13518219792
beautifulsoup解析页面
from bs4 import BeautifulSoup
soup = BeautifulSoup(htmltxt, "lxml")
# 三种装载器
soup = BeautifulSoup("", "html.parser")
### 只有起始标签的会自动补全，只有结束标签的会自动忽略
### 结果为：
soup = BeautifulSoup("", "lxml")
### 结果为：
soup = BeautifulSoup("", "html5lib")
### html5lib则出现一般的标签都会自动补全
### 结果为：
# 根据标签名、id、class、属性等查找标签
### 根据class、id、以及属性alog-action的值和标签类别查询
soup.find("a",class_="title",id="t1",attrs={"alog-action": "qb-ask-uname"}))
### 查询标签内某属性的值
pubtime = soup.find("meta",attrs={"itemprop":"datePublished"}).attrs['content']
### 获取所有class为title的标签
for i in soup.find_all(class_="title"):
print(i.get_text())
### 获取特定数量的class为title的标签
for i in soup.find_all(class_="title",limit = 2):
print(i.get_text())
### 获取文本内容时可以指定不同标签之间的分隔符，也可以选择是否去掉前后的空白。
soup = BeautifulSoup(' The Dormouses story
The Dormouses story
', "html5lib")
soup.find(class_="title").get_text("|", strip=True)
#结果为：The Dormouses story|The Dormouses story
### 获取class为title的p标签的id
soup.find(class_="title").get("id")
### 对class名称正则：
soup.find_all(class_=re.compile("tit"))
### recursive参数，recursive=False时，只find当前标签的第一级子标签的数据
soup = BeautifulSoup('abc','lxml')
soup.html.find_all("title", recursive=False)</pre> <br>
分享名称：Python常用爬虫代码总结方便查询-创新互联 <br>
本文URL：<a href="http://cdweb.net/article/hoihh.html">http://cdweb.net/article/hoihh.html</a>
</div>
</div>
<div class="other">
<h3>其他资讯</h3>
<ul>
<li>
<a href="/article/gesjci.html">phpword乱码如何解决</a>
</li><li>
<a href="/article/gesjdc.html">香港虚拟主机要不要备案吗</a>
</li><li>
<a href="/article/gesjcc.html">C语言中函数的调用能不能嵌套</a>
</li><li>
<a href="/article/gesjcd.html">匿名代理IP的分类介绍</a>
</li><li>
<a href="/article/gesjei.html">Smarty模板的优点有哪些</a>
</li> </ul>
</div>
</div>
</div>
<footer>
<div class="footop">
<div class="wrap">
<div class="bottomrpw">
<div class="erp arp">
<dl>
<dt>ADDRESS</dt>
<dd class="address"> <i class="icon"></i> <span class="word">成都市青羊区锦天国际1号楼1002室</span> </dd>
</dl>
</div>
<div class="erp arp">
<dl>
<dt>TEL</dt>
<dd class="phonum"> <i class="icon"></i> <span class="word en"> <a href="tel:18980820575">18980820575</a> </span> </dd>
</dl>
</div>
<div class="erp crp">
<dl>
<dt>OTHER</dt>
<dd> <a class="word get-quote">获得报价与方案</a> </dd>
<dd> <a href="#" target="_blank" rel='nofollow' class="word" title="付款方式">付款方式</a> </dd>
</dl>
</div>
<div class="erp code-rp">
<dl>
<dt>Wechat</dt>
<dd class="code-wrap"> <span class="code"> <img src="/Public/Home/images/qr-code.jpg" alt="快上网微信公众号" /> </span> </dd>
</dl>
</div>
</div>
</div>
</div>
<div class="footerbot">
<div class="friendlinks">
<div class="wrap">
<ul class="rpl">
