# coding: utf-8
import sys
import importlib

importlib.reload(sys)
import requests
from lxml import etree
import json

baseUrl = "http://njtczs.university-hr.cn/search_zs.php"
header = {
    'user-agent': "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.141 Safari/537.36"
}
param = {
    'name_find': '',  # 考号
    'name_find2': '',  # 姓名
    'searchtype': 0,  # 0考生号 1准考证号
    'actiontype': 0
}
infoDict = {
    'name': '',
    'id_card': '',
    'gender': '',
    'nationality': '',
    'admission_time': '',
    'professional': '',
    'stu_type': '',
    'express': ''
}
if __name__ == '__main__':
    param['name_find'] = sys.argv[1]
    param['name_find2'] = sys.argv[2].encode('gbk')
    param['searchtype'] = sys.argv[3]
    response = requests.get(baseUrl, headers=header, params=param)
    response.encoding = 'gbk'  # 返回的页面是gbk编码，不加这行就会以utf-8解析，直接乱码
    page_html = response.text
    # print(page_html)
    tree = etree.HTML(page_html)
    # 学生姓名
    name = tree.xpath("/html/body/div[3]//table[3]/tr[1]/td[2]/text()")
    infoDict['name'] = ''.join(name).strip()
    # 身份证
    infoDict['id_card'] = tree.xpath("/html/body/div[3]//table[3]/tr[8]/td[2]/text()")[0].strip()
    # 性别
    infoDict['gender'] = tree.xpath("/html/body/div[3]//table[3]/tr[7]/td[2]/text()")[0].strip()
    # 民族
    infoDict['nationality'] = tree.xpath("/html/body/div[3]//table[3]/tr[7]/td[4]/text()")[0].strip()
    # 入学年份
    infoDict['admission_time'] = tree.xpath("/html/body/div[3]//table[3]/tr[2]/td[2]/text()")[0].strip()
    # 录取专业
    infoDict['professional'] = tree.xpath("/html/body/div[3]//table[3]/tr[6]/td[2]/text()")[0].strip()
    # 考生类别
    infoDict['stu_type'] = tree.xpath("/html/body/div[3]//table[3]/tr[8]/td[4]/text()")[0].strip()
    # 通知书EMS快递单号
    infoDict['express'] = tree.xpath("/html/body/div[3]//table[3]/tr[10]/td[2]/text()")[0].strip()

    print(json.dumps(infoDict, ensure_ascii=False))