#!/bin/env python
# -*- encoding: utf-8 -*-
#-------------------------------------------------------------------------------
# Name:        find_email.py
# Purpose:     从文本中正则匹配数据
# Author:      zhoujy
# Created:     2012-10-29
# update:      2012-10-29
#-------------------------------------------------------------------------------
import re
import fileinput
import MySQLdbconn = MySQLdb.connect(host='192.168.1.20',user='zjy',passwd='123456',db='emd',port=3308)
query = '''select content from  message e JOIN mesInfo m ON e.id=m.id WHERE m.infoType=1 and date_format(e.sendTime, "%y-%m")="12-09"'''
cursor= conn.cursor()
cursor.execute(query)
item = cursor.fetchall()pat = re.compile(r'<a href="mailto:(.*)"')
Finddict = {}#for line in fileinput.input():
for line in item:line=str(line)m = pat.search(line)if m:
#        print m.group(1)Finddict[m.group(1)] = Finddict.get(m.group(1),0)+1
List = sorted(Finddict.items(),key=lambda i: -i[1])
for kv in List:print kv[0] + ' : ' + str(kv[1])

123456@qq.com : 11
123456@126.com : 10
123456@139.com : 10
123456@yeah.net : 9
123456@cmc.edu.cn : 7
123456@sina.com : 7
123456@fudan.edu.cn : 6
.....

#!/usr/bin/env python
#-*-encoding:utf8-*-
#用正则表达式将所有<img src="XXX"> 形式中的XXX的字符串提取出import sys
import urllib2
import redef get_html(url):data = urllib2.urlopen(url).read()pat  = re.compile(r'<img src="(\S*)"') #正常情况只需要写成：r'<img src="(.*)"' ,但有些后面会带有一些长宽等属性，所以需要去除空白字符imgs = pat.findall(data)for i in imgs:print i
if __name__ == '__main__':url = sys.argv[1]get_html(url)

zhoujy@m2:~$ python get_url.py http://www.baidu.com
http://www.baidu.com/img/bdlogo.gif
http://www.baidu.com/cache/global/img/gs.gif