为了账号安全,请及时绑定邮箱和手机立即绑定

代码是按照视频中来的,但是运行还是报错。。。。。。。

代码是按照视频中来的

main:
# -*- coding: utf-8 -*-
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():
            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_date(new_data)
                 
                if count==100:
                    break
                 
                count=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)  
管理器:
# -*- coding: utf-8 -*- 
class UrlManager(object):
    def __init__(self):
        self.new_urls=set()
        self.old_urls=set()
                
    def add_new_url(self,url):
        if url is None:
            return 
        if url not in self.new_urls and url not in self.old_urls:
            self.new_urls.add(url)
        
    def add_new_urls(self,urls):
        if urls is None or len(urls)==0:
            return 
        for url in urls:
            self.add_new_url(url)
                   
    def has_new_url(self):
        return  len(self.new_urls)!=0
      
    def get_new_url(self):
        new_url=self.new_urls.pop()
        self.old_urls.add(new_url)
        return new_url
下载器:
# -*- coding: utf-8 -*- 
import urllib2
class HtmlDownloader(object):
    def download(self,url):
        if url is None:
            return None
        response=urllib2.urlopen(url)
        if response.getcode()!=200:
            return None
        return response.read()
解析器:
# -*- coding: utf-8 -*- 
from bs4 import BeautifulSoup
import re,urlparse
class HtmlParser(object):
    def _get_new_urls(self,page_url,soup):
        new_urls=set()
        links=soup.find_all('a',href=re.compile(r"/view/\d+\.htm"))  
        for link in links:
            new_url=link['href']
            new_full_url=urlparse.urljoin(page_url,new_url)
            new_urls.add(new_full_url)
        return new_urls
                   
    def _get_new_data(self,page_url,soup):
        res_data ={}
        
        res_data['url']=page_url
        
        title_node=soup.find('dd',class_="lemmaWgt-lemmaTitle-title").find("h1")
        res_data ['title']=title_node.get_text()
       
        summary_node=soup.find('div',class_="lemma-summary")
        res_data ['summary']=summary_node.get_text()
        
        return res_data
        
    def parser(self,page_url,html_cont):
        if page_url is None or html_cont is None:
            return 
        soup=BeautifulSoup(html_cont,'html.parser',from_encoding='utf-8')
        new_urls=self._get_new_urls(page_url,soup)
        new_data=self._get_new_data(page_url,soup)
        return new_urls,new_data
输出器:
# -*- coding: utf-8 -*- 
class HtmlOutputer(object):
    def __init___(self):
        self.datas=[]
           
    def collect_date(self,data):
        if data is None:
            return 
        self.datas.append(data)
      
    def output_html(self):
        fout=open('output.html','w')
        fout.write("<html>")
        fout.write("<body>")
        fout.write("<table>")
        
        for data in self.datas:
            fout.write("<tr>")
            fout.write("<td>%s</td>"% data['url'])
            fout.write("<td>%s</td>"% data['title'].encode('utf-8'))
            fout.write("<td>%s</td>"% data['summary'].encode('utf-8'))
            fout.write("</tr>")
        fout.write("</table>")
        fout.write("</body>")
        fout.write("</html>")
        fout.close()

http://img1.sycdn.imooc.com//57ee1d820001610a10840620.jpg

正在回答

2 回答

看起来确实是,你的__init___中,后面多了个下划线

0 回复 有任何疑惑可以回复我~

输出器的代码写错了,报错在输出器的17行,说不认识datas这个属性;datas是在init中写的,你的init方法的名称写错了,不知道是__init__前面少了一个下划线还是后面多了一个下划线


0 回复 有任何疑惑可以回复我~

举报

0/150
提交
取消
Python开发简单爬虫
  • 参与学习       227670    人
  • 解答问题       1219    个

本教程带您解开python爬虫这门神奇技术的面纱

进入课程

代码是按照视频中来的,但是运行还是报错。。。。。。。

我要回答 关注问题
意见反馈 帮助中心 APP下载
官方微信