python3.6.2实现的简单爬虫爬取百度百科

来源：互联网发布：js a href 赋值编辑：程序博客网时间：2024/05/16 06:21

话不多说，直接上代码
1.主程序代码

from baike_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 == 1000:                    break                count = count + 1            except:                print("faild")        self.outputer.output_html()if __name__=="__main__":    root_url='https://baike.baidu.com/item/Python'    obj_spider = SpiderMain()    obj_spider.craw(root_url)    print ('end')

2.url管理模块代码

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

3.html页面下载代码

import urllib.requestclass HtmlDownloader(object):    def download(self, url):        if url is None:            return None        response = urllib.request.urlopen(url)        if response.getcode() != 200:            print("acess error")            return None        return response.read().decode("utf-8")

4.html页面解析代码

import refrom bs4 import BeautifulSoupimport urllib.parseclass HtmlParser(object):    def parse(self,page_url,html_count):        if page_url is None or html_count is None:            return        soup=BeautifulSoup(html_count,'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):        new_urls=set()        links = soup.find_all('a',href=re.compile(r"/item/(.*)"))        for link in links:            new_url=link['href']            new_full_url=urllib.parse.urljoin(page_url,new_url)            #print ("the full url is",new_full_url)            new_urls.add(new_full_url)        return new_urls    def _get_new_data(self,page_url,soup):        res_data = {}        # url        res_data['url'] = page_url        # <dd class="lemmaWgt-lemmaTitle-title"><h1>Python</h1>        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

5.爬取数据输出代码

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',encoding='utf-8')        fout.write('<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">')        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'])            fout.write("<td>%s</td>" % data['summary'])            fout.write("</tr>")        fout.write("</table>")        fout.write("</body>")        fout.write("</html>")        fout.close()

好了，到这里5个部分编写完毕即可运行爬取简单的数据了。

阅读全文

1 0