PublicMirrors/you-get
1
0
Fork 0
mirror of https://github.com/soimort/you-get.git synced 2025-02-03 00:33:58 +03:00
Code Issues Actions Packages Projects Releases 1 Wiki Activity

[google+] extract multiple photos in a post

Browse Source
This commit is contained in:
Mort Yao 2016-02-27 22:45:08 +01:00
parent 42678d9e90
commit 9bb06c45b4
1 changed files with 38 additions and 33 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
src/you_get/extractors/google.py
View File

@ -48,6 +48,20 @@ def google_download(url, output_dir = '.', merge = True, info_only = False, **kw
if service == 'plus': # Google Plus if service == 'plus': # Google Plus
# attempt to extract images first
html = get_html(parse.unquote(url))
real_urls = []
for src in re.findall(r'src="([^"]+)"[^>]*itemprop="image"', html):
t = src.split('/')
t[0], t[-2] = t[0] or 'https:', 's0-d'
u = '/'.join(t)
real_urls.append(u)
post_date = r1(r'"(20\d\d-[01]\d-[0123]\d)"', html)
post_id = r1(r'/posts/([^"]+)', html)
title = post_date + "_" + post_id
if not real_urls:
if not re.search(r'plus.google.com/photos/[^/]*/albums/\d+/\d+', url): if not re.search(r'plus.google.com/photos/[^/]*/albums/\d+/\d+', url):
html = get_html(parse.unquote(url)) html = get_html(parse.unquote(url))
url = "https://plus.google.com/" + r1(r'"(photos/\d+/albums/\d+/\d+)', html) url = "https://plus.google.com/" + r1(r'"(photos/\d+/albums/\d+/\d+)', html)
@ -74,19 +88,10 @@ def google_download(url, output_dir = '.', merge = True, info_only = False, **kw
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])
if not real_urls:
# extract the image
# FIXME: download multple images / albums
real_urls = [r1(r'<meta property="og:image" content="([^"]+)', html)]
post_date = r1(r'"(20\d\d-[01]\d-[0123]\d)"', html)
post_id = r1(r'/posts/([^"]+)', html)
title = post_date + "_" + post_id
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
type, ext, size = url_info(real_url) type, ext, size = url_info(real_url)
if ext is None: if ext is None: ext = 'mp4'
ext = 'mp4'
print_info(site_info, title_i, ext, size) print_info(site_info, title_i, ext, size)
if not info_only: if not info_only: