python提取知乎当前最热的问答内容

#-*- coding: utf-8 -*-
import urllib.request
import re
from _io import open
def yunpan_search():
 url = "https://www.zhihu.com/explore"
 req = urllib.request.Request(url, headers = {
 'Connection': 'Keep-Alive',
 'Accept': 'text/html, application/xhtml+xml, */*',
 'Accept-Language': 'en-US,en;q=0.8,zh-Hans-CN;q=0.5,zh-Hans;q=0.3',
 'User-Agent': 'Mozilla/5.0 (Windows NT 6.3; WOW64; Trident/7.0; rv:11.0) like Gecko'
})
 opener = urllib.request.urlopen(req)
 html = opener.read()
 html = html.decode('utf-8')
 rex = '(?<=).*?(?=)'
 m = re.findall(rex,html,re.S)
 f = open('/root/Desktop/zhihu.txt','w')
 for i in m:
 f.write(i)
 f.write('

')
 f.close()
 print("抓取成功!")
 file = open('/root/Desktop/zhihu.txt','r+')
 fullfile = file.readlines()
 text = []
 p = re.compile(r'w*', re.L)
 pp = re.compile(r"(&;)*")
 for line in fullfile:
 lines = p.sub('',line)
 liness = pp.sub('',lines)
 text.append(liness)
 file.seek(0)
 file.truncate(0)
 file.writelines(text)
 file.close()
 print("处理成功！")
 
if __name__=='__main__':
 yunpan_search()</pre></div> 




</p><p><script type="text/javascript" src="https://jss.51dongshi.net/pcwz/dysph.js"></script></div>    
<div class="downbox clearfix">
    <div class="ico"><img src="https://js.51dongshi.net/tpl/pc2/images/document.png" alt="文档"></div>
    <div class="txt">
        <h4>python提取知乎当前最热的问答内容</h4>
        <div class="co">python提取知乎当前最热的问答内容:#-*- coding: utf-8 -*- import urllib.request import re from _io import open def yunpan_search(): url = https://www.zhihu.com/explore req = urllib.request.Request(url, headers = { 'Connection': 'Keep-Alive', 'Accept'</div>
        <div class="tj"><b>推荐度：</b><div class="tj_stars_list"><i class="tj_stars tj_05"></i></div></div>
    </div>
    <div class="btn">
        <a href="javascript:;"  class="html2word" data-model="article" data-id="ccccah" title="文档下载">
            <b>点击下载本文</b>
            <span>文档为doc格式</span>
        </a>
    </div>
</div>
              
       <script>keji_detail_ga('article_content_bottom');</script> 
                <div class="tvideo_tag">
            标签：
                        <a href="/tlist-5169/">内容</a>
                        <a href="/tlist-9364/">获取</a>
                        <a href="/tlist-9572/">回答</a>
                    </div>
                
            
            <div class="tvideo_box tvideo_box_tab"> 
                    <div class="hd">
                        <ul><li class="on">热门焦点</li><script>keji_detail_ga('hot_jiaodian_tab_title');</script></ul>
                    </div>
                    <div class="bd">
                        <ul class="ult_jpic clearfix">
                            <script>get_hot_jiaodian_content('wz_hot_jiaodian',33,'hot',1);</script>
                            
                            
                        </ul>
                        
                    </div>
            </div>
            
        </div>
        <!--中间文章 end-->
        <!--右侧专题 star-->
        <div class="ult_zt">
            <script>keji_detail_ga('article_right_top');</script>
            <div class="ult_ztbox">
                <h4>最新推荐</h4>
                <ul class="tvideo_r_a clearfix">
                    <script>get_detail_right('wz_right_new',33,'')</script>
                
                
                
            </ul>
            </div>
            <script>keji_detail_ga('article_right_middle');</script>
            
            <div class="ult_ztbox">
                <h4>猜你喜欢</h4>
                <ul class="telist_rb clearfix">
                    <script>get_detail_right('wz_right_love',33,'')</script>
                    
                   
                    
                </ul>
            </div>
           
            <script>keji_detail_ga('article_right_new_bottom');</script>
            
           
            <div class="ult_ztbox">
                <h4>热门推荐</h4>
                <ul class="tvideo_r_b clearfix">
                    <script>get_detail_right('wz_right_hot',33,'')</script>
                    
                </ul>
            </div>
           
            <script>keji_detail_ga('article_right_bottom');</script>
        </div>
        <!--右侧专题 end-->
        <div style="display:none"><a href="https://www.51dongshi.net/wzztf/cc/ccccah/">专题</a>
</div>
    </div>

