Cómo usar proxies con Selenium: Guía completa

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.chrome.service import Service
from webdriver_manager.chrome import ChromeDriverManager
import zipfile, json

def create_proxy_extension(proxy_host, proxy_port, proxy_user, proxy_pass):
    manifest = {
        "version": "1.0.0", "manifest_version": 2,
        "name": "GProxy Auth",
        "permissions": ["proxy", "webRequest", "webRequestBlocking", "<all_urls>"],
        "background": {"scripts": ["background.js"]}
    }
    bg_js = f'chrome.webRequest.onAuthRequired.addListener(function(details) {{ return {{authCredentials: {{username: "{proxy_user}", password: "{proxy_pass}"}}}}; }}, {{urls: ["<all_urls>"]}}, ["blocking"]);'
    ext_path = '/tmp/proxy_auth.zip'
    with zipfile.ZipFile(ext_path, 'w') as zp:
        zp.writestr('manifest.json', json.dumps(manifest))
        zp.writestr('background.js', bg_js)
    return ext_path

opts = Options()
opts.add_argument('--proxy-server=http://proxy.gproxy.net:1000')
opts.add_extension(create_proxy_extension('proxy.gproxy.net', 1000, 'USER', 'PASS'))
driver = webdriver.Chrome(service=Service(ChromeDriverManager().install()), options=opts)
driver.get('https://httpbin.org/ip')
print(driver.find_element('tag name', 'pre').text)
driver.quit()

from selenium import webdriver
from selenium.webdriver.firefox.options import Options

opts = Options()
opts.set_preference('network.proxy.type', 1)
opts.set_preference('network.proxy.http', 'proxy.gproxy.net')
opts.set_preference('network.proxy.http_port', 1000)
opts.set_preference('network.proxy.ssl', 'proxy.gproxy.net')
opts.set_preference('network.proxy.ssl_port', 1000)
driver = webdriver.Firefox(options=opts)
driver.get('https://httpbin.org/ip')
print(driver.page_source)
driver.quit()

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from concurrent.futures import ThreadPoolExecutor

def scrape_with_proxy(url):
    opts = Options()
    opts.add_argument('--headless=new')
    opts.add_argument('--proxy-server=http://proxy.gproxy.net:1000')
    opts.add_argument('--no-sandbox')
    driver = webdriver.Chrome(options=opts)
    try:
        driver.set_page_load_timeout(30)
        driver.get(url)
        return driver.page_source
    finally:
        driver.quit()

urls = ['https://example.com/page1', 'https://example.com/page2']
with ThreadPoolExecutor(max_workers=4) as pool:
    results = list(pool.map(scrape_with_proxy, urls))