python抓取百度百科记录

# encoding=utf8 from baike_spider import url_manager, html_downloader, html_parser,\ html_outputer 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): count = 1 self.urls.add_new_url(root_url) while self.urls.has_new_url(): #如果有未下载的url try: new_url = self.urls.get_new_url() #取一个未下载的url print 'craw %d : %s'%(count,new_url) html_cont = self.downloader.download(new_url) #由下载器下载对应的url new_urls,new_data = self.parser.parse(new_url,html_cont) #由解析器解析得到urls和data self.urls.add_new_urls(new_urls) #将新的urls加入url管理器 self.outputer.collect_data(new_data) #将新的数据收集 if count == 1000: break count = count + 1 except: print 'craw failed' self.outputer.output_html() #输出生成一个html文件 if __name__ == "__main__": # root_url = "http://baike.baidu.com/view/21087.htm" root_url = "http://baike.baidu.com/view/9936357.htm" obj_spider = SpiderMain() obj_spider.craw(root_url)