baike-spider.zip

#!/usr/bin/env python # -*- coding: utf-8 -*- """ Created on 2016-10-25 @author: xue365.taobao.com """ 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): """ 1.通过root_url抓取页面，返回new_urls和new_data 2.将new_urls时放入待抓取的集合。同时，将new_data放到outputer.datas里面 3.循环检查new_urls，抓取内容。 4.输出html结果 :param root_url: :return: """ 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.downloader(new_url) # 拿到在new_url页面爬取到的新的url（列表），以及解析出来的指定数据（词条title和词条概要） new_urls, new_data = self.parser.parse(new_url, html_cont) self.urls.add_new_urls(new_urls) # 抓取到的new_urls，放入new_urls 集合 self.outputer.collect_data(new_data) # 同时，保存new_data if count == 10: break # 抓取10个资源之后，停止爬虫 count += 1 except: 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)