Created
October 18, 2013 07:59
-
-
Save shouya/7038020 to your computer and use it in GitHub Desktop.
konachan picture downloader
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
require 'nokogiri' | |
require 'open-uri' | |
require 'ap' | |
BASE_URI = 'http://konachan.com/post?tags=%s' | |
link_list = [] | |
def save_list(list) | |
File.open('out.list', 'w') do |f| | |
list.each {|i| f.puts i } | |
end | |
puts 'finished, list outputed as "out.list"' | |
exit | |
end | |
trap(:INT) { save_list(link_list) } | |
tag = ARGV[0] or abort "run with '#{File.basename($0)} <tag_name>'" | |
load_page = BASE_URI % URI.encode(tag) | |
loop do | |
html = Nokogiri::HTML(open(load_page)) | |
# html = Nokogiri::HTML(open('./test.html')) | |
link_list += html.css('a.directlink').map {|x| x['href'] } | |
next_page = html.css('a.next_page')[0]['href'] rescue break | |
load_page = URI.join(BASE_URI % 'yo', next_page) or break | |
puts "loading next page, number of links read: #{link_list.length}." | |
end | |
save_list(link_list) | |
# puts html |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment