1
0
mirror of https://github.com/l1ving/youtube-dl synced 2024-11-30 20:02:59 +08:00
youtube-dl/youtube_dl/extractor/tumblr.py
2014-10-25 22:42:56 +02:00

62 lines
2.2 KiB
Python

# -*- coding: utf-8 -*-
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class TumblrIE(InfoExtractor):
_VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/(?:post|video)/(?P<id>[0-9]+)(?:$|[/?#])'
_TESTS = [{
'url': 'http://tatianamaslanydaily.tumblr.com/post/54196191430/orphan-black-dvd-extra-behind-the-scenes',
'md5': '479bb068e5b16462f5176a6828829767',
'info_dict': {
'id': '54196191430',
'ext': 'mp4',
'title': 'tatiana maslany news, Orphan Black || DVD extra - behind the scenes ↳...',
'description': 'md5:37db8211e40b50c7c44e95da14f630b7',
'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)
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)
iframe_url = self._search_regex(
r'src=\'(https?://www\.tumblr\.com/video/[^\']+)\'',
webpage, 'iframe url')
iframe = self._download_webpage(iframe_url, video_id)
video_url = self._search_regex(r'<source src="([^"]+)"',
iframe, 'video url')
# 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'(?s)<title>(?P<title>.*?)(?: \| Tumblr)?</title>',
webpage, 'title')
return {
'id': video_id,
'url': video_url,
'ext': 'mp4',
'title': video_title,
'description': self._og_search_description(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
}