def __init__(self):
    """

    """
    self.urls = url_manager.UrlManager()
    self.downloader = html_downloader.HtmlDownloader()
    self.parser = html_parser.HtmlParser()
    self.outputer = html_outputer.HtmlOutputer()

先在这里点击UrlManager/HtmlDownloader等，按下快捷键"Alt + Enter"生成对应的类

然后再在下面的方法，按下"Alt + Enter"生成方法即可

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.parse(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 failed')

    self.outputer.output_html()