爬取贴吧图

 1 import urllib.request
 2 import re
 3 
 4 def open_url(url):
 5     req = urllib.request.Request(url)
 6     req.add_header('User-Agent', 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36')
 7     page = urllib.request.urlopen(req)
 8     html = page.read().decode('utf-8')
 9 
10     return html
11 
12 def get_img(html):
13     p = r'<img class="BDE_Image" src="([^"]+.jpg)"'
14     imglist = re.findall(p, html)
15     '''
16     for each in imglist:
17         print(each)
18     '''
19     for each in imglist:
20         filename = each.split("/")[-1]
21         urllib.request.urlretrieve(each, filename, None)
22 
23     
24 if __name__ == '__main__':    
25     url = "http://tieba.baidu.com/p/3563409202"
26     get_img(open_url(url))