爬虫入门--模拟登录

概述

本文模拟登录，古诗文网，并附带关键代码。

步骤

• 1.获取登录页HTML
• 2.解析验证码url并下载保存
• 3.解析验证码（这里使用超级鹰）
• 4.模拟发起请求

注意事项

• 1.请求改为使用session发送，因为过程中可能会需要携带cookie，session会自动携带cookie

import requests
from lxml import etree
from chaojiying import Chaojiying_Client

if __name__ == '__main__':
    url = 'https://so.gushiwen.cn/user/login.aspx?from=http://so.gushiwen.cn/user/collect.aspx'
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.195 Safari/537.36'
    }

    session = requests.Session()
    page_text = session.get(url=url, headers=headers).text
    tree = etree.HTML(page_text)
    code_url = 'https://so.gushiwen.cn' + tree.xpath('//*[@id="imgCode"]/@src')[0]
    print(code_url)
    code_img = session.get(url=code_url, headers=headers).content
    with open('code.jpg', 'wb') as fp:
        fp.write(code_img)
        codeClient = Chaojiying_Client()
    code_text = codeClient.decode(1902, 'code.jpg')
    login_url = 'https://so.gushiwen.cn/user/login.aspx?from=http%3a%2f%2fso.gushiwen.cn%2fuser%2fcollect.aspx'

    data = {
        '__VIEWSTATE': tree.xpath('//*[@id="__VIEWSTATE"]/@value')[0],
        '__VIEWSTATEGENERATOR': tree.xpath('//*[@id="__VIEWSTATEGENERATOR"]/@value')[0],
        'from': 'http://so.gushiwen.cn/user/collect.aspx',
        'email': '******',
        'pwd': '******',
        'code': code_text,
        'denglu': '登录'}

    response = session.post(url=login_url, data=data, headers=headers)
    user_page_text = response.text
    print(data)
    # user_page_text.encode('gbk', 'ignore').decode('gbk')
    with open('./gushiciwang.html', 'w', encoding='utf-8') as fp:
        fp.write(user_page_text)
    print(response.status_code)
    print(response.text)