python实现简单爬虫程序
#coding=utf-8
import re
import urllib
def getHtml(url):
page = urllib.urlopen(url)
html = page.read()
return html
def getImg(html):
reg = r'src="(.*?\.jpg)" pic_ext'
imgre = re.compile(reg)
imglist = re.findall(imgre,html)
return imglist
if __name__ == "__main__":
html = getHtml("http://tieba.baidu.com/p/2460150866")
print getImg(html)