python正则表达式获取网址、IP、手机号、邮箱

#!/usr/bin/env python
#-*- coding:utf-8 -*-
import re
import sys

def getIPAddFromFile ( fobj ):
regex = re . compile ( r '\b(?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\.){3}(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\b' , re . IGNORECASE )
ipadds = re . findall ( regex , fobj )
print ipadds
return ipadds

def getPhoneNumFromFile ( fobj ):
regex = re . compile ( r '1\d{10}' , re . IGNORECASE )
phonenums = re . findall ( regex , fobj )
print phonenums
return phonenums

def getMailAddFromFile ( fobj ):
regex = re . compile ( r "\b[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,4}\b" , re . IGNORECASE )
mails = re . findall ( regex , fobj )
print mails
return mails

def getUrlFromFile ( fobj ):
regex = re . compile ( r "http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+" , re . IGNORECASE )
urls = regex . findall ( fobj )
print urls
return urls

def main ( FilefilePath ):
fobj = open ( FilefilePath , 'rb' ). read ()
urllist = getUrlFromFile ( fobj )
mailList = getMailAddFromFile ( fobj )
phoneNum = getPhoneNumFromFile ( fobj )
ipaddlist = getIPAddFromFile ( fobj )

if __name__ == '__main__' :
main ( sys . argv [ 1 ])
  • 1
    点赞
  • 5
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值