Method: ContentLinkParser#initialize

Defined in:
lib/content_link_parser.rb

#initialize(url, content, options = {}) ⇒ ContentLinkParser

Parses the content and absolutizes the urls based on url. Options can be setup to determine the links that are extracted.



8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
 
# File 'lib/content_link_parser.rb', line 8

def initialize(url, content, options = {})
  @options = {}.merge(options)
  @url = url
  @doc = Nokogiri::HTML(content)
  
  base_url = @url.to_s
  if @doc.at("base[href]")
    base_url = @doc.at("base[href]").attr("href").to_s
    @url = base_url if base_url
  end

  @options[:tags] = {}
  @options[:tags][:links] = [["a[href]", "href"], ["frame[src]", "src"], ["meta[@http-equiv=\"refresh\"]", "content"], ["link[href]:not([rel])", "href"], ["area[href]", "href"]]
  @options[:tags][:images] = [["img[src]", "src"]]
  @options[:tags][:related] = [["link[rel]", "href"]]
  @options[:tags][:scripts] = [["script[src]", "src"]]
  @options[:tags][:styles] = [["link[rel='stylesheet'][href]", "href"], ["style[@type^='text/css']", lambda{|array,tag|
    first_regex =/url\((['"]?)(.*?)\1\)/
    tag.content.scan(first_regex) {|match| array << Addressable::URI.parse(match[1]).to_s}
  }]]
  
  #clear the default tags if required
  @options[:tags] = {} if @options[:ignore_default_tags]
  @options[:tags].merge!(@options[:additional_tags]) unless @options[:additional_tags].nil?
  
end