?://dotsub.com/media/747bcf58-bd59-45b7-8c8c-ac312d084ee6/p',
  34             'duration': 290,
  35             'timestamp': 1476767794.2809999,
  36             'upload_date': '20161018',
  37             'uploader': 'parthivi001',
  38             'uploader_id': 'user52596202',
  39             'view_count': int,
  40         },
  41         'add_ie': ['Vimeo'],
  42     }]
  43
  44     def _real_extract(self, url):
  45         video_id = self._match_id(url)
  46
  47         info = self._download_json(
  48             'https://dotsub.com/api/media/%s/metadata' % video_id, video_id)
  49         video_url = info.get('mediaURI')
  50
  51         if not video_url:
  52             webpage = self._download_webpage(url, video_id)
  53             video_url = self._search_regex(
  54                 [r'<source[^>]+src="([^"]+)"', r'"file"\s*:\s*\'([^\']+)'],
  55                 webpage, 'video url', default=None)
  56             info_dict = {
  57                 'id': video_id,
  58                 'url': video_url,
  59                 'ext': 'flv',
  60             }
  61
  62         if not video_url:
  63             setup_data = self._parse_json(self._html_search_regex(
  64                 r'(?s)data-setup=([\'"])(?P<content>(?!\1).+?)\1',
  65                 webpage, 'setup data', group='content'), video_id)
  66             info_dict = {
  67                 '_type': 'url_transparent',
  68                 'url': setup_data['src'],
  69             }
  70
  71         info_dict.update({
  72             'title': info['title'],
  73             'description': info.get('description'),
  74             'thumbnail': info.get('screenshotURI'),
  75             'duration': int_or_none(info.get('duration'), 1000),
  76             'uploader': info.get('user'),
  77             'timestamp': float_or_none(info.get('dateCreated'), 1000),
  78             'view_count': int_or_none(info.get('numberOfViews')),
  79         })
  80
  81         return info_dict