python正则匹配查询办理进度示例分享

分享原创的一段查询通行证办理进度查询的python 3.3代码,利用socket请求相关网站,获得结果后利用正则找出办理进度

[code]
import socket
import re

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'\<td class="news_font"\>([^<td]+)\</td\>', 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())