python爬虫--古诗文网的模拟登陆(验证码识别)

验证码识别登录古诗文网

请求参数:

级鹰代码:

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

import requests
from hashlib import md5

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()

def codecjy():
    chaojiying = Chaojiying_Client('tjtjtj', 'tangjian219', '902590')#用户中心>>软件ID 生成一个替换 96001
    im = open('yzm.jpg', 'rb').read()#本地图片文件路径 来替换 a.jpg 有时WIN系统须要//
    code=chaojiying.PostPic(im, 1902)['pic_str']#1902 验证码类型  官方网站>>价格体系 3.4+版 print 后要加()
    return code

爬虫程序:

import requests
from lxml import etree
session = requests.Session() #实例化一个session对象
url = 'https://so.gushiwen.org/user/login.aspx?from=http://so.gushiwen.org/user/collect.aspx' #登陆页面的url
headers={
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.97 Safari/537.36'
}
page_img_text = session.get(url=url,headers=headers).text
tree = etree.HTML(page_img_text)
img_url=tree.xpath('//*[@id="aspnetForm"]/div[4]/div[4]/img/@src')[0]  #获取验证码图片的url
new_img_url = 'https://so.gushiwen.org/'+ img_url  #验证码图片的全路径拼接

login_url = 'https://so.gushiwen.org/user/login.aspx?from=http%3a%2f%2fso.gushiwen.org%2fuser%2fcollect.aspx'  #点击登陆按钮发送的请求url
headers={
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.97 Safari/537.36'
}
img=session.get(new_img_url,headers=headers).content  #请求图片

# 对验证码图片的下载
with open('./yzm.jpg','wb') as f:
    f.write(img)
img_code = codecjy() #验证码
print(img_code)

VIEWSTATE=tree.xpath('//*[@id="__VIEWSTATE"]/@value')  #发送post请求携带的动态参数

VIEWSTATEGENERATOR=tree.xpath('//*[@id="__VIEWSTATEGENERATOR"]/@value')#发送post请求携带的动态参数

data={
    '__VIEWSTATE': VIEWSTATE,
    '__VIEWSTATEGENERATOR': VIEWSTATEGENERATOR,
    'from': 'http://so.gushiwen.org/user/collect.aspx',
    'email': '15032551128',
    'pwd': 'tangjian219',
    'code': img_cod,    #验证码
    'denglu': '登录',
}
new_page_text = session.post(url=login_url,headers=headers,data=data).text
with open('./gushiwen.html','w',encoding='utf-8') as fp:
    fp.write(new_page_text)