Class: Arachnid
- Inherits:
-
Object
- Object
- Arachnid
- Defined in:
- lib/arachnid.rb
Instance Method Summary collapse
- #crawl(options = {}) ⇒ Object
- #ignore_extensions(url) ⇒ Object
-
#initialize(url, options = {}) ⇒ Arachnid
constructor
A new instance of Arachnid.
- #internal_link?(url, effective_url) ⇒ Boolean
- #make_absolute(href, root) ⇒ Object
- #no_hash_in_url?(url) ⇒ Boolean
- #parse_domain(url) ⇒ Object
- #sanitize_link(url) ⇒ Object
- #split_url_at_hash(url) ⇒ Object
Constructor Details
#initialize(url, options = {}) ⇒ Arachnid
Returns a new instance of Arachnid.
11 12 13 14 15 16 17 18 19 20 |
# File 'lib/arachnid.rb', line 11 def initialize(url, = {}) @start_url = url @domain = parse_domain(url) @split_url_at_hash = [:split_url_at_hash] ? [:split_url_at_hash] : false @exclude_urls_with_hash = [:exclude_urls_with_hash] ? [:exclude_urls_with_hash] : false @exclude_urls_with_extensions = [:exclude_urls_with_extensions] ? [:exclude_urls_with_extensions] : false @debug = [:debug] ? [:debug] : false end |
Instance Method Details
#crawl(options = {}) ⇒ Object
22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 |
# File 'lib/arachnid.rb', line 22 def crawl( = {}) #defaults to 1 thread so people don't do a stupid amount of crawling on unsuspecting domains threads = [:threads] ? [:threads] : 1 #defaults to -1 so it will always keep running until it runs out of urls max_urls = [:max_urls] ? [:max_urls] : nil @hydra = Typhoeus::Hydra.new(:max_concurrency => threads) @global_visited = BloomFilter::Native.new(:size => 1000000, :hashes => 5, :seed => 1, :bucket => 8, :raise => false) @global_queue = [] @global_queue << @start_url while(@global_queue.size > 0 && (max_urls.nil? || @global_visited.size.to_i < max_urls)) temp_queue = @global_queue temp_queue.each do |q| begin request = Typhoeus::Request.new(q, :timeout => 10000, :follow_location => true) request.on_complete do |response| yield response links = Nokogiri::HTML.parse(response.body).xpath('.//a/@href') links.each do |link| if(internal_link?(link, response.effective_url) && !@global_visited.include?(make_absolute(link, response.effective_url)) && no_hash_in_url?(link) && ignore_extensions(link)) sanitized_link = sanitize_link(split_url_at_hash(link)) if(sanitized_link) absolute_link = make_absolute(sanitized_link, response.effective_url) if(absolute_link) @global_queue << absolute_link end end end end end @hydra.queue request rescue URI::InvalidURIError, NoMethodError => e puts "Exception caught: #{e}" if @debug == true end @global_visited.insert(q) @global_queue.delete(q) end @hydra.run end end |
#ignore_extensions(url) ⇒ Object
128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 |
# File 'lib/arachnid.rb', line 128 def ignore_extensions(url) return true if url.to_s.length == 0 return true unless @exclude_urls_with_extensions not_found = true @exclude_urls_with_extensions.each do |e| if(url.to_s.length > e.size && url.to_s[-e.size .. -1].downcase == e.to_s.downcase) not_found = false puts "#{e} Found At URL: #{url}" if @debug end end return not_found end |
#internal_link?(url, effective_url) ⇒ Boolean
99 100 101 102 103 104 105 106 107 108 109 |
# File 'lib/arachnid.rb', line 99 def internal_link?(url, effective_url) absolute_url = make_absolute(url, effective_url) parsed_url = parse_domain(absolute_url) if(@domain == parsed_url) return true else return false end end |
#make_absolute(href, root) ⇒ Object
152 153 154 155 156 157 158 159 |
# File 'lib/arachnid.rb', line 152 def make_absolute( href, root ) begin URI.parse(root).merge(URI.parse(split_url_at_hash(href.to_s.gsub(/\s+/, "%20")))).to_s rescue URI::InvalidURIError, URI::InvalidComponentError => e return false end end |
#no_hash_in_url?(url) ⇒ Boolean
118 119 120 121 122 123 124 125 126 |
# File 'lib/arachnid.rb', line 118 def no_hash_in_url?(url) return true unless @exclude_urls_with_hash if(url.to_s.scan(/#/).size > 0) return false else return true end end |
#parse_domain(url) ⇒ Object
82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 |
# File 'lib/arachnid.rb', line 82 def parse_domain(url) puts "Parsing URL: #{url}" if @debug begin parsed_domain = Domainatrix.parse(url) if(parsed_domain.subdomain != "") parsed_domain.subdomain + '.' + parsed_domain.domain + '.' + parsed_domain.public_suffix else parsed_domain.domain + '.' + parsed_domain.public_suffix end rescue NoMethodError, Addressable::URI::InvalidURIError => e puts "URL Parsing Exception (#{url}): #{e}" return nil end end |
#sanitize_link(url) ⇒ Object
144 145 146 147 148 149 150 |
# File 'lib/arachnid.rb', line 144 def sanitize_link(url) begin return url.gsub(/\s+/, "%20") rescue return false end end |
#split_url_at_hash(url) ⇒ Object
111 112 113 114 115 116 |
# File 'lib/arachnid.rb', line 111 def split_url_at_hash(url) return url.to_s unless @split_url_at_hash return url.to_s.split('#')[0] end |