# PYTHON 2.7   Ubuntu 14.04nuswide = "$NUS-WIDE-urls_ROOT" #the location of your nus-wide-urls.txtimagepath = "$IMAGE_ROOT" # path of dataset you want to download inf = open(nuswide, 'r')url = f.readlines()import reimport urllibimport osreg = r"ImageData.+?jpg"location_re = re.compile(reg)reg = r"(ImageData.+?)/0"direction_re = re.compile(reg)reg = r"http.+?jpg"image_re = re.compile(reg)for i in url:  filename = re.findall(location_re, i)  direction = re.findall(direction_re, i)  image = re.findall(image_re, i)  if image:    path = imagepath+filename[0]    path_n = imagepath+direction[0]    print path_n    if os.path.exists(path_n):      urllib.urlretrieve(image[1], path)    else:      os.makedirs(path_n)      urllib.urlretrieve(image[1], path)

#coding=utf-8#urllib模塊提供了讀取Web頁面數據的接口import urllib#re模塊主要包含了正則表達式import re#定義一個getHtml()函數def getHtml(url):  page = urllib.urlopen(url) #urllib.urlopen()方法用于打開一個URL地址  html = page.read() #read()方法用于讀取URL上的數據  return htmldef getImg(html):  reg = r'src="(.+?/.jpg)" pic_ext'  #正則表達式，得到圖片地址  imgre = re.compile(reg)   #re.compile() 可以把正則表達式編譯成一個正則表達式對象.  imglist = re.findall(imgre,html)   #re.findall() 方法讀取html 中包含 imgre（正則表達式）的  數據  #把篩選的圖片地址通過for循環遍歷并保存到本地  #核心是urllib.urlretrieve()方法,直接將遠程數據下載到本地，圖片通過x依次遞增命名  x = 0  for imgurl in imglist:  urllib.urlretrieve(imgurl,'D:/E/%s.jpg' % x)      x+=1html = getHtml("http://tieba.baidu.com/p/xxxx")print getImg(html)