A py-spider : download the pictures of Taobao'models~

taobaoxiaomei_spider.py

#-*- coding: utf-8 -*-
#Author: toddlerya
#History: 2014/8/10
import urllib,re

num = raw_input("你要下载哪一页的淘宝小妹?\n输入一个页码: ")
web = "http://mm.taobao.com/json/request_top_list.htm?type=0&page="
url = web + str(num)

def getModelHomePage(url):
    val = urllib.urlopen(url).read()
    #print val
    modre = r'href=".*?com/\d+\.htm'
    modelre = re.compile(modre)
    modurls = modelre.findall(val)
    head = 'href="'
    for modurl in modurls:
        html = modurl[len(head):]
    return html

def getImgUrl():
    html = getModelHomePage(url)
    home = urllib.urlopen(html).read()
    imgre = r'src="\w+?.*?\.jpg'
    imglist = re.findall(imgre,home)
    return imglist

def getImage():
    imglist = getImgUrl()
    temp = 'src="'
    n =0
    for img in imglist:
        image = img[len(temp):]
        #print image
        urllib.urlretrieve(image,"pic\\mm.jpg" +str(n)+".jpg")
        print "正在下载第%s张" % n 
        n += 1
        
getImage()
print "下载完毕！"