python爬取某个网站的图片并保存到本地
#coding:utf-8
import urllib
import re
import sys reload(sys)
sys.setdefaultencoding('gb2312') #获取整个页面的数据
def getHtml (url):
page = urllib.urlopen(url)
html = page.read()
return html
#保存图片到本地
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.666hdhd.com/?tz") print getImg(html)