爬虫 spider

python 2.x

# -*- coding: utf-8 -*-
import re
import urllib

url = 'http://tieba.baidu.com/p/4872795764'
page = urllib.urlopen(url)
html = page.read()

r = 'src="(.*?.jpg)" size'         # 注意此处？的作用，取消贪婪匹配 结合findall方法，只匹配分组中的内容
imgre = re.compile(r)
imglist = re.findall(imgre, html)

count = 0
for imgurl in imglist:
    urllib.urlretrieve(imgurl, filename='mac_book Pro %s.jpg' % count)
    count += 1




函数：

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

def getimg(html):
    r = 'src="(.*?.jpg)" size'
    imgre = re.compile(r)
    imglist = re.findall(imgre, html)
    print imglist
    count = 0
    for imgurl in imglist:
        urllib.urlretrieve(imgurl, filename='mac_book_Pro_%s.jpg' % count)
        count += 1
html = gethtml('http://tieba.baidu.com/p/4872795764')
getimg(html)