Created
May 27, 2019 14:16
-
-
Save YanhaoYang/c821b4a88ac3c6a176a2157bc35df632 to your computer and use it in GitHub Desktop.
Create a crawler with Capybara
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| require 'capybara' | |
| require 'capybara/dsl' | |
| require 'selenium-webdriver' | |
| # java -jar selenium-server-standalone-3.14.0.jar | |
| # | |
| if ENV["SELENIUM_REMOTE_HOST"] | |
| Capybara.register_driver :selenium_chrome_remote do |app| | |
| args = [ | |
| "--disable-infobars", | |
| "--window-size=1024,768", | |
| ] | |
| prefs = {download: {default_directory: "~/Downloads", prompt_for_download: false}} | |
| caps = Selenium::WebDriver::Remote::Capabilities.chrome("chromeOptions" => { "args" => args, "prefs" => prefs }) | |
| Capybara::Selenium::Driver.new( | |
| app, | |
| browser: :remote, | |
| url: "http://#{ENV["SELENIUM_REMOTE_HOST"]}:4444/wd/hub", | |
| desired_capabilities: caps | |
| ) | |
| end | |
| puts "Using remote Chrome from #{ENV["SELENIUM_REMOTE_HOST"]}..." | |
| else | |
| Capybara.register_driver :selenium_chrome_remote do |app| | |
| Capybara::Selenium::Driver.load_selenium | |
| browser_options = ::Selenium::WebDriver::Chrome::Options.new | |
| browser_options.args << "--headless" | |
| browser_options.args << "--no-sandbox" | |
| browser_options.args << "--window-size=1024,768" | |
| browser_options.args << "--disable-gpu" if Gem.win_platform? | |
| client = Selenium::WebDriver::Remote::Http::Default.new | |
| client.read_timeout = 120 | |
| options = { | |
| browser: :chrome, | |
| http_client: client, | |
| options: browser_options | |
| } | |
| Capybara::Selenium::Driver.new(app, options) | |
| end | |
| end | |
| Capybara.run_server = false | |
| Capybara.current_driver = :selenium_chrome_veh | |
| Capybara.app_host = "https://google.com" | |
| class Crawler | |
| include Capybara::DSL | |
| def query(params) | |
| visit("/") | |
| return page.html | |
| end | |
| end | |
| crawler = Crawler.new | |
| item = crawler.query(item) | |
| # Notes: | |
| # Capybara.current_session.driver.browser.manage.all_cookies |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment