python-爬图小样

python-爬某页面图

注意：python3+版本与python2有一定区别，需要注意多点。

 1 #! /usr/bin/env python3.5.4
 2 # coding=utf-8
 3 # 爬百度某贴吧页面图
 4 
 5 import urllib.request
 6 import re
 7 
 8 
 9 def get_html(url):
10     page = urllib.request.urlopen(url)
11     htmla = page.read()
12     return htmla
13 
14 
15 def get_img(htmlb):
16     reg = r'src="(.+?.jpg)" pic_ext'
17     imgre = re.compile(reg)
18     htmlb = htmlb.decode('utf-8')  # python3.5特性,必须添加
19     imglist = re.findall(imgre, htmlb)
20     x = 0
21     for imgurl in imglist:
22         urllib.request.urlretrieve(imgurl, '%s.jpg' % x)
23         x += 1
24 
25 htmlb = get_html("http://tieba.baidu.com/p/2460150866")
26 
27 # 结尾要加换行符
28 print(get_img(htmlb))