一行都没打印出来就failed 打印错误信息显示global name 'url' is not defined
弱弱的问下 好多人输出了一行 我一行都没输出 打印错误信息 显示这个 global name 'url' is not defined 是哪里错了 ？
下面是我的代码
# coding=utf-8 import url_manager, html_downloader, html_parser, html_outputer class SpiderMain(object): def __init__(self): # url管理器 self.urls = url_manager.UrlManager() # 网页下载器 self.downloader = html_downloader.HtmlDownloader() # 网页下载器 self.parser = html_parser.HtmlParser() # 网页输出器 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_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 Exception as e: print e print "craw failed" self.outputer.output_html() if __name__ == "__main__": root_url = "http://baike.baidu.com/view/21087.htm" obj_spider = SpiderMain() obj_spider.craw(root_url)
