Upstream/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-15 21:57:53 +01:00
Code Issues Projects Releases Wiki Activity

[tumblr] Fix extraction (fixes #4029)

Browse Source
This commit is contained in:
Jaime Marquínez Ferrándiz 2014-10-25 22:42:56 +02:00
parent 0eb9fb9f24
commit 681b9caa9c
1 changed files with 13 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
youtube_dl/extractor/tumblr.py
View File

@ -4,9 +4,6 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
)
class TumblrIE(InfoExtractor):
@ -18,7 +15,7 @@ class TumblrIE(InfoExtractor):
'id': '54196191430',
'ext': 'mp4',
'title': 'tatiana maslany news, Orphan Black || DVD extra - behind the scenes ↳...',
'description': 'md5:dfac39636969fe6bf1caa2d50405f069',
'description': 'md5:37db8211e40b50c7c44e95da14f630b7',
'thumbnail': 're:http://.*\.jpg',
}
}, {
@ -27,7 +24,7 @@ class TumblrIE(InfoExtractor):
'info_dict': {
'id': '90208453769',
'ext': 'mp4',
'title': '5SOS STRUM ;)',
'title': '5SOS STRUM ;]',
'description': 'md5:dba62ac8639482759c8eb10ce474586a',
'thumbnail': 're:http://.*\.jpg',
}
@ -41,18 +38,12 @@ class TumblrIE(InfoExtractor):
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('Unable to extract video')
video_url = video.group('video_url')
ext = video.group('ext')
video_thumbnail = self._search_regex(
r'posters.*?\[\\x22(.*?)\\x22',
webpage, 'thumbnail', fatal=False) # We pick the first poster
if video_thumbnail:
video_thumbnail = video_thumbnail.replace('\\\\/', '/')
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
@ -63,8 +54,8 @@ class TumblrIE(InfoExtractor):
return {
'id': video_id,
'url': video_url,
'ext': 'mp4',
'title': video_title,
'description': self._html_search_meta('description', webpage),
'thumbnail': video_thumbnail,
'ext': ext,
'description': self._og_search_description(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
}