复制代码 代码如下:
import socket
import re

\’\’\’
广东省公安厅出入境政务服务网护照，通行证办理进度查询。
分析网址格式为 http://www.gdcrj.com/wsyw/tcustomer/tcustomer.do?&method=find&applyid=身份证号码
构造socket请求网页html，利用正则匹配出查询结果
\’\’\’
def gethtmlbyidentityid(identityid):
 s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
 host = \’www.gdcrj.com\’;
 suburl = \’/wsyw/tcustomer/tcustomer.do?&method=find&applyid={0}\’
 port = 80;

 remote_ip = socket.gethostbyname(host)
 s.connect((remote_ip , port))

 print(\’【INFO】:socket连接成功\’)

 message = \’GET \’+ suburl.format(identityid) +\’ HTTP/1.1\\r\\nHost: \’+ host +\’\\r\\n\\r\\n\’

 # str 2 bytes
 m_bytes = message.encode(\’utf-8\’)

 # send bytes
 s.sendall(m_bytes)

 print(\’【INFO】:远程下载中…\’)

 recevstr = \’\’
 while True:
  # return bytes
  recev = s.recv(4096)
  # bytes 2 str
  recevstr += recev.decode(encoding = \’utf-8\’, errors = \’ignore\’)
  if not recev:
   s.close()
   print(\’【INFO】:远程下载网页完成\’)
   break
 return recevstr

\’\’\’
利用正则表达式从上步获取的网页html内容里找出查询结果
\’\’\’
def getresultfromhtml(htmlstr):
 linebreaks = re.compile(r\’\\n\\s*\’)
 space = re.compile(\'( )+\’)
 resultReg = re.compile(r\’\\([^\’, re.MULTILINE)

 #去除换行符和空格
 htmlstr = linebreaks.sub(\’\’, htmlstr)
 htmlstr = space.sub(\’ \’, htmlstr)

 #匹配出查询结果
 result = resultReg.findall(htmlstr)
 for res in result:
  print(res.strip())

if __name__ == \’__main__\’:
 identityid = input(\’输入您的身份证号码(仅限广东省居民查询):\’)
 try:
  identityid = int(identityid)
  print(\’【INFO】:开始查询\’)
  html = gethtmlbyidentityid(identityid)
  getresultfromhtml(html)
  print(\’【INFO】:查询成功\’)
 except:
  print(\’【WARN】:输入非法\’)

 input(\’【INFO】:按任意键退出\’)