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 = {
        &＃39;Connection&＃39;: &＃39;Keep-Alive&＃39;,
        &＃39;Accept&＃39;: &＃39;text/html, application/xhtml+xml, */*&＃39;,
       &＃39;Accept-Language&＃39;: &＃39;en-US,en;q=0.8,zh-Hans-CN;q=0.5,zh-Hans;q=0.3&＃39;,
        &＃39;User-Agent&＃39;: &＃39;Mozilla/5.0 (Windows NT 6.3; WOW64; Trident/7.0; rv:11.0) like Gecko&＃39;
})
    opener = urllib.request.urlopen(req)
    html = opener.read()
    html = html.decode(&＃39;utf-8&＃39;)
    rex = &＃39;(?<=\n).*?(?=<span class="answer-date-link-wrap">)&＃39;
    m = re.findall(rex,html,re.S)
    f = open(&＃39;/root/Desktop/zhihu.txt&＃39;,&＃39;w&＃39;)
    for i in m:
        f.write(i)
        f.write(&＃39;\n\n&＃39;)
    f.close()
    print("抓取成功!")
    file = open(&＃39;/root/Desktop/zhihu.txt&＃39;,&＃39;r+&＃39;)
    fullfile = file.readlines()
    text = []
    p = re.compile(r&＃39;\w*&＃39;, re.L)
    pp = re.compile(r"(&;)*")
    for line in fullfile:
        lines = p.sub(&＃39;&＃39;,line)
        liness = pp.sub(&＃39;&＃39;,lines)
        text.append(liness)
    file.seek(0)
    file.truncate(0)
    file.writelines(text)
    file.close()
    print("处理成功！")
 
if __name__==&＃39;__main__&＃39;:
    yunpan_search()</pre>        <br>
        <script type="text/javascript">
            var cpro_id = "u6885494";

        </script>
        <script type="text/javascript" src="//cpro.baidustatic.com/cpro/ui/cm.js"></script>
    </div>


    <div class="blog_tags">
        <ul>
                        <li><a href="https://www.php1.cn/tag/https" target="_blank" title="https">https</a></li>
                        <li><a href="https://www.php1.cn/tag/html" target="_blank" title="html">html</a></li>
                        <li><a href="https://www.php1.cn/tag/xml" target="_blank" title="xml">xml</a></li>
                        <li><a href="https://www.php1.cn/tag/windows" target="_blank" title="windows">windows</a></li>
                    </ul>
    </div>



    <div class="article_cmnt" style="display: none;">
        <div class="cmnt_title">写下你的评论吧 !</div>
        <form action="" method="post">
            <div class="cmnt_text">
                <textarea class="ping-txt" onfocus="ck_txt(this);" onblur="ck_txt2(this);" id="ping-txt" name="ping-txt" >吐个槽吧,看都看了