代码中已经做详细注释,这里不再赘述了
获取cookies
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time : 2020/12/20 11:00
# @Author : huni
# @File : cookies获取.py
# @Software: PyCharm
from selenium import webdriver
from time import sleep
import json
if __name__ == '__main__':
driver = webdriver.Chrome(executable_path='./chromedriver.exe')
driver.maximize_window()
driver.get('https://passport.csdn.net/login?code=public')
sleep(2)
driver.find_element_by_xpath('/html/body/div[2]/div/div/div[1]/div[2]/div[5]/ul/li[1]/a').click()
sleep(6)
dictCookies = driver.get_cookies() # 获取list的cookies
jsonCookies = json.dumps(dictCookies) # 转换成字符串保存
with open('csdn_cookies.txt', 'w') as f:
f.write(jsonCookies)
print('cookies保存成功!')
扫码之后,再进行下面的代码
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time : 2021/1/7 17:31
# @Author : huni
# @File : 获取文章href.py
# @Software: PyCharm
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
import json
from selenium.webdriver.common.action_chains import ActionChains
from time import sleep
from lxml import etree
def browser_initial():
# chrome_options = Options()
# chrome_options.add_argument('--headless') # 无头
# chrome_options.add_argument("--window-size=1920,1080") # 屏幕大小
# browser = webdriver.Chrome(options=chrome_options)
options = webdriver.ChromeOptions()
options.add_experimental_option('excludeSwitches', ['enable-automation']