正则表达式匹配（python）

提示：扫一扫查出行
【扫一扫了解最新限行尾号】
复制提示

获取图片的python代码

#coding=utf-8
import urllib
import redef getHtml(url):
page = urllib.urlopen(url)
html = page.read()
return htmldef 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+=1html = 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