spider_main中的  root_url  通过urls.get_new_url()获取的可爬取的URL

def craw(self,root_url):
        count=1
        self.urls.add_new_url(root_url)
        while self.urls.has_new_url():
            try:
                new_url=self.urls.get_new_url()
                print 'craw %d:%s' %(count,new_url)
                html_cont=self.downloader.download(new_url)
                new_urls,new_data=self.parser.parser(new_url,html_cont)
                self.urls.add_new_urls(new_urls)
                self.outputer.collect_data(new_data)

                if count==1000:
                    break
                count=count+1
            except:
                print 'craw feild'
        self.outputer.output_html()
        

if __name__=="__main__":
    root_url="http://baike.baidu.com/view/21087.htm"
    obj_spider=SpiderMain()
    obj_spider.craw(root_url)