How to parse XML in Bash?
Ideally, what I would like to be able to do is:
cat xhtmlfile.xhtml |
getElementViaXPath --path=\'/html/head/title\' |
sed -e \'s%(^|</title&>
<script async src="https://pagead2.googlesyndication.com/pagead/js/adsbygoogle.js"></script>
<ins class="adsbygoogle"
style="display:block"
data-ad-client="ca-pub-5408099190056760"
data-ad-slot="7305827575"
data-ad-format="auto"
data-full-width-responsive="true"></ins>
<script>
(adsbygoogle = window.adsbygoogle || []).push({});
</script> </div>
</div>
<div class="fly-panel detail-box" id="flyReply">
<fieldset class="layui-elem-field layui-field-title" style="text-align: center;">
<legend>15条回答</legend> </fieldset>
<ul class="jieda" id="jieda">
<li data-id="111" class="jieda-daan">
<a name="item-1111111111"></a>
<div class="detail-about detail-about-reply">
<a class="fly-avatar" href="">
<img src="https://www.e-learn.cn/qa/data/avatar/000/00/01/small_000000119.jpg" alt=" 無奈伤痛 ">
</a>
<div class="fly-detail-user">
<a href="" class="fly-link">
<cite> 無奈伤痛</cite>
</a>
<span>(楼主)</span>
</div> <div class="detail-hits">
<span>2020-11-22 03:33</span>
</div>
</div>
<div class="detail-body jieda-body photos">
<p>
<p>This works if you are wanting XML attributes:</p>
<pre><code>$ cat alfa.xml
<video server="asdf.com" stream="H264_400.mp4" cdn="limelight"/>
$ sed 's.[^ ]*..;s./>..' alfa.xml > alfa.sh
$ . ./alfa.sh
$ echo "$stream"
H264_400.mp4
</code></pre>
</p>
<div class="appendcontent">
</div>
</div>
<div class="jieda-reply">
<span class="jieda-zan button_agree" type="zan" data-id='59704'>
<i class="iconfont icon-zan"></i>
<em>0</em>
</span>
<span type="reply" class="showpinglun" data-id="59704">
<i class="iconfont icon-svgmoban53"></i>
讨论(0)
</span>
<div class="jieda-admin">
</div>
<div class="noreplaytext bb">
<center><div> <a href="https://www.e-learn.cn/qa/q-19606.html"> 查看其它15个回答
</a>
</div></center>
</div> </div>
<div class="comments-mod " style="display: none; float:none;padding-top:10px;" id="comment_59704">
<div class="areabox clearfix">
<form class="layui-form" action="">
<div class="layui-form-item">
<label class="layui-form-label" style="padding-left:0px;width:60px;">发布评论:</label>
<div class="layui-input-block" style="margin-left:90px;">
<input type="text" placeholder="不少于5个字" AUTOCOMPLETE="off" class="comment-input layui-input" name="content" />
<input type='hidden' value='0' name='replyauthor' />
</div>
<div class="mar-t10"><span class="fr layui-btn layui-btn-sm addhuidapinglun" data-id="59704">提交评论 </span></div>
</div>
</form>
</div>
<hr>
<ul class="my-comments-list nav">
<li class="loading">
<img src='https://www.e-learn.cn/qa/static/css/default/loading.gif' align='absmiddle' />
加载中...
</li>
</ul>
</div>
</li>
</ul>
<div class="layui-form layui-form-pane">
<form id="huidaform" name="answerForm" method="post">
<div class="layui-form-item layui-form-text">
<a name="comment"></a>
<div class="layui-input-block">
<script type="text/javascript" src="https://www.e-learn.cn/qa/static/js/neweditor/ueditor.config.js"></script>
<script type="text/javascript" src="https://www.e-learn.cn/qa/static/js/neweditor/ueditor.all.js"></script>
<script type="text/plain" id="editor" name="content" style="width:100%;height:200px;"></script>
<script type="text/javascript">
var isueditor=1;
var editor = UE.getEditor('editor',{
//这里可以选择自己需要的工具按钮名称,此处仅选择如下五个
toolbars:[['source','fullscreen', '|', 'undo', 'redo', '|', 'bold', 'italic', 'underline', 'fontborder', 'strikethrough', 'removeformat', 'formatmatch', 'autotypeset', 'blockquote', 'pasteplain', '|', 'forecolor', 'backcolor', 'insertorderedlist', 'insertunorderedlist', 'selectall', 'cleardoc', '|', 'rowspacingtop', 'rowspacingbottom', 'lineheight', '|', 'customstyle', 'paragraph', 'fontfamily', 'fontsize', '|', 'indent', '|', 'justifyleft', 'justifycenter', 'justifyright', 'justifyjustify', '|', 'link', 'unlink', 'anchor', '|', 'simpleupload', 'insertimage', 'scrawl', 'insertvideo', 'attachment', 'map', 'insertcode', '|', 'horizontal', '|', 'preview', 'searchreplace', 'drafts']],
initialContent:'',
//关闭字数统计
wordCount:false,
zIndex:2,
//关闭elementPath
elementPathEnabled:false,
//默认的编辑区域高度
initialFrameHeight:250
//更多其他参数，请参考ueditor.config.js中的配置项
//更多其他参数，请参考ueditor.config.js中的配置项
});
editor.ready(function() {
editor.setDisabled();
});
$("#editor").find("*").css("max-width","362px");
</script> </div>
</div>
<div class="layui-form-item">
<label for="L_vercode" class="layui-form-label">验证码</label>
<div class="layui-input-inline">
<input type="text" id="code" name="code" value="" required lay-verify="required" placeholder="图片验证码" autocomplete="off" class="layui-input">
</div>
<div class="layui-form-mid">
<span style="color: #c00;"><img class="hand" src="https://www.e-learn.cn/qa/user/code.html" onclick="javascript:updatecode();" id="verifycode"><a class="changecode" href="javascript:updatecode();"> 看不清?</a></span>
</div>
</div>
<div class="layui-form-item">
<input type="hidden" value="19606" id="ans_qid" name="qid">
<input type="hidden" id="tokenkey" name="tokenkey" value=''/>
<input type="hidden" value="How to parse XML in Bash?" id="ans_title" name="title">
<div class="layui-btn layui-btn-disabled" id="ajaxsubmitasnwer" >提交回复</div>
</div>
</form>
</div>
</div>
<input type="hidden" value="19606" id="adopt_qid" name="qid" />
<input type="hidden" id="adopt_answer" value="0" name="aid" />
</div>
<div class="layui-col-md4">
<!-- 热门讨论问题 -->
<dl class="fly-panel fly-list-one">
<dt class="fly-panel-title">热议问题</dt>
<!-- 本周热门讨论问题显示10条-->