Last active
January 1, 2016 13:09
-
-
Save daveshah/8148977 to your computer and use it in GitHub Desktop.
Crawling the clinic site for all our css yo'
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 'anemone' | |
require 'nokogiri' | |
require 'set' | |
@url = "http://my.clevelandclinic.org/default.aspx" | |
@moss_garbage = "layouts/1033/styles" | |
@css_link_set = Set.new | |
@flash_link_set = Set.new | |
@css_out_file = File.new("css_output.txt","w+") | |
@flash_out_file = File.new("flash_output.txt","w+") | |
@snips_out_file = File.new("snips_output.txt","w+") | |
def add_links_from(page) | |
Nokogiri::HTML(page.body).xpath('//link[@href]').each { |link| | |
href = link["href"] | |
if (href.include?(".css") && !href.include?(@moss_garbage)) | |
unless @css_link_set.add?(href).nil? | |
puts "CSS used = #{href}" | |
@css_out_file.puts href | |
end | |
end | |
} | |
end | |
def add_pages_with_flash_from(page) | |
Nokogiri::HTML(page.body).xpath('//object').each { |obj| | |
unless @flash_link_set.add?(page.url).nil? | |
puts "Flash found on #{page.url}" | |
@flash_out_file.puts page.url | |
end | |
} | |
end | |
def look_for_snips_on(page) | |
@snips_out_file.puts "------ BEGIN #{page.url} ------ " | |
Nokogiri::HTML(page.body).xpath('//comment()').each { |comment| | |
if(comment.to_s.include?("Snippets")) | |
puts "#{comment} on page #{page.url}" | |
@snips_out_file.puts comment | |
end | |
} | |
@snips_out_file.puts "------- END #{page.url} ------ \n" | |
end | |
def crawl(site) | |
Anemone.crawl(site) do |anemone| | |
anemone.on_every_page { |page| | |
add_links_from page | |
add_pages_with_flash_from page | |
look_for_snips_on page | |
} | |
end | |
end | |
start_time = Time.new | |
crawl(@url) | |
end_time = Time.new | |
puts "completed in #{end_time - start_time}" | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Good gravy this thing is getting ugly...