Created
August 4, 2011 16:09
-
-
Save varnie/1125528 to your computer and use it in GitHub Desktop.
Three ways of handling images from the net using Ruby
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
#!/usr/bin/env ruby | |
require 'open-uri' | |
require 'pool' #taken fron http://burgestrand.se/code/ruby-thread-pool/ | |
IMG_REGEXP = /\<img[^(src)]*src=(\"|\')((http:\/\/)?[\w\.\/:-]+)\1[^\\>]*\\?\>/ | |
VALID_IMAGE_EXTENSION_REGEXP = /.*\.(gif|tif|png|jpeg|jpg)$/ | |
def image_extension_correct?(image) | |
not image.nil? and image =~ VALID_IMAGE_EXTENSION_REGEXP | |
end | |
def grab_images_by_hand(address) | |
result = [] | |
content = open(address) do |f| | |
data = f.read | |
data.scan(IMG_REGEXP) do |img| | |
img_src = img[1] | |
next if not image_extension_correct?(img_src) | |
img_src = (address + img_src) unless img_src.start_with?('http://') | |
result << img_src | |
end | |
end | |
result | |
end | |
def grab_images_using_hpricot(address) | |
require 'rubygems' | |
require 'hpricot' | |
result = [] | |
doc = Hpricot(open(address)) | |
doc.search("img").each do |img| | |
img_src = img.attributes['src'] | |
next if not image_extension_correct?(img_src) | |
img_src = (address + img_src) unless img_src.start_with?('http://') | |
result << img_src | |
end | |
result | |
end | |
def grab_images_using_nokogiri(address) | |
require 'rubygems' | |
require 'nokogiri' | |
result = [] | |
doc = Nokogiri::HTML(open(address)) | |
doc.xpath('//img').each do |node| | |
img_src = node.attribute('src').text | |
next if not image_extension_correct?(img_src) | |
img_src = (address + img_src) unless img_src.start_with?('http://') | |
result << img_src | |
end | |
result | |
end | |
def usage | |
puts "Usage: URL destination_folder" | |
exit 0 | |
end | |
def process(url, dstFolder) | |
url.chop! if url.end_with?('/') | |
url = ('http://' + url) unless url.start_with?('http://') | |
images = grab_images_by_hand(url) | |
count = 0 | |
pool = Pool.new(25) | |
images.each do |img_src| | |
pool.schedule do | |
print '.' | |
last_slash_index = img_src.rindex('/') | |
img_name = last_slash_index ? img_src[last_slash_index+1, img_src.length] : img_src | |
begin | |
img_body = open(img_src).read | |
File.open(File.join(dstFolder, img_name), 'wb') do |f| | |
f.puts img_body | |
count+= 1 | |
end | |
rescue Exception => e | |
puts "an exception: #{e}" | |
end | |
end | |
end | |
at_exit{ pool.shutdown; puts "downloaded #{count} images into #{dstFolder} folder" } | |
end | |
######################################################################## | |
if ARGV.length == 0 | |
usage | |
exit 0 | |
end | |
url = ARGV[0].chomp | |
dstFolder = ARGV[1].chomp | |
if url.empty? or dstFolder.empty? | |
usage | |
exit 0 | |
end | |
if not File.exists?(dstFolder) | |
Dir.mkdir(dstFolder) | |
end | |
if not File.directory?(dstFolder) | |
puts '#{dstFolder} is not a folder' | |
else | |
process(url, dstFolder) | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment