#!/usr/bin/env python import urllib import re x=0 def getHtml(url): page = urllib.urlopen(url) html = page.read() return html def getImg(html): global x reg = 'alt=".+?" src="(.+?\.jpg)"' imgre = re.compile(reg) imglist = re.findall(imgre,html) for imgurl in imglist: urllib.urlretrieve(re.sub(r',\d+,\d+',',800,450',imgurl),"img/%s.jpg" % x) print "\n"+re.sub(r',\d+,\d+',',800,450',imgurl)+"========"+"img/%s.jpg" % x x+=1 print 'Starting...' pages = range(1,9) for p in pages: html = getHtml('http://m.lovebizhi.com/category/7655/%d/' % p) print "\n-------------------------page:%d-------------------------------" % p getImg(html) print "\nDone!"