rip images from ねこ＠ふたば <3

c.py

#!/usr/bin/env python3

########################################################################
#
# A ねこ＠ふたば image crawler
#
# License: [GPL](http://www.gnu.org/copyleft/gpl.html)
#
# Usage: ./c.py > foo.html && chromium foo.html
#
########################################################################

import lxml.html

BASE = "http://may.2chan.net/27/"

main = lxml.html.parse(BASE + "futaba.htm")
pages = [ x.get('href') for x in main.xpath('/html/body/form[2]/a') if "res" in x.get('href') ]

img_list = []
for p in pages:
    res = lxml.html.parse(BASE + p)

    # first one
    res.xpath('/html/body/form[2]/a[2]')[0].get('href')

    # the rest
    pics = res.xpath('/html/body/form[2]/table/tr/td[2]/a[3]')

    for x in pics:
        img_list.append(x.get('href'))

for img in img_list:
    print("<img src=\"" + img + "\">")