Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/engadget.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     url_basename,
   8 )
   9
  10
  11 class EngadgetIE(InfoExtractor):
  12     _VALID_URL = r'''(?x)https?://www.engadget.com/
  13         (?:video(?:/5min)?/(?P<id>\d+)|
  14             [\d/]+/.*?)
  15         '''
  16
  17     _TEST = {
  18         'url': 'http://www.engadget.com/video/5min/518153925/',
  19         'md5': 'c6820d4828a5064447a4d9fc73f312c9',
  20         'info_dict': {
  21             'id': '518153925',
  22             'ext': 'mp4',
  23             'title': 'Samsung Galaxy Tab Pro 8.4 Review',
  24         },
  25         'add_ie': ['FiveMin'],
  26     }
  27
  28     def _real_extract(self, url):
  29         video_id = self._match_id(url)
  30
  31         if video_id is not None:
  32             return self.url_result('5min:%s' % video_id)
  33         else:
  34             title = url_basename(url)
  35             webpage = self._download_webpage(url, title)
  36             ids = re.findall(r'<iframe[^>]+?playList=(\d+)', webpage)
  37             return {
  38                 '_type': 'playlist',
  39                 'title': title,
  40                 'entries': [self.url_result('5min:%s' % vid) for vid in ids]
  41             }