python3+ 简单爬虫笔记

import urllib.request
import re

def getHtml(url):
    html = urllib.request.urlopen(url).read()
    return html

def getImg(html):
    reg = r'src="(.+?\.jpg)" pic_ext'
    imgre = re.compile(reg)
    html = html.decode('utf-8')
    imglist = re.findall(imgre,html)

    x = 0

    for imgurl in imglist:
        urllib.request.urlretrieve(imgurl,'%s.jpg' %x)
        x += 1
    return imglist

html = getHtml("http://tieba.baidu.com/p/2460150866")
print(getImg(html))