爬虫学习1:红薯网首页的爬取

爬虫之红薯网首页的爬取(成功进行验证码识别并模拟登录成功)

核心

session = requests.Session()

代码：

#!/usr/bin/env python
# coding:utf-8

import requests
from lxml import etree
from hashlib import md5
import time

class Chaojiying_Client(object):

    def __init__(self, username, password, soft_id):
        self.username = username
        password =  password.encode('utf8')
        self.password = md5(password).hexdigest()
        self.soft_id = soft_id
        self.base_params = {
            'user': self.username,
            'pass2': self.password,
            'softid': self.soft_id,
        }
        self.headers = {
            'Connection': 'Keep-Alive',
            'User-Agent': 'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0)',
        }

    def PostPic(self, im, codetype):
        """
        im: 图片字节
        codetype: 题目类型 参考 http://www.chaojiying.com/price.html
        """
        params = {
            'codetype': codetype,
        }
        params.update(self.base_params)
        files = {'userfile': ('ccc.jpg', im)}
        r = requests.post('http://upload.chaojiying.net/Upload/Processing.php', data=params, files=files, headers=self.headers)
        return r.json()

    def ReportError(self, im_id):
        """
        im_id:报错题目的图片ID
        """
        params = {
            'id': im_id,
        }
        params.update(self.base_params)
        r = requests.post('http://upload.chaojiying.net/Upload/ReportError.php', data=params, headers=self.headers)
        return r.json()


if __name__ == "__main__":
    #准备一个UA伪装
    headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.77 Safari/537.36'
    }
    #对需要识别的图片进行请求
    url = 'https://i.hongshu.com/userverify.html?1624113370734'
    #得到二进制文本的图片
    img_data_text = requests.get(url = url,headers = headers).content
    #对图片进行存储
    with open('./a.jpg','wb') as fp:
        fp.write(img_data_text)

    #利用超级鹰进行识别
    chaojiying = Chaojiying_Client('user-name', 'passwd', '918582')  # 用户中心>>软件ID 生成一个替换 96001
    im = open('a.jpg', 'rb').read()  # 本地图片文件路径 来替换 a.jpg 有时WIN系统须要//
    print(chaojiying.PostPic(im, 1902))  # 1902 验证码类型  官方网站>>价格体系 3.4+版 print 后要加()

    #准备需要登录的url
    url = 'https://i.hongshu.com/login.html'
    #读取我们刚刚识别到的结果
    result = chaojiying.PostPic(im, 1902)['pic_str']
    print(result)
    post_data = {
    'username': '',
    'password': '',
    'validcode': result,
    'url': 'https://i.hongshu.com/login.html?url=https%3A%2F%2Fi.hongshu.com%2Fprofile%2Faccount.do',
    'sign': '1',
    'logining': '1'
    }

    #得到网页的源码数据
    #使用保持页面的方法进行post请求
    session = requests.Session()
    response = session.post(url=url,data=post_data,headers=headers)
    print(response.status_code)

    #由于进行了重定向，所以我们需要重新去get一下这个网页
    url = 'https://i.hongshu.com/profile/center.do'

    res = session.get(url=url,headers=headers)
    print(res.status_code)

    text_data = res.text
    print(text_data)
    with open('./hongshu.html','w',encoding='utf-8') as fp:
        fp.write(text_data)
    print("爬取完成！")