# 详解（一）Python + Selenium 批量采集微信公众号，搭建自己的微信公众号每日AI简报，告别信息焦虑
# https://blog.csdn.net/k352733625/article/details/149222945

# 微信爬爬猫---公众号文章抓取代码分析
# https://blog.csdn.net/yajuanpi4899/article/details/121584268

import json
import logging

from torch.distributed.elastic.timer import expires

"""
# 查看selenium版本
pip show selenium
4.34.2

# 查看Chrome浏览器版本
chrome://version/
138.0.7204.101 (正式版本) （64 位）

# 下载驱动包
https://googlechromelabs.github.io/chrome-for-testing/
https://storage.googleapis.com/chrome-for-testing-public/138.0.7204.94/win64/chromedriver-win64.zip
"""
import time
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.chrome.service import Service as ChromeService

if __name__ == '__main__':
    # 定义一个空的字典，存放cookies内容
    cookies = {}
    # 设置headers - 使用微信内置浏览器的User-Agent
    header = {
        "HOST": "mp.weixin.qq.com",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.116 Safari/537.36 QBCore/4.0.1301.400 QQBrowser/9.0.2524.400 Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2875.116 Safari/537.36 NetType/WIFI MicroMessenger/7.0.20.1781(0x6700143B) WindowsWechat(0x63010200)",
        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
        "Accept-Encoding": "gzip, deflate, br",
        "Accept-Language": "zh-CN,zh;q=0.8,en-US;q=0.6,en;q=0.5;q=0.4",
        "Connection": "keep-alive"
    }
    # 用webdriver启动谷歌浏览器
    logging.info("启动浏览器，打开微信公众号登录界面")
    options = Options()

    service = ChromeService(executable_path=r"C:\Windows\System32\chromedriver.exe")
    driver = webdriver.Chrome(service=service, options=options)
    # 打开微信公众号登录页面
    driver.get('https://mp.weixin.qq.com/')
    # 等待5秒钟
    time.sleep(2)
    # # 拿手机扫二维码！
    logging.info("请拿手机扫码二维码登录公众号")
    time.sleep(20)

    # 重新载入公众号登录页，登录之后会显示公众号后台首页，从这个返回内容中获取cookies信息
    driver.get('https://mp.weixin.qq.com/')
    # 获取cookies
    cookie_items = driver.get_cookies()
    expiry=-1
    # 获取到的cookies是列表形式，将cookies转成json形式并存入本地名为cookie的文本中
    for cookie_item in cookie_items:
        cookies[cookie_item['name']] = cookie_item['value']
        if('expiry' in cookie_item and cookie_item['expiry'] > expiry):
            expiry = cookie_item['expiry']

    if "slave_sid" not in cookies:
        logging.info("登录公众号失败，获取cookie失败")
        exit()

    # 将cookies写入文件
    cookies["expiry"] = expiry
    with open('cookies.txt', mode='w', encoding="utf-8") as f:
        f.write(json.dumps(cookies, indent=4, ensure_ascii=False))
    # 关闭浏览器
    driver.quit()
    # 输出提示
    print("成功获取了cookies内容！")