lambda-ruby-selenium-activerecord

lambda-ruby-selenium-activerecord.rb

require "active_record"
require "selenium-webdriver"

ActiveRecord::Base.establish_connection(
  adapter:  "mysql2",
  host:     ENV["DB_HOST"],
  username: ENV["DB_USER"],
  password: ENV["DB_PASSWORD"],
  database: ENV["DB_NAME"]
)

class Crawler < ActiveRecord::Base
  self.table_name = 'crawler'
end

def lambda_handler(event:, context:)
  driver = setup_driver
  driver.navigate.to 'https://google.com'
  title = driver.find_element(:tag_name, 'title')

  data = Crawler.new
  data.title = title.text
  data.save
  driver.quit
end

def setup_driver
  service = Selenium::WebDriver::Service.chrome(path: '/opt/bin/chromedriver')
  client = Selenium::WebDriver::Remote::Http::Default.new
  client.read_timeout = 20 # seconds
  Selenium::WebDriver.for :chrome, service: service, options: driver_options, http_client: client
end

def driver_options
  options = Selenium::WebDriver::Chrome::Options.new(binary: '/opt/bin/headless-chromium')
  arguments = ["--headless", "--disable-gpu", "--window-size=1280x1696", "--disable-application-cache", "--disable-infobars", "--no-sandbox", "--hide-scrollbars", "--enable-logging", "--log-level=0", "--single-process", "--ignore-certificate-errors" "--homedir=/tmp"]
  arguments.each do |argument|
    options.add_argument(argument)
  end
  options
end