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

来源：互联网发布：2017淘宝网双11销量编辑：程序博客网时间：2024/05/01 21:35

spider_main.py

# -*- coding: utf-8 -*-from baidu_spider import url_manager, html_downloader, html_parser, html_outputerclass 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 urlparseimport urllib.parsefrom urllib import parsefrom bs4 import BeautifulSoupclass 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 requestclass 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')

想直接看效果，可以到github.com上直接下载我的baidu_spider项目
地址：https://github.com/yeshell/baidu_spider/

我自己出错在html_downloader.py，里面有个if url is None: 我写成了 if url in None: 然后运行后只出一条结果，然后报错argument of type ‘NoneType’ is not iterable。craw failed。

0 0