Created
April 24, 2019 15:08
-
-
Save jpsilvashy/25ea97d20ec76551c159462e60a9f9d5 to your computer and use it in GitHub Desktop.
Use findmyfbid.com to get facebook ids from URLs
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 'selenium-webdriver' | |
module ScrapeTools | |
def self.connect(base_url) | |
loop do | |
# proxy | |
proxy = ProxyServer.get_round_robin # get a proxy that hasent been used lately | |
puts "[ScrapeTools] trying proxy: #{proxy.as_string}" | |
# profile | |
profile = Selenium::WebDriver::Firefox::Profile.new | |
profile.proxy = Selenium::WebDriver::Proxy.new(ssl: proxy.as_string) | |
# options | |
options = Selenium::WebDriver::Firefox::Options.new(args: ['-headless']) | |
options.profile = profile | |
# desired_capabilities | |
caps = Selenium::WebDriver::Remote::Capabilities.firefox | |
caps['acceptInsecureCerts'] = true | |
# driver | |
driver = Selenium::WebDriver.for :firefox, options: options, desired_capabilities: caps | |
driver.manage.timeouts.implicit_wait = 5 | |
driver.manage.timeouts.script_timeout = 30 | |
driver.manage.timeouts.page_load = 30 | |
begin | |
driver.get(base_url) | |
puts "[ScrapeTools] loaded: #{base_url}" | |
return driver | |
rescue => e | |
puts "[ScrapeTools] error: #{e.message}" | |
ensure | |
proxy.update_column(:last_used_at, Time.now) | |
end | |
end | |
end | |
end | |
module FacebookIdResolver | |
def self.get_facebook_id_for_url(facebook_profile_url) | |
driver = ScrapeTools.connect('https://findmyfbid.com/') | |
driver.find_element(css: 'form input.input-lg').send_keys(facebook_profile_url) | |
driver.find_element(css: 'form input.btn-primary').click | |
wait = Selenium::WebDriver::Wait.new(:timeout => 10) | |
wait.until { driver.find_element(css: 'h1').text == "Success!" } | |
facebook_id = driver.find_element(css: '#success-wrap code').text | |
driver.quit | |
return facebook_id | |
end | |
end | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment