youtube_dl/extractor/engadget.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from .fivemin import FiveMinIE
   7 from ..utils import (
   8     url_basename,
   9 )
  10
  11
  12 class EngadgetIE(InfoExtractor):
  13     _VALID_URL = r'''(?x)https?://www.engadget.com/
  14         (?:video/5min/(?P<id>\d+)|
  15             [\d/]+/.*?)
  16         '''
  17
  18     _TEST = {
  19         'url': 'http://www.engadget.com/video/5min/518153925/',
  20         'md5': 'c6820d4828a5064447a4d9fc73f312c9',
  21         'info_dict': {
  22             'id': '518153925',
  23             'ext': 'mp4',
  24             'title': 'Samsung Galaxy Tab Pro 8.4 Review',
  25         },
  26         'add_ie': ['FiveMin'],
  27     }
  28
  29     def _real_extract(self, url):
  30         mobj = re.match(self._VALID_URL, url)
  31         video_id = mobj.group('id')
  32
  33         if video_id is not None:
  34             return FiveMinIE._build_result(video_id)
  35         else:
  36             title = url_basename(url)
  37             webpage = self._download_webpage(url, title)
  38             ids = re.findall(r'<iframe[^>]+?playList=(\d+)', webpage)
  39             return {
  40                 '_type': 'playlist',
  41                 'title': title,
  42                 'entries': [FiveMinIE._build_result(id) for id in ids]
  43             }