身份证名字转四六级成绩爬虫

来源:吾爱破解的ai酸的博文

https://www.52pojie.cn/thread-1112199-1-1.html

修改了一下用xlwt和xlrd批量读写只为以后方便用,详情还是上上面这个网址找原作..因为没论坛账号找不到作者..

目前时间:2020-2-22 20:04:25

#score.py
# @Time:2020.02.20
# @Author:ai酸的博文
 
from zkzh import *
from urllib.parse import quote
import requests,re,json
#import x
import xlwt,xlrd

from xlutils.copy import copy
 
class score:
    def __init__(self):
        s1 = requests.Session()
        self.s = s1
        self.url1 = 'http://cet.neea.edu.cn/cet/query_c.html'#四六级成绩查询网站
        #三个{}内分别是：4还是6   准考证号    姓名
        self.url2 = 'http://cachecloud.neea.cn/cet/query?data=CET{}_192_DANGCI%2C{}%2C{}'
        self.headers1 = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.116 Safari/537.36'}
        self.headers2 = {'Referer': 'http://cet.neea.edu.cn/cet',
                         'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.116 Safari/537.36',
                         'Host': 'cachecloud.neea.cn'}
 
    def gScore(self,name,grade,zkzhNum):
        response=None
        if name==0:
            return
        self.s.get(url=self.url1,headers=self.headers1)
        #url注意是urlencode编码
        print('test!!',name,zkzhNum)
        self.url2 = self.url2.format(grade,zkzhNum,quote(name))
        response = self.s.get(url=self.url2,headers=self.headers2)
        html = response.content.decode()
        #with open('test.html','wb') as f:
        #    f.write(response.content)
        school = re.findall('x:\'(.*?)\'',html)[0]
        score = re.findall('s:(.*?),',html)[0]
        tingLi = re.findall('l:(.*?),',html)[0]
        yueDu = re.findall('r:(.*?),',html)[0]
        xieZuoFanYi = re.findall('w:(.*?),',html)[0]
###########用xlrd和xlwt模块操作保存成表格
        data =xlrd.open_workbook(r"res.xls")
        nrows=data.sheets()[0].nrows#读取当前文件行数
        excel =copy(wb=data)#把读变成写的格式
        #workbook =xlwt.Workbook(encoding ="utf-8",style_compression=0)
        sheet = excel.get_sheet(0)
        #sheet =data.sheets()[0]
        sheet.write(nrows,0,score)
        sheet.write(nrows,1,tingLi)
        sheet.write(nrows,2,yueDu)
        sheet.write(nrows,3,xieZuoFanYi)
        sheet.write(nrows,4,name)
        excel.save('res.xls')#保存
########
        #with open()
        print(name)
        #print('学校：',school)
        print('英语'+str(grade)+'级成绩：',score)
        print('听力得分：',tingLi)
        print('阅读得分：',yueDu)
        print('写作和翻译得分：',xieZuoFanYi)
 
    def run_(self,ZKZH,name,num):
        name,num,grade,zkzhNum = zkzh.run_(ZKZH,name,num)
        #print(name,',',zkzhNum,',!!!',grade)
        self.gScore(name=name,grade=grade,zkzhNum=zkzhNum)
 
if __name__ == '__main__':
    z = zkzh()
    s = score()
    s.run_(z)

#main.py
from zkzh import *
from score import *
import xlrd

workbook = xlrd.open_workbook(r'info.xls')#读取身份证与名字的表格
sheet2 = workbook.sheet_by_index(0)

while index<sheet2.nrows:
    z = zkzh()
    s = score()
    rows = sheet2.row_values(index)
    name=rows[2]
    num=rows[3]
    index=index+1
    if not num.startswith("44"):#如果不是广东的身份证则跳过
        print(name,num,'跳过')
    else:
        print(name+'--'+num)
        s.run_(z,name,num)
#z = zkzh()
#s = score()
#s.run(z,name,num)

#zhzh.py
# @Time:2020.02.uteResultType @Author:ai酸的博文
 
import requests,random,subprocess,time,json,re,sys
 
class zkzh:
    def __init__(self):
        s1 = requests.Session()
        self.s = s1
        self.url = 'http://cet-kw.neea.edu.cn/Home/ToQueryTestTicket'
        self.headers ={'Referer': 'http://cet-kw.neea.edu.cn/Home/QueryTestTicket'
                  ,'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.116 Safari/537.36'
                  #'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.116 Safari/537.36'
                  ,'X-Requested-With': 'XMLHttpRequest'
                  ,'Origin': 'http://cet-kw.neea.edu.cn'
                  ,'Host': 'cet-kw.neea.edu.cn'}
 
    #获取准考证号
    def get(self,num,name,img):
        data = {'provinceCode': '44',#省编号，这里默认是四川51 其他的省在查询准考证号的网页源码上有,广东是44
                'IDTypeCode': '1',#证件类型，这里也是网页源码有的
                'IDNumber': num,#身份证号
                'Name': name,#姓名
                'verificationCode': img}#验证码识别
        response = self.s.post(self.url,headers=self.headers,data=data)
        html = response.content.decode()
        json_html = json.loads(html)
        ExceuteResult = json_html['ExceuteResultType']
        if ExceuteResult==1 :
            List = re.findall('"(.*?)"',json_html['Message'])
            return List[1],List[3]#List[1]是英语四或六级 List[3]是准考证号
        elif ExceuteResult==-1:
            #print('验证码输入错误ee！')
            print(json_html['Message'])
            if '验证码' in json_html['Message']:
                return 0,1
            elif '报名' in json_html['Message']:
                return 0,2
        else:
            print('未知错误！')
 
    #获取验证码图片并且读取
    def gImg(self):
        urlImg = 'http://cet-kw.neea.edu.cn/Home/VerifyCodeImg'
        response = self.s.get(url=urlImg)
        #将图片保存在本地
        with open('./img.png','wb') as f:
            f.write(response.content)
        #将保存在本地的图片使用本地默认打开方式打开
        subprocess.Popen('img.png',shell=True)#
        img = input('输入验证码：')
        return img
 
    def run_(self,name,num):
        zkzhNum=1
        while zkzhNum==1:
            img = self.gImg()
            grade,zkzhNum = self.get(num=num,name=name,img=img)
            if zkzhNum==2:
                return 0,0,0,0
        print('您的'+grade+'准考证号是：'+zkzhNum)
        if grade=='英语六级笔试':
            grade = 6
        elif grade=='英语四级笔试':
            grade = 4
        else:
            print('未知错误！')
        return name,num,grade,zkzhNum
 
if __name__ == '__main__':
    a = zkzh()
    a.run()