Class: Skrape::Page

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

Instance Method Summary collapse

Constructor Details

#initialize(url) ⇒ Page

Returns a new instance of Page.



12
13
14
15
16
17
 
# File 'lib/skrape.rb', line 12

def initialize url
  @fail_loudly = false
  @extracted_info = {}
  agent = "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Ubuntu Chromium/32.0.1700.102 Chrome/32.0.1700.102 Safari/537.36"
  @document = Nokogiri::HTML(open(url, "User-Agent" => agent))
end

Dynamic Method Handling

This class handles dynamic methods through the method_missing method

#method_missing(name, args) ⇒ Object 



29
30
31
32
33
34
35
36
37
38
39
40
 
# File 'lib/skrape.rb', line 29

def method_missing name, args
  feature_name = name.to_s.gsub('extract_', '').to_sym
  element = @document.css args[:with]
  if @fail_loudly
    raise NoElementsFoundError, "the css selector for '#{feature_name}' did not return anything" if element.empty?
  end
  if args[:and_run]
    @extracted_info[feature_name] = args[:and_run].call(element)
  else
    @extracted_info[feature_name] = element.text
  end
end

Instance Method Details

#error_when_selector_returns_nothing(value) ⇒ Object 



25
26
27
 
# File 'lib/skrape.rb', line 25

def error_when_selector_returns_nothing value
  @fail_loudly = value
end

#extract ⇒ Object 



19
20
21
22
23
 
# File 'lib/skrape.rb', line 19

def extract
  block = Proc.new
  instance_eval &block
  @extracted_info
end