Class: UrlExtractor::HTML

Inherits:
Object
  • Object
show all
Defined in:
lib/url_extractor/html.rb

Constant Summary collapse

InvalidURL = 
Class.new(StandardError)

Instance Method Summary collapse

Constructor Details

#initialize(ignore_patterns = []) ⇒ HTML

Returns a new instance of HTML.



8
9
10
 
# File 'lib/url_extractor/html.rb', line 8

def initialize(ignore_patterns = [])
  @ignore_patterns = ignore_patterns
end

Instance Method Details

#replace_urls(template) ⇒ Object 



12
13
14
15
16
17
18
19
20
21
22
23
24
 
# File 'lib/url_extractor/html.rb', line 12

def replace_urls(template)
  document = Nokogiri::HTML(template)

  document.search("a").each do |link|
    url = link['href']
    raise InvalidURL, "cannot be blank" if UrlExtractor::Util.blank_string?(url)
    next if ignored_url?(url)

    link['href'] = yield(url)
  end

  document.to_s
end