PublicMirrors/you-get
1
0
Fork 0
mirror of https://github.com/soimort/you-get.git synced 2025-03-12 10:20:13 +03:00
Code Issues Actions Packages Projects Releases 1 Wiki Activity

[google+] fix support for videos (image/gif is not what we want)

Browse Source
This commit is contained in:
Mort Yao 2016-02-27 23:25:51 +01:00
parent ab4ba75d2f
commit 3493437721
1 changed files with 12 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
src/you_get/extractors/google.py
View File

@ -64,33 +64,28 @@ def google_download(url, output_dir = '.', merge = True, info_only = False, **kw
post_id = r1(r'/posts/([^"]+)', html) post_id = r1(r'/posts/([^"]+)', html)
title = post_date + "_" + post_id title = post_date + "_" + post_id
if not real_urls: try:
url = "https://plus.google.com/" + r1(r'"(photos/\d+/albums/\d+/\d+)', html)
if not re.search(r'plus.google.com/photos/[^/]*/albums/\d+/\d+', url):
html = get_html(parse.unquote(url))
url = "https://plus.google.com/" + r1(r'"(photos/\d+/albums/\d+/\d+)', html)
title = r1(r'<title>([^<\n]+)', html)
else:
title = None
html = get_html(url) html = get_html(url)
temp = re.findall(r'\[(\d+),\d+,\d+,"([^"]+)"\]', html) temp = re.findall(r'\[(\d+),\d+,\d+,"([^"]+)"\]', html)
temp = sorted(temp, key = lambda x : fmt_level[x[0]]) temp = sorted(temp, key = lambda x : fmt_level[x[0]])
real_urls = [unicodize(i[1]) for i in temp if i[0] == temp[0][0]] urls = [unicodize(i[1]) for i in temp if i[0] == temp[0][0]]
assert urls
real_urls = urls # Look ma, there's really a video!
if title is None: post_url = r1(r'"(https://plus.google.com/[^/]+/posts/[^"]*)"', html)
post_url = r1(r'"(https://plus.google.com/[^/]+/posts/[^"]*)"', html) post_author = r1(r'/\+([^/]+)/posts', post_url)
post_author = r1(r'/\+([^/]+)/posts', post_url) if post_author:
if post_author: post_url = "https://plus.google.com/+%s/posts/%s" % (parse.quote(post_author), r1(r'posts/(.+)', post_url))
post_url = "https://plus.google.com/+%s/posts/%s" % (parse.quote(post_author), r1(r'posts/(.+)', post_url)) post_html = get_html(post_url)
post_html = get_html(post_url) title = r1(r'<title[^>]*>([^<\n]+)', post_html)
title = r1(r'<title[^>]*>([^<\n]+)', post_html)
if title is None: if title is None:
response = request.urlopen(request.Request(real_url)) response = request.urlopen(request.Request(real_url))
if response.headers['content-disposition']: if response.headers['content-disposition']:
filename = parse.unquote(r1(r'filename="?(.+)"?', response.headers['content-disposition'])).split('.') filename = parse.unquote(r1(r'filename="?(.+)"?', response.headers['content-disposition'])).split('.')
title = ''.join(filename[:-1]) title = ''.join(filename[:-1])
except: pass
for (i, real_url) in enumerate(real_urls): for (i, real_url) in enumerate(real_urls):
title_i = "%s[%s]" % (title, i) if len(real_urls) > 1 else title title_i = "%s[%s]" % (title, i) if len(real_urls) > 1 else title