Class: Spidy::Connector::Lightpanda

Inherits:
Object
  • Object
show all
Includes:
StaticAccessor
Defined in:
lib/spidy/connector/lightpanda.rb

Overview

Lightpanda connector for JavaScript-rendered pages via CDP Using Ferrum for direct CDP connection

Defined Under Namespace

Classes: LightpandaPage

Constant Summary collapse

DEFAULT_HOST = 
'127.0.0.1'.freeze
DEFAULT_PORT = 
9222

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(user_agent:, host: nil, port: nil) ⇒ Lightpanda

Returns a new instance of Lightpanda.



13
14
15
16
17
18
19
20
21
22
23
 
# File 'lib/spidy/connector/lightpanda.rb', line 13

def initialize(user_agent:, host: nil, port: nil)
  begin
    require 'ferrum'
  rescue LoadError
    raise 'Ferrum gem is required. Please install with: gem install ferrum'
  end

  @user_agent = user_agent
  @host = host || ENV['LIGHTPANDA_HOST'] || DEFAULT_HOST
  @port = port || ENV['LIGHTPANDA_PORT'] || DEFAULT_PORT
end

Instance Attribute Details

#host ⇒ Object (readonly)

Returns the value of attribute host.



8
9
10
 
# File 'lib/spidy/connector/lightpanda.rb', line 8

def host
  @host
end

#port ⇒ Object (readonly)

Returns the value of attribute port.



8
9
10
 
# File 'lib/spidy/connector/lightpanda.rb', line 8

def port
  @port
end

#user_agent ⇒ Object (readonly)

Returns the value of attribute user_agent.



8
9
10
 
# File 'lib/spidy/connector/lightpanda.rb', line 8

def user_agent
  @user_agent
end

Instance Method Details

#call(url) {|page| ... } ⇒ Object

Yields:

  • (page) 


25
26
27
28
29
30
31
32
33
34
35
36
37
38
 
# File 'lib/spidy/connector/lightpanda.rb', line 25

def call(url)
  fail 'url is not specified' if url.blank?

  # Clean the URL by removing any whitespace or newlines
  clean_url = url.to_s.strip

  puts "Processing URL: #{clean_url}" if ENV['DEBUG']

  # Create a page-like object similar to Mechanize
  page = fetch_with_ferrum(clean_url)

  # Apply yielder to the page
  yield(page)
end

#refresh! ⇒ Object 



40
41
42
 
# File 'lib/spidy/connector/lightpanda.rb', line 40

def refresh!
  # No special refresh actions needed for Lightpanda
end