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

   1 import re
   2 from ..utils import compat_urllib_parse
   3 from .common import InfoExtractor
   4
   5
   6 class EhowIE(InfoExtractor):
   7     _VALID_URL = r'(?:http://)?(?:www\.)?ehow\.com/([^/]+)'
   8     _TEST = {
   9         u'url': u'http://www.break.com/video/when-girls-act-like-guys-2468056',
  10         u'file': u'2468056.mp4',
  11         u'md5': u'a3513fb1547fba4fb6cfac1bffc6c46b',
  12         u'info_dict': {
  13             u"title": u"When Girls Act Like D-Bags"
  14         }
  15     }
  16
  17     def _real_extract(self, url):
  18         mobj = re.match(self._VALID_URL, url)
  19         video_id = mobj.group(1).split("_")[1]
  20         webpage = self._download_webpage(url, video_id)
  21         video_url = self._search_regex(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)',
  22             webpage, u'video URL')
  23         final_url = compat_urllib_parse.unquote(video_url)
  24         thumbnail_url = self._search_regex(r'<meta property="og:image" content="(.+?)" />',
  25             webpage, u'thumbnail URL')
  26         uploader = self._search_regex(r'<meta name="uploader" content="(.+?)" />',
  27             webpage, u'uploader')
  28         title = self._search_regex(r'<meta property="og:title" content="(.+?)" />',
  29             webpage, u'Video title').replace(' | eHow','')
  30         description = self._search_regex(r'<meta property="og:description" content="(.+?)" />',
  31             webpage, u'video description')
  32         ext = final_url.split('.')[-1]
  33         return [{
  34             'id':          video_id,
  35             'url':         final_url,
  36             'ext':         ext,
  37             'title':       title,
  38             'thumbnail':   thumbnail_url,
  39             'description': description,
  40             'uploader':    uploader,
  41         }]
  42