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

# -*- coding:utf-8 -*-
import urllib2
import re
import urllib
# 爬取淘宝小姐姐头像

class Spider:

    def __init__(self):
        self.siteURL = "https://mm.taobao.com/json/request_top_list.htm?page="

    def getPage(self, pageIndex):
        curURL = self.siteURL + str(pageIndex)
        request = urllib2.Request(curURL)
        response = urllib2.urlopen(request)
        return response.read().decode('gbk')

    def getPageImg(self, pageIndex):
        content = self.getPage(pageIndex)
        pattern = re.compile('<div class="list-item".*?img src="(.*?)".*?<a class="lady-name".*?target="_blank">(.*?)</a>',re.S)
        find = re.findall(pattern, content)
        for item in find:
            # item[1].encode('utf-8')
            self.saveImg(item[0],item[1])

    # 根据网址和姓名命名来保存图片
    def saveImg(self, url, name):
        print "正在保存",name,"的头像到当前文件夹..."
        imgurl = "http:" + url
        # u = urllib2.urlopen(imgurl)
        u = urllib.urlopen(imgurl)
        data = u.read()
        filename = name + ".jpg"
        f = open(filename,'wb')
        f.write(data)
        f.close()


spider = Spider()
spider.getPageImg(1)