import url_manager,html_downloader,html_parser,html_outputer

class SpiderMain(object):
        """docstring for SpiderMain"""
        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():
                        print(count)

                        # 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.parse(new_url,html_cont)
                        self.urls.add_new_urls(new_urls)
                        self.outputer.collect_data(new_data)

                        # except:
                        #       print('craw failed')

                        if count == 1000:
                                break

                        count = count + 1
                        print(count)

                self.outputer.output_html()


if __name__ == "__main__":
        root_url = "https://baike.baidu.com/item/Python"
        obj_spider = SpiderMain()
        obj_spider.craw(root_url)

运行结果如下：

1

craw 1 : https://baike.baidu.com/item/Python

Traceback (most recent call last):

  File "C:\Users\liukai7\Desktop\New folder\新浪微博爬虫\spider_main.py", line 44, in <module>

    obj_spider.craw(root_url)

  File "C:\Users\liukai7\Desktop\New folder\新浪微博爬虫\spider_main.py", line 25, in craw

    new_urls,new_data = self.parser.parse(new_url,html_cont)

TypeError: 'NoneType' object is not iterable

不知道问题在哪里，请帮忙看下