#-*- 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 = '(?<=\n).*?(?=<span class="answer-date-link-wrap">)' m = re.findall(rex,html,re.S) f = open('/root/Desktop/zhihu.txt','w') for i in m: f.write(i) f.write('\n\n') 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 class='share layui-clear bdsharebuttonbox'> <li ><a href='javascript:;' data-cmd="weixin" class='wechat'><i class="layui-icon"></i>微信</a></li> <li ><a href='javascript:;' data-cmd="more" class='share-btn'><i class="layui-icon"></i>分享</a></li> </div> <img src="/static/images/article_wechat.jpg?1" style="margin-top: 30px;" alt="php教程最新课程二维码"/> <div class='tags layui-clear'> <li>相关标签:<a href="/search?word=代码片段,代码分享,php代码分享,java代码分享" target="_blank">代码片段,代码分享,PHP代码分享,Java代码分享</a> <a href="/search?word=ruby代码分享,python代码分享,html代码分享,css代" target="_blank">Ruby代码分享,Python代码分享,HTML代码分享,CSS代</a></li> <li class='line'> 本文原创发布php教程 ,转载请注明出处,感谢您的尊重! </li> </div> <div class='page layui-clear'> <ul> <li>上一篇:<a href="/python-tutorials-338919.html">模拟登录封包python实现</a></li> <li>下一篇:<a href="/python-tutorials-338922.html">python实现将文本转换成语音的方法</a></li> </ul> </div> </div> <p class="article-relative-header">相关文章</p> <p class="article-relative-header">相关视频</p> <hr class="layui-clear"> <ul class="article-relative-ul"> <li><span class="layui-badge-dots"></span><a class="relevant" href="/python-tutorials-83516.html" target="_blank">在Django框架中运行Python应用全攻略</a></li> <li><span class="layui-badge-dots"></span><a class="relevant" href="/python-tutorials-83517.html" target="_blank">在Python的Django框架中创建和使用模版</a></li> <li><span class="layui-badge-dots"></span><a class="relevant" href="/python-tutorials-83526.html" target="_blank">python获取元素在数组中索引号的方法</a></li> <li><span class="layui-badge-dots"></span><a class="relevant" href="/python-tutorials-83531.html" target="_blank">浅谈python中截取字符函数strip,lstr...</a></li> <li><span class="layui-badge-dots"></span><a class="relevant" href="/python-tutorials-338921.html">python提取知乎当前最热的问答内容</a></li> </ul> <ul class="article-relative-ul"> <li><span class="layui-badge-dots"></span><a class="relevant" href="/code/31616.html" target="_blank" title='轮播图案例讲解'>轮播图案例讲解</a></li> <li><span class="layui-badge-dots"></span><a class="relevant" href="/code/31615.html" target="_blank" title='轮播图案例的预备知识(3)'>轮播图案例的预备知识(3)</a></li> <li><span class="layui-badge-dots"></span><a class="relevant" href="/code/31614.html" target="_blank" title='轮播图案例的预备知识(2)'>轮播图案例的预备知识(2)</a></li> <li><span class="layui-badge-dots"></span><a class="relevant" href="/code/31613.html" target="_blank" title='轮播图案例的预备知识(1)'>轮播图案例的预备知识(1)</a></li> </ul> <div class="layui-clear"></div> </div> <div class="comment layui-clear"> <div class="J_Header" id="J_Header"> <p class="header-title">网友评论</p> <p class="header-protocol">文明上网理性发言,请遵守 <a href="javascript:void(0);">新闻评论服务协议</a></p> <a class="article-comment-publish" href="javascript:void(0);">我要评论</a> </div> <div class="layui-row diy-page"></div> <div class="text-box layui-clear article_comment_textarea" > <div class="box-left"> <li> <a href="javascript:login_trigger()"> <img src="/static/images/user_avatar.jpg" alt=""> </a> </li> <li><a href="javascript:login_trigger()"></a></li> </div> <div class="box-right"> <textarea name="desc" placeholder="请输入内容" class="layui-textarea article_textarea"> 立即提交