基础的python抓取网站图片的例子

#-*- coding: utf-8 -*-
import re
import urllib
import urllib2
import os

class Spider:
    def downLoadImage(self, url, imageDirName):
        html = self.__getHtml(url)
        imageList = self.__getImageUrls(html)
        self.__saveImage(imageDirName, imageList)

    def __mkdir(self, dirName):
        if os.path.exists(dirName):
            print(dict, "ready exits")
        else:
            os.makedirs(dirName)

    def __getHtml(self, url):
        urlCtx = urllib.urlopen(url)
        return urlCtx.read()

    def __getImageUrls(self, html):
        rgx = re.compile(r'src="(.+?\.jpg)" pic_ext')
        imageList = rgx.findall(html)
        return  imageList

    def __saveImage(self, dirName, imageList):
        self.__mkdir(dirName)
        imageIndex = 0
        for s in imageList:
            try:
                data = urllib2.urlopen(s).read()
                fileName = dirName + str("/%d.jpg" % imageIndex)
                file = open(fileName, "wb+")
                file.write(data)
                imageIndex += 1
            except urllib2.URLError as e:
                print (e.reason)


if __name__ == "__main__":
    spider = Spider()
    spider.downLoadImage('http://tieba.baidu.com/p/2460150866', "picture")