Raphaël G. Git Repositories - youtubedl/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': 'http://dotsub.com/view/aed3b8b2-1889-4df5-ae63-ad85f5572f27',
  14         'md5': '0914d4d69605090f623b7ac329fea66e',
  15         'info_dict': {
  16             'id': 'aed3b8b2-1889-4df5-ae63-ad85f5572f27',
  17             'ext': 'flv',
  18             'title': 'Pyramids of Waste (2010), AKA The Lightbulb Conspiracy - Planned obsolescence documentary',
  19             'description': 'md5:699a0f7f50aeec6042cb3b1db2d0d074',
  20             'thumbnail': 're:^https?://dotsub.com/media/aed3b8b2-1889-4df5-ae63-ad85f5572f27/p',
  21             'duration': 3169,
  22             'uploader': '4v4l0n42',
  23             'timestamp': 1292248482.625,
  24             'upload_date': '20101213',
  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'"file"\s*:\s*\'([^\']+)', webpage, 'video url')
  40
  41         return {
  42             'id': video_id,
  43             'url': video_url,
  44             'ext': 'flv',
  45             'title': info['title'],
  46             'description': info.get('description'),
  47             'thumbnail': info.get('screenshotURI'),
  48             'duration': int_or_none(info.get('duration'), 1000),
  49             'uploader': info.get('user'),
  50             'timestamp': float_or_none(info.get('dateCreated'), 1000),
  51             'view_count': int_or_none(info.get('numberOfViews')),
  52         }