</div>
<script src="https://js.51dongshi.net/plug/qrcode/qrcode.min.js"></script>
<script src="https://js.51dongshi.net/js/share.js" charset="UTF-8"></script>
<script type="text/javascript" src="https://js.51dongshi.net/tpl/pc2/js/waypoints.min.js"></script>
<script type="text/javascript" src="https://js.51dongshi.net/tpl/pc2/js/icon_step.js"></script>
<style>
#qrcode{padding: 15px;background: #fff;}
</style>
<div id="qrcode" style="display: none"></div>
<script>new QRCode(document.getElementById("qrcode"), "https://m.51dongshi.net/eedfccccah.html");</script>
<iframe src="https://hits.51dongshi.net/?biao=ho_article&id=888895" border="0" frameborder="0" style="width: 0px; height: 0px"></iframe>
<script src="https://js.51dongshi.net/js/shHighlighter.js"></script>
<link rel="stylesheet" href="https://jss.51dongshi.net/js/fffz/css/box.css">
<script id="fffz" data-domain="//www.51dongshi.net/index" src="https://js.51dongshi.net/js/fffz/fffz.js"></script>
<script type="text/javascript" src="https://jss.51dongshi.net/pcwz/tj.js"></script>
<div style="display:none"><script>
    var _hmt = _hmt || [];
    (function() {
      var hm = document.createElement("script");
      hm.src = "https://hm.baidu.com/hm.js?4b1ebb0298b66c8a109db070c4878833";
      var s = document.getElementsByTagName("script")[0]; 
      s.parentNode.insertBefore(hm, s);
    })();
    </script>
    </div>

<!--foot star-->
<div class="footer">
    <div class="m_box">
        <div class="footer_in"> 
            <a href="#" target="_blank">产品服务</a>
            <a href="#" target="_blank">发展历程</a>
            <a href="#" target="_blank">企业资讯</a>
            <a href="#" target="_blank">企业文化</a>
            <a href="#" target="_blank">关于我们</a>
            <a href="#" target="_blank">加入我们</a>
            <a href="#" target="_blank">联系我们</a>
            <a href="#" target="_blank">网站导航</a>
            <a href="#" target="_blank">网站律师</a>
        </div>
        <ul class="ftrlist">
            <li>
                 <a rel="nofollow" href="https://www.itrust.org.cn" target="_blank">
                     <img src="https://js.51dongshi.net/tpl/pc2/images/footer_logo01.gif" alt="中国互联网协会"></a>
             </li>
             <li>
                 <a rel="nofollow" href="https://www.12377.cn/" target="_blank">
                     <img src="https://js.51dongshi.net/tpl/pc2/images/12377logo.png" alt="中国互联网举报中心"></a>
             </li>
             <li>
                 <a rel="nofollow" href="http://www.cyberpolice.cn/" target="_blank">
                     <img src="https://js.51dongshi.net/tpl/pc2/images/footer_logo05.gif" alt="网络110报警服务"></a>
             </li>
             <li>
                 <a rel="nofollow" href="http://www.creditchina.gov.cn/" target="_blank">
                     <img src="https://js.51dongshi.net/tpl/pc2/images/creditchina.gif" alt="信用中国"></a>
             </li>
             <li class="last">
                 <a rel="nofollow" href="http://www.shdf.gov.cn/shdf/channels/740.html" target="_blank">
                     <img src="https://js.51dongshi.net/tpl/pc2/images/footer_logo11.png" alt="中国扫黄打非网"><p>中国扫黄打非网</p>
                 </a>
             </li>
        </ul>
        <div class="footer_co"> 
            <a href="/" class="footlogo"><img src="https://js.51dongshi.net/tpl/pc2/images/logo_bottom.png" alt="懂视"></a>
            <p>Copyright © 2019-2025 <a href="/" target="_blank">51dongshi.net</a> 版权所有</p>
            <p>
                <a rel="nofollow" target="_blank" href="https://beian.miit.gov.cn/">赣ICP备2023002352号-34</a>
            </p>
            <p>违法及侵权请联系：TEL:177 7030 7066 E-MAIL:11247931@qq.com 本站由北京市万商天勤律师事务所王兴未律师提供法律服务</p>
            
        </div>
    </div>
</div>
<!--foot end-->


<a href="#0" class="cd-top">Top</a>

<script type="text/javascript">
$(function(){
	var _line=parseInt($(window).height()/3);
	$(window).scroll(function(){
		if ($(window).scrollTop()>100) {
			$('.edu_top').css({'position':'fixed','top':'0','z-index':'99'})
		}else{
			$('.edu_top').css({'position':'relative','top':'0'})
		}
    })
})

</script>
<script type="text/javascript" src="https://jss.51dongshi.net/ga/all.js"></script>

</body>
</html>