Python爬虫模拟真实登录案例系列之十二

一个模拟真实登录案例

import time
import requests
from bs4 import BeautifulSoup


def captcha(data):
    with open("captcha.png", "wb") as f:
        f.write(data)
    # 返回输入的验证码字符串
    return input("请输入验证码：")


def login():
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.115 Safari/537.36"}

    ssion = requests.session()
    # 获取登录页面的数据, URL地址不可变
    html = ssion.get("https://www.zhihu.com/", headers=headers).content
    # 提取html文件，指定lxml文件解析器
    soup = BeautifulSoup(html, "lxml")
    # 提取_xsrf值
    _xsrf = soup.find('input', attrs={"name": "_xsrf"}).get("value")

    # 处理验证码url地址
    captchaURL = "https://www.zhihu.com/captcha.gif?r=%d&type=login" % (time.time() * 1000)

    # 发送验证码图片的请求，返回图片数据
    captcha_data = ssion.get(captchaURL, headers=headers).content

    # post登录表单数据
    formdata = {
        "email": "123456789@qq.com",
        "password": "ABCDEFG",
        "captcha": captcha(captcha_data),
        "_xsrf": _xsrf
    }

    # 发送post登录请求，拿到cookie，URL地址不能变
    ssion.post("https://www.zhihu.com/login/email", data=formdata, headers=headers)

    # 访问登录之后页面，并保存到本地
    html = ssion.get("https://www.zhihu.com/settings/account#signin", headers=headers).content

    with open("myhtml.html", "w") as f:
        f.write(str(html.decode('utf-8')))


if __name__ == "__main__":
    login()