Created
June 21, 2013 04:27
-
-
Save deatheragetr/5828797 to your computer and use it in GitHub Desktop.
crawler part 1
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
require 'nokogiri' | |
require 'open-uri' | |
class WebPage | |
attr_reader :search_frequency, :url, :links | |
@@all = [] | |
@@top_20 = [] | |
def self.sort | |
@@all.sort_by! {|page| page.search_frequency } | |
@@top_10 = @@all.first(10) | |
end | |
def self.all | |
@@all | |
end | |
def initialize(url, search_term) | |
@url = url | |
@search_term | |
@webpage = Nokogiri::HTML(open(url)) | |
@links = Links.new(@webpage, @url).urls | |
frequency_of(search_term) | |
@@all << self | |
end | |
def frequency_of(search_term) | |
search_term.downcase! | |
@search_frequency = @webpage.to_s.downcase.scan(search_term).size | |
end | |
end | |
class Links | |
attr_reader :urls | |
def initialize(webpage, url) | |
@doc = webpage | |
@url = url | |
searcher | |
urls | |
end | |
def searcher | |
@raw_urls = @doc.search('a') | |
end | |
def urls | |
@raw_urls.each do |url| | |
@urls ||= [] | |
@urls << prepend_domain(url.attr('href')) | |
end | |
@urls | |
end | |
def prepend_domain(path) | |
if path && path[0, 5] != "http:" | |
path = @url + path | |
end | |
end | |
end | |
def search_term_frequencies(*urls, search_term) | |
urls.each do |url| | |
page = WebPage.new(url, search_term) | |
puts "#{page.url}: +#{page.search_frequency} hits" | |
end | |
end | |
puts "Welcome. Search." | |
def user_interface | |
print "search term >> " | |
search_term = gets.strip | |
print "search urls(seperated by spaces)>> " | |
links = gets.strip.split | |
search_term_frequencies(*links, search_term) | |
end | |
user_interface |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment