Selenium 模拟登录淘宝，获取cookies给requests使用

前言代码总结

今天爬取淘宝商品图片，遇到登录拦截，看了淘宝的登录 url 里的请求参数，好多加密，果断放弃。
不过可以用selenium模拟登录，然后获取cookies给requests使用，开整。

from selenium import webdriver
from selenium.webdriver.support import wait
from selenium.webdriver.common.by import By
import requests
from requests.cookies import RequestscookieJar
from fake_useragent import UserAgent


class SeleniumGetcookies:
    def __init__(self, user, pwd):
        self.user = user
        self.pwd = pwd

        ua = UserAgent()
        headers = {
            'User-Agent': ua.random
        }
        self.session = requests.Session()
        self.session.headers.update(headers)
		
		# 配置chrome，绕过淘宝的检测
        option = webdriver.ChromeOptions()
        # option.add_argument('--headless')    # 无头模式
        option.add_experimental_option('excludeSwitches', ['enable-automation'])
        option.add_experimental_option('useAutomationExtension', False)
        self.driver = webdriver.Chrome(options=option)
        self.driver.execute_cdp_cmd("Page.addscriptToevaluateOnNewdocument", {
            "source": """
                        Object.defineProperty(navigator, 'webdriver', {
                          get: () => undefined
                        })
                      """
        })

        self.driver.maximize_window()
        self.driver.get('https://www.taobao.com/?spm=a230r.1.0.0.2dbc56bcMjHM4u')

    def login(self):
        # 点击登录
        wait.WebDriverWait(self.driver, 5).until(
            lambda x: x.find_element(By.CSS_SELECTOR, '.site-nav-sign > a'))
        self.driver.find_element(By.CSS_SELECTOR, '.site-nav-sign > a').click()

        # 输入账号密码登录
        self.driver.find_element(By.CSS_SELECTOR, '#fm-login-id').send_keys(self.user)
        self.driver.find_element(By.CSS_SELECTOR, '#fm-login-password').send_keys(self.pwd)
        self.driver.find_element(By.CSS_SELECTOR, '.fm-btn > button').click()
	
	# 检测是否登录成功
    def inspect_login(self):
        wait.WebDriverWait(self.driver, 10).until(
            lambda x: x.find_element(By.CSS_SELECTOR, '.site-nav-user > a'))
        user = self.driver.find_element(By.CSS_SELECTOR, '.site-nav-user > a').text
        if user == '你的用户名':
            print('登录成功')
            return True
        else:
            print('登录失败')
            return False
	
	# 加载cookies给requests
    def load_to_requests(self):
        selenium_cookies = self.driver.get_cookies()
        tmp_cookies = RequestscookieJar()
        for item in selenium_cookies:
            tmp_cookies.set(item["name"], item["value"])

        self.session.cookies.update(tmp_cookies)

    def run(self):
        self.login()
        if self.inspect_login():
            self.load_to_requests()
            self.driver.close()
            self.driver.quit()
            return self.session
        else:
        	# 这里可以加登陆失败后的处理
            return False
            

直接导入SeleniumGetcookies类，运行run()函数，获取session返回给爬虫文件即可。
全部代码看这里 github地址