# !/usr/bin/python
# -*- coding: UTF-8 -*-
import re
import urllib
# 获取网页信息
def getHtml(url):
page = urllib.urlopen(url)
html = page.read()
print html
return html
def getImg(html):
# 匹配网页中的图片
reg = r'src="(.*?\.jpg)" alt'
imgre = re.compile(reg)
imglist = re.findall(imgre, html)
x = 0
for imgurl in imglist:
print imgurl
urllib.urlretrieve(imgurl, '%s.jpg' % x)
x += 1
# html2 = getHtml("https://tieba.baidu.com/p/3901139917")
html3 = getHtml("http://photo.bitauto.com/?WT.mc_id=360tpdq")
print getImg(html3)
Python爬取网页图片01
猜你喜欢
转载自blog.csdn.net/u011106915/article/details/78313488
今日推荐
周排行