_ Git - youtube-dl/blob - youtube_dl/extractor/dotsub.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     float_or_none,
   6     int_or_none,
   7 )
   8
   9
  10 class DotsubIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?dotsub\.com/view/(?P<id>[^/]+)'
  12     _TEST = {
  13         'url': 'https://dotsub.com/view/9c63db2a-fa95-4838-8e6e-13deafe47f09',
  14         'md5': '21c7ff600f545358134fea762a6d42b6',
  15         'info_dict': {
  16             'id': '9c63db2a-fa95-4838-8e6e-13deafe47f09',
  17             'ext': 'flv',
  18             'title': 'MOTIVATION - "It\'s Possible" Best Inspirational Video Ever',
  19             'description': 'md5:41af1e273edbbdfe4e216a78b9d34ac6',
  20             'thumbnail': 're:^https?://dotsub.com/media/9c63db2a-fa95-4838-8e6e-13deafe47f09/p',
  21             'duration': 198,
  22             'uploader': 'liuxt',
  23             'timestamp': 1385778501.104,
  24             'upload_date': '20131130',
  25             'view_count': int,
  26         }
  27     }
  28
  29     def _real_extract(self, url):
  30         video_id = self._match_id(url)
  31
  32         info = self._download_json(
  33             'https://dotsub.com/api/media/%s/metadata' % video_id, video_id)
  34         video_url = info.get('mediaURI')
  35
  36         if not video_url:
  37             webpage = self._download_webpage(url, video_id)
  38             video_url = self._search_regex(
  39                 [r'<source[^>]+src="([^"]+)"', r'"file"\s*:\s*\'([^\']+)'],
  40                 webpage, 'video url')
  41
  42         return {
  43             'id': video_id,
  44             'url': video_url,
  45             'ext': 'flv',
  46             'title': info['title'],
  47             'description': info.get('description'),
  48             'thumbnail': info.get('screenshotURI'),
  49             'duration': int_or_none(info.get('duration'), 1000),
  50             'uploader': info.get('user'),
  51             'timestamp': float_or_none(info.get('dateCreated'), 1000),
  52             'view_count': int_or_none(info.get('numberOfViews')),
  53         }