<li><a href="http://www.sczjjygc.com/" title="中建建业环保" target="_blank">中建建业环保</a></li><li><a href="https://www.xwcx.net/jigui.html" title="成都服务器机柜租用" target="_blank">成都服务器机柜租用</a></li><li><a href="http://www.jyfdjzy.cn/" title="名片设计制作" target="_blank">名片设计制作</a></li><li><a href="http://chengdu.cdcxhl.com/seo/" title="成都网络营销" target="_blank">成都网络营销</a></li><li><a href="http://www.czyouth.cn/" title="水泥搅拌车" target="_blank">水泥搅拌车</a></li><li><a href="http://www.cdshujin.cn/" title="蜀锦在线" target="_blank">蜀锦在线</a></li><li><a href="http://www.cqcxhl.com/service/foreigntrade.html" title="重庆外贸网站建设" target="_blank">重庆外贸网站建设</a></li><li><a href="https://www.cdxwcx.com/city/nanchong/" title="南充网站建设" target="_blank">南充网站建设</a></li><li><a href="https://www.cdxwcx.com/wangzhan/mbshangcheng.html" title="商城网站" target="_blank">商城网站</a></li><li><a href="http://www.scjiangyou.cn/" title="江油网站建设" target="_blank">江油网站建设</a></li> </ul>
</div>
</div>
<div class="wrap">
<div class="copyright"> <span class="en">©2007-2022</span> 成都快上网科技有限公司 <span class="en">ALL RIGHTS
RESERVED.</span> <a rel="nofollow" href="http://www.miitbeian.gov.cn" target="_blank">蜀ICP备19037934号</a> </div>
</div>
</div>
</footer>
<div class="fcwrap">
<ul class="rpl clearfix">
<li class="phone"> <a rel="nofollow" target="_blank" href="tel:18980820575"> <i class="icon"></i>
<strong>18980820575</strong> </a> </li>
<li class="qq"> <a rel="nofollow" target="_blank"
href="https://wpa.qq.com/msgrd?v=1&uin=244261566&site=qq&menu=yes"> <i class="icon"></i>
<strong>244261566</strong> </a> </li>
<li class="back-top"> <a href="javascript:void(0)" rel="nofollow" class="back-to-top"> <i class="icon"></i>
<strong>回到顶部</strong> </a> </li>
</ul>
</div>
<!--nav-->
<div class="n-Wrap">
<div class="navBar visble show">
<div class="barlogo">
<a href="/" rel="nofollow">
<img src="/Public/Home/images/logo1.png" alt="成都做网站" />
<img src="/Public/Home/images/logo2.png" alt="成都网站设计" />
</a>
</div>
<div class="bmenu">
<i class="bar-top"><span></span></i>
<i class="bar-cen"><span></span></i>
<i class="bar-bom"><span></span></i>
<i class="bar-left"><span></span></i>
<i class="bar-right"><span></span></i>
</div>
</div>
<section class="fixmenu">
<div class="close-bar">
<i class="bar-left"><span></span></i>
<i class="bar-right"><span></span></i>
</div>
<nav class="smph">
<ul>
<li class="index-hrefs on"><a href="http://www.cdweb.net/"><font>首页</font></a></li>
<li><a href="/about/" rel="nofollow"><font>关于快上网</font></a></li>
<li><a href="/service/" rel="nofollow"><font>服务范围</font></a></li>
<li><a href="/case/" rel="nofollow"><font>案例展示</font></a></li>
<li><a href="/solve/" rel="nofollow"><font>解决方案</font></a></li>
<li><a href="/news/" rel="nofollow"><font>建站资讯</font></a></li>
<li><a href="/contact/" rel="nofollow"><font>联系快上网</font></a></li>
</ul>
<div class="pwrap">
<span class="label">服务热线</span>
<strong class="phone"><a href="tel:18980820575">18980820575</a></strong>
</div>
</nav>
</section>
</div>
<!--end nav-->
<script src="/Public/Home/js/hotcss.js"></script>
<script type="text/javascript" src="/Public/Home/js/su_new.js"></script>
</body>
</html>
<script>
$(".con img").each(function(){
var src = $(this).attr("src"); //获取图片地址
var str=new RegExp("http");
var result=str.test(src);
if(result==false){
var url = "https://www.cdcxhl.com"+src; //绝对路径
$(this).attr("src",url);
}
});
window.onload=function(){
document.oncontextmenu=function(){
return false;
}
}
</script>