站长资源脚本专栏

复制代码 代码如下:
from sgmllib import SGMLParser
import urllib2

class sgm(SGMLParser):
    def reset(self):
        SGMLParser.reset(self)
        self.srcs=[]
        self.ISTRUE=True

    def start_div(self,artts):
        for k,v in artts:
            if v=="author":
                self.ISTRUE=False
    def end_div(self):
        self.ISTRUE=True
    def start_img(self,artts):
        for k,v in artts:
            if k=="src" and self.ISTRUE==True:
                self.srcs.append(v)

    def download(self):
        for src in self.srcs:
            f=open(src[-12:],"wb")
            print src
            img=urllib2.urlopen(src)
            f.write(img.read())
            f.close()
sgm=sgm()
for page in range(1,500):
    url="http://www.qiushibaike.com/late/page/%s?s=4622726" % page
    data=urllib2.urlopen(url).read()
    sgm.feed(data)
    sgm.download()