Sha256: 54fb4b2ff3690444999019ee6b794d39a3f785a58be0837a63f48b8843696301
Contents?: true
Size: 1.07 KB
Versions: 5
Compression:
Stored size: 1.07 KB
Contents
=begin class MyAwesomeProxyListParser < Janis::Parsing::WebSpecificParsers::ProxyWebsiteParser include CapybaraWithPanthomJs # optional - only if you use capybara-poltergeist for parsing def self.url # url to the proxy list website you will be parsing in the #parse method end def configure_capybara # optional - only if you use capybara-poltergeist for parsing Capybara.configure { |c| c.app_host = url } end def initialize super configure_capybara # optional - only if you use capybara-poltergeist for parsing @session = new_session # optional - only if you use capybara-poltergeist for parsing @session.visit(url) # optional - only if you use capybara-poltergeist for parsing obtain_html_doc end def parse # Your code to parse the page's content and deliver an array of strings # Those strings must have the format "IP:PORT_NUMBER" end private def obtain_html_doc # optional - Redefine the way the html document to parse is obtained if you use capybara/poltergeist @html_doc = Nokogiri.HTML(@session.html) end end =end
Version data entries
5 entries across 5 versions & 1 rubygems