Created
February 1, 2012 20:45
-
-
Save markprovan/1719202 to your computer and use it in GitHub Desktop.
Crawler
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 'net/http' | |
require 'open-uri' | |
require 'nokogiri' | |
require 'uri' | |
class Crawler | |
attr_accessor :visited_links, :links_to_visit | |
def initialize(starting_link) | |
self.visited_links = [] | |
self.links_to_visit = [] | |
crawl(starting_link) | |
end | |
def valid_link?(link) | |
uri = URI.parse(link) | |
response = Net::HTTP.get_response(uri) | |
response.code == "200" ? true : false | |
end | |
def crawl(url) | |
if url[0] != "h" | |
self.links_to_visit.delete(url) | |
crawl(self.links_to_visit[0]) | |
end | |
doc = Nokogiri::HTML(open(url)) | |
puts "Crawling: #{url}" | |
doc.css('a').each do |link| | |
if self.visited_links.include?(link['href']) | |
self.links_to_visit.delete(link['href']) | |
else | |
self.links_to_visit << link['href'] | |
end | |
end | |
self.visited_links << url | |
crawl(self.links_to_visit[0]) | |
end | |
end | |
c = Crawler.new("http://www.vamosa.com") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment