Created
June 26, 2014 01:54
-
-
Save chaserx/de1761db2af79d516dcf to your computer and use it in GitHub Desktop.
download all images from a web page via img src using nokogiri and mechanize
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 'rubygems' | |
require 'nokogiri' | |
require 'open-uri' | |
require 'uri' | |
require 'mechanize' | |
require 'pathname' | |
# inspired by: http://stackoverflow.com/a/7933585/281699 | |
class Downloader | |
def make_absolute href, root | |
URI.parse(root).merge(URI.parse(href)).to_s | |
end | |
def get_images_from_url url, destination='~/Desktop/nest' | |
begin | |
webpage = Nokogiri::HTML(open(url)) | |
rescue OpenURI::HTTPError => e | |
if e.message == '404 Not Found' | |
puts "Not Found" | |
return | |
else | |
raise e, "#{e.message}" | |
end | |
rescue => e | |
raise e, "#{e.message}" | |
end | |
webpage.xpath("//img/@src").each do |src| | |
uri = make_absolute(src,url) | |
final_destination = File.join(File.expand_path(destination), File.basename(uri)) | |
begin | |
next if File.exists? final_destination | |
puts "Getting: #{uri}" | |
agent = Mechanize.new | |
agent.get(uri).save final_destination | |
rescue => e | |
puts "The request for a page at #{uri} returned an error. #{e.message}" | |
next | |
end | |
end | |
end | |
end | |
URLs = [ | |
'http://example.com' | |
] | |
URLs.each do |url| | |
Downloader.new.get_images_from_url url | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment