+# -*- coding: utf-8 -*-
from __future__ import unicode_literals
import re
class TumblrIE(InfoExtractor):
_VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/((post)|(video))/(?P<id>\d*)($|/)'
- _TEST = {
+ _TESTS = [{
'url': 'http://tatianamaslanydaily.tumblr.com/post/54196191430/orphan-black-dvd-extra-behind-the-scenes',
- 'file': '54196191430.mp4',
'md5': '479bb068e5b16462f5176a6828829767',
'info_dict': {
- "title": "tatiana maslany news"
+ 'id': '54196191430',
+ 'ext': 'mp4',
+ 'title': 'tatiana maslany news, Orphan Black || DVD extra - behind the scenes ↳...',
+ 'description': 'md5:dfac39636969fe6bf1caa2d50405f069',
+ 'thumbnail': 're:http://.*\.jpg',
}
- }
+ }, {
+ 'url': 'http://5sostrum.tumblr.com/post/90208453769/yall-forgetting-the-greatest-keek-of-them-all',
+ 'md5': 'bf348ef8c0ef84fbf1cbd6fa6e000359',
+ 'info_dict': {
+ 'id': '90208453769',
+ 'ext': 'mp4',
+ 'title': '5SOS STRUM ;)',
+ 'description': 'md5:dba62ac8639482759c8eb10ce474586a',
+ 'thumbnail': 're:http://.*\.jpg',
+ }
+ }]
def _real_extract(self, url):
m_url = re.match(self._VALID_URL, url)
return [{'id': video_id,
'url': video_url,
'title': video_title,
+ 'description': self._html_search_meta('description', webpage),
'thumbnail': video_thumbnail,
'ext': ext
}]