PublicMirrors/you-get
1
0
Fork 0
mirror of https://github.com/soimort/you-get.git synced 2025-01-23 21:45:02 +03:00
Code Issues Actions Packages Projects Releases 1 Wiki Activity

[tumblr] fix for embedded vimeo videos

Browse Source
This commit is contained in:
Mort Yao 2015-12-13 03:31:09 +01:00
parent 6cbf9bd0e5
commit 7f895973d4
1 changed files with 32 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
src/you_get/extractors/tumblr.py
View File

@ -4,6 +4,7 @@ __all__ = ['tumblr_download']
from ..common import *
from .universal import *
from .vimeo import vimeo_download
def tumblr_download(url, output_dir='.', merge=True, info_only=False, **kwargs):
if re.match(r'https?://\d+\.media\.tumblr\.com/', url):
@ -14,6 +15,7 @@ def tumblr_download(url, output_dir='.', merge=True, info_only=False, **kwargs):
feed = r1(r'<meta property="og:type" content="tumblr-feed:(\w+)" />', html)
if feed in ['photo', 'photoset'] or feed is None:
# try to extract photos
page_title = r1(r'<meta name="description" content="([^"\n]+)', html) or \
r1(r'<meta property="og:description" content="([^"\n]+)', html) or \
r1(r'<title>([^<\n]*)', html)
@ -38,30 +40,39 @@ def tumblr_download(url, output_dir='.', merge=True, info_only=False, **kwargs):
'size': size,
}
size = sum([tuggles[t]['size'] for t in tuggles])
print_info(site_info, page_title, None, size)
if tuggles:
size = sum([tuggles[t]['size'] for t in tuggles])
print_info(site_info, page_title, None, size)
if not info_only:
for t in tuggles:
title = tuggles[t]['title']
ext = tuggles[t]['ext']
size = tuggles[t]['size']
url = tuggles[t]['url']
print_info(site_info, title, ext, size)
download_urls([url], title, ext, size,
output_dir=output_dir)
return
if not info_only:
for t in tuggles:
title = tuggles[t]['title']
ext = tuggles[t]['ext']
size = tuggles[t]['size']
url = tuggles[t]['url']
print_info(site_info, title, ext, size)
download_urls([url], title, ext, size,
output_dir=output_dir)
return
elif feed == 'audio':
real_url = r1(r'source src=\\x22([^\\]+)\\', html)
if not real_url:
real_url = r1(r'audio_file=([^&]+)&', html) + '?plead=please-dont-download-this-or-our-lawyers-wont-let-us-host-audio'
elif feed == 'video':
iframe_url = r1(r'<iframe src=\'([^\']*)\'', html)
iframe_html = get_html(iframe_url)
real_url = r1(r'<source src="([^"]*)"', iframe_html)
else:
# feed == 'audio' or feed == 'video' or feed is None
# try to extract video / audio
real_url = r1(r'source src=\\x22([^\\]+)\\', html)
if not real_url:
real_url = r1(r'audio_file=([^&]+)&', html)
if real_url:
real_url = real_url + '?plead=please-dont-download-this-or-our-lawyers-wont-let-us-host-audio'
if not real_url:
real_url = r1(r'<source src="([^"]*)"', html)
if not real_url:
iframe_url = r1(r'<iframe src=[\'"]([^\'"]*)[\'"]', html)
if re.search(r'player\.vimeo\.com', iframe_url):
vimeo_download(iframe_url, output_dir, merge=merge, info_only=info_only,
referer='http://tumblr.com/')
return
else:
iframe_html = get_content(iframe_url)
real_url = r1(r'<source src="([^"]*)"', iframe_html)
title = unescape_html(r1(r'<meta property="og:title" content="([^"]*)" />', html) or
r1(r'<meta property="og:description" content="([^"]*)" />', html) or