-
-
Save pugson/777f11d9ec73d9c322cd to your computer and use it in GitHub Desktop.
This file contains hidden or 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 'openssl' | |
| require 'uri' | |
| # Uncomment next line if you don't have the Ruby SSL cert bundle installed. | |
| # OpenSSL::SSL::VERIFY_PEER = OpenSSL::SSL::VERIFY_NONE | |
| pages = ['http://psiupuxa.com/index'] | |
| images = [] | |
| puts 'Scraping pages for image links.' | |
| while page = pages.shift | |
| puts "Scraping #{page}." | |
| doc = Nokogiri::HTML(open(page)) | |
| doc.css('.post a[href*="desktop"]').each do |e| | |
| href = e['href'].to_s | |
| images << href | |
| end | |
| next_link = doc.css('.pages-link-active + a.pages-link').first | |
| if next_link | |
| next_page = next_link['href'].to_s | |
| pages << URI.join(page, next_page) | |
| end | |
| end | |
| puts "Found #{images.length} images." | |
| puts 'Downloading images.' | |
| count = 0 | |
| images.each do |url| | |
| count += 1 | |
| local_file = url.split('/').last | |
| print "[#{count}/#{images.length}] " | |
| if File.exist? local_file | |
| puts "Skipping #{local_file}, file exists." | |
| next | |
| else | |
| puts "Downloading #{local_file}." | |
| end | |
| open(url, 'rb') do |image| | |
| open(local_file, 'wb') do |file| | |
| file.write(image.read) | |
| end | |
| end | |
| end | |
| puts 'Fin.' |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment