代碼如下:
#-*- encoding: utf-8 -*-
'''
Created on 2014-4-24

@author: Leon Wong
'''

import urllib2
import urllib
import re
import time
import os
import uuid

#獲取二級頁面url
def findUrl2(html):
    re1 = r'http://tuchong.com//d+//d+/|http:///w+(?<!photos).tuchong.com//d+/'
    url2list = re.findall(re1,html)
    url2lstfltr = list(set(url2list))
    url2lstfltr.sort(key=url2list.index)
    #print url2lstfltr
    return url2lstfltr

#獲取html文本
def getHtml(url):
    html = urllib2.urlopen(url).read().decode('utf-8')#解碼為utf-8
    return html

#下載圖片到本地
def download(html_page , pageNo):  
    #定義文件夾的名字
    x = time.localtime(time.time())
    foldername = str(x.__getattribute__("tm_year"))+"-"+str(x.__getattribute__("tm_mon"))+"-"+str(x.__getattribute__("tm_mday"))
    re2=r'http://photos.tuchong.com/.+/f/.+/.jpg'
    imglist=re.findall(re2,html_page)
    print imglist
    download_img=None
    for imgurl in imglist:
        picpath = 'D://TuChong//%s//%s'  % (foldername,str(pageNo))
        filename = str(uuid.uuid1())
        if not os.path.exists(picpath):
            os.makedirs(picpath)              
        target = picpath+"http://%s.jpg" % filename
        print "The photos location is:"+target
        download_img = urllib.urlretrieve(imgurl, target)#將圖片下載到指定路徑中
        time.sleep(1)
        print(imgurl)
    return download_img

# def callback(blocknum, blocksize, totalsize):
#     '''回調函數
#     @blocknum: 已經下載的數據塊
#     @blocksize: 數據塊的大小
#     @totalsize: 遠程文件的大小
#     '''
#     print str(blocknum),str(blocksize),str(totalsize)
#     if blocknum * blocksize >= totalsize:
#         print '下載完成'

def quitit():
    print "Bye!"
    exit(0)
   

if __name__ == '__main__':
    print '''            *****************************************