正则表达式匹配（python）

获取图片的python代码

#coding=utf-8
import urllib
import re

def getHtml(url):
    page = urllib.urlopen(url)
    html = page.read()
    return html

def getImg(html):
    reg = r'src="(.+?\.jpg).+"'
    imgre = re.compile(reg)
    imglist = re.findall(imgre,html)
    x = 0
    for imgurl in imglist:
        urllib.urlretrieve(imgurl,'%s.jpg' % x)
        x+=1


html = getHtml("http://www.csdn.net/article/2015-01-15/2823564")

print getImg(html)

 

findall和group的用法

import re
reg = r'www\.(.*)\..{3}'
imgre = re.compile(reg)
imglist = re.findall(imgre,'www.python.org')
#for imgurl in imglist:
print imglist

 

import re
reg = r'(.+):"(.+a)"'
imgre = re.compile(reg)
imglist = re.findall(imgre,'name:"wangjian"ok')
#for imgurl in imglist:
print imglist

 

import re
reg = r'src="(.+?\.jpg)"'
imgre = re.compile(reg)
html='<img src="http://cms.csdnimg.cn/article/201501/15/54b70da54b668_middle.jpg?_=48735" style="float: none; margin: 0px;" alt="">'
imglist = re.findall(imgre,html)
print imglist

参考https://docs.python.org/2/library/re.html#re.findall

 

python的search和match的区别

 

 

精通正则表达式第三版

解释了在正则表达式中\b元字符的使用的参考文档如下：

http://www.cnblogs.com/85538649/archive/2011/07/26/wtq0705.html

http://www.cnblogs.com/deerchao/archive/2006/08/24/zhengzhe30fengzhongjiaocheng.html