爬取淘宝小姐姐头像

ε=(´ο｀*)))唉  持续更新吧...

11.16更新

保存网页上的图片  并指定命名

 1 # -*- coding:utf-8 -*-
 2 import urllib2
 3 import re
 4 import urllib
 5 # 爬取淘宝小姐姐头像
 6 
 7 class Spider:
 8 
 9     def __init__(self):
10         self.siteURL = "https://mm.taobao.com/json/request_top_list.htm?page="
11 
12     def getPage(self, pageIndex):
13         curURL = self.siteURL + str(pageIndex)
14         request = urllib2.Request(curURL)
15         response = urllib2.urlopen(request)
16         return response.read().decode('gbk')
17 
18     def getPageImg(self, pageIndex):
19         content = self.getPage(pageIndex)
20         pattern = re.compile('<div class="list-item".*?img src="(.*?)".*?<a class="lady-name".*?target="_blank">(.*?)</a>',re.S)
21         find = re.findall(pattern, content)
22         for item in find:
23             # item[1].encode('utf-8')
24             self.saveImg(item[0],item[1])
25 
26     # 根据网址和姓名命名来保存图片
27     def saveImg(self, url, name):
28         print "正在保存",name,"的头像到当前文件夹..."
29         imgurl = "http:" + url
30         # u = urllib2.urlopen(imgurl)
31         u = urllib.urlopen(imgurl)
32         data = u.read()
33         filename = name + ".jpg"
34         f = open(filename,'wb')
35         f.write(data)
36         f.close()
37 
38 
39 spider = Spider()
40 spider.getPageImg(1)

 

转载于:https://www.cnblogs.com/Elaine-DWL/p/7844866.html