Created
March 5, 2012 22:12
-
-
Save hotchpotch/1981518 to your computer and use it in GitHub Desktop.
Photozou Scraper
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 'digest/sha1' | |
require 'pathname' | |
require 'open-uri' | |
require 'uri' | |
require 'nokogiri' | |
module PhotozouScraper | |
PHOTOZOU_URL = 'http://photozou.jp' | |
extend self | |
@cache_path = 'cache' | |
@download_path = 'download' | |
attr_accessor :cache_path, :download_path | |
def all_scrape(url) | |
path = URI.parse(url).path | |
while path = scrape(path) | |
end | |
end | |
def get_html(path) | |
cache = Pathname.new(cache_path + '/' + Digest::SHA1.hexdigest(path)) | |
cache.parent.mkpath | |
if cache.exist? | |
puts "cache exist: #{path} (#{cache})" | |
cache.read | |
else | |
puts "cache not found: #{path} (#{cache})" | |
source = open(PHOTOZOU_URL + path).read | |
cache.open('w') {|f| f.puts source } | |
source | |
end | |
end | |
def scrape(path) | |
puts "scrape start: #{path}" | |
nokogiri = Nokogiri(get_html(path)) | |
download(nokogiri) | |
next_link(nokogiri) | |
end | |
def download(nokogiri) | |
image = nokogiri.search('#indivi_media > a > img').first.attributes['src'].value | |
timestamp = image.scan(/photo\/(\d+)/).flatten.last | |
alt = nokogiri.search('#indivi_media > a > img').first.attributes['alt'].value | |
orig = original_image(image) | |
puts "downloading... #{orig}" | |
jpg = open(orig, :read_timeout => nil).read | |
path = Pathname.new("#{download_path}/#{timestamp}_#{alt}.jpg") | |
path.parent.mkpath | |
puts "save download file: #{path}" | |
path.open('wb') {|f| f.puts jpg} | |
end | |
def original_image(image) | |
image.sub(%r{(/photo/\d+)\.}, "\\1_org.") | |
end | |
def next_link(nokogiri) | |
next_link = nokogiri.search('//link[@rel="next"]') | |
unless next_link.empty? | |
next_link.first.attributes['href'].value | |
end | |
end | |
end | |
PhotozouScraper.all_scrape(ARGV.first) | |
# ./photozou_scrape.rb http://photozou.jp/photo/show/user_id/xxxxxxxxx |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment