标签:utf-8 lib reg eth def page read urllib odi
#coding=utf-8
import urllib.request
import re
def getHtml(url):
page = urllib.request.urlopen(url)
html = page.read()
return html
def getImg(html):
html = html.decode(‘utf-8‘)
reg = r‘src="(.+?\.jpg)" pic_ext‘
imgre = re.compile(reg)
imglist = re.findall(imgre,html)
x = 0
for imgurl in imglist:
urllib.request.urlretrieve(imgurl,‘%s.jpg‘ % x)
x+=1
html = getHtml("https://tieba.baidu.com/p/2460150866")
print (getImg(html))
标签:utf-8 lib reg eth def page read urllib odi
原文地址:http://www.cnblogs.com/wuhl-89/p/7491048.html