使用Python抓取网页图片

ImgDownloader

import win32com.client,time,win32inet,win32file,os

class ImgDownloader:

    def __init__(self,url,dir):

        self.__dir=dir

        self.__ie=win32com.client.Dispatch('InternetExplorer.Application')

        self.__ie.Navigate(url)

        self.__wait__()



    def __wait__(self):

        while self.__ie.Busy:

            time.sleep(0.1)



    def start(self):

        self.__wait__()

        imgs=self.__ie.Document.getElementsByTagName('img')

      

        for i in range(imgs.length):

            try:

                cachInfo=win32inet.GetUrlCacheEntryInfo(imgs[i].src)

                if cachInfo:

                    path=cachInfo['LocalFileName']

                    pathinfo=path.split('\\')

                    pathinfo.reverse()

                    filename=('[%d]' % i) + pathinfo[0]

 

                    win32file.CopyFile(path,os.path.join(self.__dir,filename),True)

            except:

                pass

    def close(self):

        self.__ie.Quit()



if __name__=='__main__':

    d=ImgDownloader('http://image.baidu.com/i?ct=201326592&cl=2&lm=-1&tn=baiduimage&pv=&word=boy&z=0','c:\\temp\\')

    d.start()

    d.close()