使用python爬取百度百科python词条相关的1000个网页的标题和简介_python爬取百度百科条目的标题与内容介绍-CSDN博客

本文链接：https://blog.csdn.net/stopcpp/article/details/69946607

本文介绍了如何使用Python爬虫抓取百度百科中与Python相关的1000个页面的标题和简介。项目代码包含spider_main.py、url_manager.py、html_parser.py、html_outputer.py和html_downloader.py。在html_downloader.py中，作者发现并修复了一个错误，原本的if url in None: 应改为if url is None:，修复后程序能正确运行并避免了'NoneType'错误，爬取过程顺利完成。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

spider_main.py

# -*- coding: utf-8 -*-
from baidu_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_data(new_data)
                if count == 15:
                    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/item/Python"
    obj_spider = SpiderMain()
    obj_spider.craw(root_url)

url_manager.py

# -*- 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

html_parser.py

# -*- coding: utf-8 -*-
import re
#from urllib.parse import urlparse
import urllib.parse
from urllib import parse
from bs4 import BeautifulSoup

class HtmlParser(object):
    def parse(self, page_url, html_cont):
        if page_url is None or html_cont is None:
            return
        soup = BeautifulSoup(html_cont,"html.parser")
        new_urls = self._get_new_urls(page_url,soup)
        new_data = self._get_new_data(page_url,soup)
        return new_urls,new_data

    def _get_new_urls(self, page_url, soup):
        try:
            new_urls=set()
            links = soup.findAll('a',href=re.compile(r"^/item/"))
            for link in links:
                new_url=link['href']
                new_full_url=urllib.parse.urljoin(page_url,new_url)
                new_urls.add(new_full_url)
            return new_urls
        except Exception as e:
            print(e)
    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

html_outputer.py

# -*- coding: utf-8 -*-
class HtmlOutputer(object):
    def __init__(self):
        self.datas = []

    def collect_data(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("<head><meta http-equiv='content-type' content='text/html;charset=utf-8'></head>")
        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()

html_downloader.py

# -*- coding: utf-8 -*-
from urllib import request
class HtmlDownloader(object):
    def download(self, url):
        if url is None:
            return
        response = request.urlopen(url)
        if response.getcode() != 200:
            return
        else:
            return response.read().decode('utf-8')