1
0
mirror of https://github.com/l1ving/youtube-dl synced 2024-11-23 06:22:55 +08:00
youtube-dl/youtube_dl/extractor/tumblr.py
2013-06-23 22:24:07 +02:00

42 lines
1.5 KiB
Python

import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
)
class TumblrIE(InfoExtractor):
_VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/((post)|(video))/(?P<id>\d*)/(.*?)'
def _real_extract(self, url):
m_url = re.match(self._VALID_URL, url)
video_id = m_url.group('id')
blog = m_url.group('blog_name')
url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id)
webpage = self._download_webpage(url, video_id)
re_video = r'src=\\x22(?P<video_url>http://%s\.tumblr\.com/video_file/%s/(.*?))\\x22 type=\\x22video/(?P<ext>.*?)\\x22' % (blog, video_id)
video = re.search(re_video, webpage)
if video is None:
raise ExtractorError(u'Unable to extract video')
video_url = video.group('video_url')
ext = video.group('ext')
video_thumbnail = self._search_regex(r'posters(.*?)\[\\x22(?P<thumb>.*?)\\x22',
webpage, u'thumbnail', fatal=False) # We pick the first poster
if video_thumbnail: video_thumbnail = video_thumbnail.replace('\\', '')
# The only place where you can get a title, it's not complete,
# but searching in other places doesn't work for all videos
video_title = self._html_search_regex(r'<title>(?P<title>.*?)</title>',
webpage, u'title', flags=re.DOTALL)
return [{'id': video_id,
'url': video_url,
'title': video_title,
'thumbnail': video_thumbnail,
'ext': ext
}]