new_urls, new_data = self.parser.parse(new_url, html_cont) TypeError: 'NoneType' object is not iterable
class Spidermain(object): 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): self.urls.add_new_url(root_url) while self.urls.has_new_url(): new_url = self.urls.get_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) self.outputer.output_html() if __name__ == "__main__": root_url = "http://baike.baidu.com/view/21087.htm" obj_spider = Spidermain() obj_spider.craw(root_url)
不太清楚问题出在哪里，请大神指点。。。
