964b5efcd3
There are two kinds of thumbnails that need to be rewritten. First case:
new /img-master/ URLs need to be rewritten to /img-original/ URLs like this:
http://i2.pixiv.net/c/600x600/img-master/img/2014/10/04/03/59/52/46337015_p0_master1200.jpg
=> http://i2.pixiv.net/img-original/img/2014/10/04/03/59/52/46337015_p0.png
This is what `rewrite_new_medium_images` does. In order to do this, it
has to use the Pixiv API to get the correct file extension.
Second case: Old small/medium size URLs need to be rewritten to full
size URLs like this:
http://i2.pixiv.net/img18/img/evazion/14901720_m.png
=> http://i2.pixiv.net/img18/img/evazion/14901720.png
But when the medium size URL is actually for a manga image, it needs to be
rewritten to the big manga URL instead:
http://i2.pixiv.net/img04/img/syounen_no_uta/46170939_m.jpg
=> http://i2.pixiv.net/img04/img/syounen_no_uta/46170939_big_p0.jpg
But we can't tell whether it's a manga image from the URL, so we have to
use the manga page count from either the HTML page or the API to
determine whether it's part of a manga gallery.
So in order to make this work, `rewrite_old_small_and_medium_images`
takes an `is_manga` flag. `Sources::Strategies::Pixiv#get` gets the
page count from the HTML and passes the `is_manga` flag on down through
the call chain until `rewrite_old_small_and_medium_images` gets it.
When `rewrite_old_small_and_medium_images` is called from
`Downloads::Strategies::Pixiv#rewrite_thumbnails`, the `is_manga` flag
isn't passed in because we didn't scrape the HTML. This causes
`rewrite_old_small_and_medium_images` to look it up in the API instead.
79 lines
2.8 KiB
Ruby
79 lines
2.8 KiB
Ruby
module Downloads
|
|
module Strategies
|
|
class Pixiv < Base
|
|
def rewrite(url, headers)
|
|
if url =~ /https?:\/\/(?:\w+\.)?pixiv\.net/
|
|
url, headers = rewrite_headers(url, headers)
|
|
url, headers = rewrite_cdn(url, headers)
|
|
url, headers = rewrite_html_pages(url, headers)
|
|
url, headers = rewrite_thumbnails(url, headers)
|
|
url, headers = rewrite_old_small_manga_pages(url, headers)
|
|
end
|
|
|
|
return [url, headers]
|
|
end
|
|
|
|
protected
|
|
def rewrite_headers(url, headers)
|
|
headers["Referer"] = "http://www.pixiv.net"
|
|
return [url, headers]
|
|
end
|
|
|
|
# Rewrite these:
|
|
# http://www.pixiv.net/i/18557054
|
|
# http://www.pixiv.net/member_illust.php?mode=medium&illust_id=18557054
|
|
# http://www.pixiv.net/member_illust.php?mode=big&illust_id=18557054
|
|
# http://www.pixiv.net/member_illust.php?mode=manga&illust_id=18557054
|
|
# http://www.pixiv.net/member_illust.php?mode=manga_big&illust_id=18557054&page=1
|
|
# Plus this:
|
|
# i2.pixiv.net/img-inf/img/2014/09/25/00/57/24/46170939_64x64.jpg
|
|
def rewrite_html_pages(url, headers)
|
|
if url =~ /illust_id=\d+/i || url =~ %r!pixiv\.net/img-inf/img/!i
|
|
source = ::Sources::Strategies::Pixiv.new(url)
|
|
source.get
|
|
return [source.image_url, headers]
|
|
else
|
|
return [url, headers]
|
|
end
|
|
end
|
|
|
|
# Rewrite these:
|
|
# http://i2.pixiv.net/img04/img/syounen_no_uta/46170939_m.jpg
|
|
# http://i1.pixiv.net/c/600x600/img-master/img/2014/09/24/23/25/08/46168376_p0_master1200.jpg
|
|
def rewrite_thumbnails(url, headers)
|
|
source = ::Sources::Strategies::Pixiv.new(url)
|
|
url = source.rewrite_thumbnails(url)
|
|
return [url, headers]
|
|
end
|
|
|
|
# Rewrite these:
|
|
# http://i2.pixiv.net/img04/img/syounen_no_uta/46170939_p0.jpg
|
|
# http://img04.pixiv.net/img/syounen_no_uta/46170939_p0.jpg
|
|
# but not these:
|
|
# http://i2.pixiv.net/img04/img/syounen_no_uta/46170939_big_p0.jpg
|
|
# http://i1.pixiv.net/c/600x600/img-master/img/2014/09/24/23/25/08/46168376_p0_master1200.jpg
|
|
# http://i1.pixiv.net/img-original/img/2014/09/25/23/09/29/46183440_p0.jpg
|
|
def rewrite_old_small_manga_pages(url, headers)
|
|
if url !~ %r!/img-(?:original|master)/img/!i && url =~ %r!/(\d+_p\d+)\.!i
|
|
match = $1
|
|
repl = match.sub(/_p/, "_big_p")
|
|
big_url = url.sub(match, repl)
|
|
if http_exists?(big_url, headers)
|
|
url = big_url
|
|
end
|
|
end
|
|
|
|
return [url, headers]
|
|
end
|
|
|
|
def rewrite_cdn(url, headers)
|
|
if url =~ %r{https?:\/\/(?:\w+\.)?pixiv\.net\.edgesuite\.net}
|
|
url = url.sub(".edgesuite.net", "")
|
|
end
|
|
|
|
return [url, headers]
|
|
end
|
|
end
|
|
end
|
|
end
|