最近有个需求需要爬取 GSC 的页面，先用 requests 获取页面，配合 beautifulsoup 进行解析即可，还需要搞定登录状态的问题。

用 requests 怎么都搞不定登录，Google 的技术还是非常前沿的，登录页面的js做了非常多的加密或者压缩，很难破解。最后用 Selenium 搞定了这个事情。默认的包莫名其妙会触发 Google 的反爬机制，始终提示浏览器不安全，好在找到一个专门做了针对的扩展—— undetected-chromedriver，解决了这个问题。

直接贴代码：

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions
import undetected_chromedriver.v2 as uc

chrome_options = uc.ChromeOptions()
chrome_options.add_argument("--disable-extensions")
chrome_options.add_argument("--disable-popup-blocking")
chrome_options.add_argument("--profile-directory=Default")
chrome_options.add_argument("--ignore-certificate-errors")
chrome_options.add_argument("--disable-plugins-discovery")
chrome_options.add_argument("--incognito")
chrome_options.add_argument('--no-first-run')
chrome_options.add_argument('--no-service-autorun')
chrome_options.add_argument('--no-default-browser-check')
chrome_options.add_argument('--password-store=basic')
chrome_options.add_argument('--no-sandbox')

driver = uc.Chrome(options=chrome_options, executable_path='./driver/chromedriver')

driver.delete_all_cookies()
driver.get("https://accounts.google.com/signin/v2/identifier?service=accountsettings&continue=https%3A%2F%2Fmyaccount.google.com%3Futm_source%3Daccount-marketing-page%26utm_medium%3Dgo-to-account-button&flowName=GlifWebSignIn&flowEntry=ServiceLogin")

driver.find_element_by_xpath('//input[@type="email"]').send_keys(email)
input = WebDriverWait(driver, 10).until(expected_conditions.element_to_be_clickable((By.XPATH, '//*[@id="identifierNext"]')))
input.click()

WebDriverWait(driver, 10).until(expected_conditions.element_to_be_clickable((By.XPATH, '//*[@id="password"]/div[1]/div/div[1]/input')))
driver.find_element_by_xpath('//*[@id="password"]/div[1]/div/div[1]/input').send_keys(password)

input = WebDriverWait(driver, 100).until(expected_conditions.element_to_be_clickable((By.XPATH, '//*[@id="passwordNext"]/div/button')))
input.click()
time.sleep(5)

cookies = driver.get_cookies()
cookies_arr = []
for c in cookies:
    if c['domain'].endswith('.google.com'):
        cookies_arr.append(f'{c["name"]}={c["value"]}')

driver.close()
print( "; ".join(cookies_arr))