craw failed 求帮助呀
import url_manager,html_parser,html_outputer,html_downloader
class SpiterMain():
def __init__(self):
self.urls=url_manager.UrlManager()
self.downloader=html_downloader.HtmlDownloader()
self.parser=html_parser.HtmlParser()
self.outputer=html_outputer.HtmlOutputer()
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_urls))
html_cont=self.downloader.download(new_url)
new_urls,new_data=self.parser.parse(new_url,html_cont)
self.urls.add_new_urls(new_urls)
self.outputer.collect_date(new_data)
if count==1000:
break
count+=1
except:
print('craw failed')
self.outputer.output_html()
if __name__=='__main__':
root_url='https://baike.baidu.com/item/Python/407313?fr=aladdin'
obj_spider=SpiterMain()
obj_spider.craw(root_url)
这是什么原因啊,为什么一条都爬不出来