[python爬虫]爬取普通话水平测试成绩(畅言网)

今天，我们的普通话考试成绩出来了（以山东为例），下午闲来无事用python写了写代码来爬了爬大家的成绩（已知姓名和身份证），方法有点暴力，敬请指点！

import urllib.request
import urllib.parse
import re
import time

#获取成绩单页的html
def get_html(txtName,txtIDCard):
    url = 'http://sd.cltt.org/Web/Login/PSCP01001.aspx'
    data = {}
    #来自Form Data,下面赋值
    data['txtName']= txtName
    data['txtIDCard']=txtIDCard
    data['btnLogin']='查  询'
    data['__VIEWSTATE']=''
    data['txtStuID']=''
    data['txtCertificateNO:']=''
    data['txtCardNO']=''

    data = urllib.parse.urlencode(data).encode('utf-8')
    response = urllib.request.urlopen(url,data)
    html = response.read().decode('utf-8')
    return html

#解析html取出个人信息
def get_result(html):

    #姓名
    name_start = html.find(r'姓名：') #起点记录查询位置    
    name_end = html.find(r'证件号：')
    name_html = html[name_start+190:name_end-186]

    #身份证
    id_start = html.find(r'证件号：') #起点记录查询位置    
    id_end = html.find(r'准考证号：')
    id_html = html[id_start+192:id_end-786]

    #等级
    level_start = html.find(r'等级：') #起点记录查询位置    
    level_end = html.find(r'证书编号：')
    level_html = html[level_start+171:level_end-169]

    #分数
    score_start = html.find(r'最终分：') #起点记录查询位置    
    score_end = html.find(r'等级：')
    score_html = html[score_start+173:score_end-280]

    #证书编号
    bookid_start = html.find(r'证书编号：') #起点记录查询位置    
    bookid_end = html.find(r'省份：')
    bookid_html = html[bookid_start+174:bookid_end-280]

    #准考证号
    k_start = html.find(r'准考证号：') #起点记录查询位置    
    k_end = html.find(r'出生日期：')
    k_html = html[k_start+173:k_end-171]
    
    #print(new_html)
    if len(name_html) < 10:
        print("--------------------------------------------------------------------------------------------------------------")
        print("姓名(id):%s(%s) | 等级:%s(%s分) | 证书编号:%s | 准考证号:%s"%(name_html,id_html,level_html,score_html,bookid_html,k_html))


    
#主函数
def main():
    #txtName = input("请输入姓名：")
    #txtIDCard = input("请输入身份证号：")
    #可以把姓名和身份证存到文件然后依次读取，由于样本太少，直接用元组了。。。
    names =  ["张三","李四","王五","赵四","狗子","二虎"]
    ids = ["3xxxxxxxxxxxxxx2","3xxxxxxxxxxxxxx0","6xxxxxxxxxxxxxx0","3xxxxxxxxxxxxxx2","3xxxxxxxxxxxxxx1X","3xxxxxxxxxxxxxx7"]
    for i in range(len(names)):
        txtName = names[i]
        txtIDCard = ids[i]
        html = get_html(txtName,txtIDCard)
        get_result(html)
        
    #print(html)
    
if __name__ == "__main__":
    main()