Python中的正则表达式

#返回pattern对象
re.compile(string[,flag])  
#以下为匹配所用函数
re.match(pattern, string[, flags])
re.search(pattern, string[, flags])
re.split(pattern, string[, maxsplit])
re.findall(pattern, string[, flags])
re.finditer(pattern, string[, flags])
re.sub(pattern, repl, string[, count])
re.subn(pattern, repl, string[, count])

# -*- coding: utf-8 -*-
 
#导入re模块
import re
 
# 将正则表达式编译成Pattern对象，注意hello前面的r的意思是“原生字符串”
pattern = re.compile(r'hello')
 
# 使用re.match匹配文本，获得匹配结果，无法匹配时将返回None
result1 = re.match(pattern,'hello')
result2 = re.match(pattern,'helloo CQC!')
result3 = re.match(pattern,'helo CQC!')
result4 = re.match(pattern,'hello CQC!')

import urllib2
import re

# create header
page = 1
url = 'http://www.qiushibaike.com/hot/page/' + str(page)
user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
headers = { 'User-Agent' : user_agent }
# get original page
request = urllib2.Request(url,headers = headers)
response = urllib2.urlopen(request).read()
# complie image and jpg tag
pattern = re.compile(r'<img\ssrc="//[^\s]*.jpg')
# find all out
result = re.findall(pattern, response)
# print result
if result:
    for r in result:
        index = len(r)
        print r[12:index]

else:
    print 'match none'