[tumblr] Fix extraction (fixes #4029)

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

View File

@ -4,9 +4,6 @@ from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import (
ExtractorError,
)
class TumblrIE(InfoExtractor): class TumblrIE(InfoExtractor):
@ -18,7 +15,7 @@ class TumblrIE(InfoExtractor):
'id': '54196191430', 'id': '54196191430',
'ext': 'mp4', 'ext': 'mp4',
'title': 'tatiana maslany news, Orphan Black || DVD extra - behind the scenes ↳...', 'title': 'tatiana maslany news, Orphan Black || DVD extra - behind the scenes ↳...',
'description': 'md5:dfac39636969fe6bf1caa2d50405f069', 'description': 'md5:37db8211e40b50c7c44e95da14f630b7',
'thumbnail': 're:http://.*\.jpg', 'thumbnail': 're:http://.*\.jpg',
} }
}, { }, {
@ -27,7 +24,7 @@ class TumblrIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': '90208453769', 'id': '90208453769',
'ext': 'mp4', 'ext': 'mp4',
'title': '5SOS STRUM ;)', 'title': '5SOS STRUM ;]',
'description': 'md5:dba62ac8639482759c8eb10ce474586a', 'description': 'md5:dba62ac8639482759c8eb10ce474586a',
'thumbnail': 're:http://.*\.jpg', 'thumbnail': 're:http://.*\.jpg',
} }
@ -41,18 +38,12 @@ class TumblrIE(InfoExtractor):
url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id) url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id)
webpage = self._download_webpage(url, 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) iframe_url = self._search_regex(
video = re.search(re_video, webpage) r'src=\'(https?://www\.tumblr\.com/video/[^\']+)\'',
if video is None: webpage, 'iframe url')
raise ExtractorError('Unable to extract video') iframe = self._download_webpage(iframe_url, video_id)
video_url = video.group('video_url') video_url = self._search_regex(r'<source src="([^"]+)"',
ext = video.group('ext') iframe, 'video url')
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('\\\\/', '/')
# The only place where you can get a title, it's not complete, # The only place where you can get a title, it's not complete,
# but searching in other places doesn't work for all videos # but searching in other places doesn't work for all videos
@ -62,9 +53,9 @@ class TumblrIE(InfoExtractor):
return { return {
'id': video_id, 'id': video_id,
'url': video_url, 'url': video_url,
'title': video_title, 'ext': 'mp4',
'description': self._html_search_meta('description', webpage), 'title': video_title,
'thumbnail': video_thumbnail, 'description': self._og_search_description(webpage),
'ext': ext, 'thumbnail': self._og_search_thumbnail(webpage),
} }