zoukankan
html css js c++ java
过滤HTML字符显示摘要
public
static
string
GetSummary(
string
html,
int
summaryLength)
{
string
text
=
GetHtmlText(html);
text
=
DelHTML(text);
text
=
Strtitle(text);
if
(summaryLength
>=
text.Length)
return
text;
return
text.Substring(
0
, summaryLength)
+
"
"
;
}
public
static
string
GetHtmlText(
string
html)
{
return
System.Text.RegularExpressions.Regex.Replace(html,
@"
<[^>]*>
"
,
""
);
}
public
static
string
DelHTML(
string
Htmlstring)
//
将HTML去除
{
#region
//
删除脚本
Htmlstring
=
System.Text.RegularExpressions.Regex.Replace(Htmlstring,
@"
<script[^>]*?>.*?</script>
"
,
""
, System.Text.RegularExpressions.RegexOptions.IgnoreCase);
//
删除HTML
Htmlstring
=
System.Text.RegularExpressions.Regex.Replace(Htmlstring,
@"
<(.[^>]*)>
"
,
""
, System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring
=
System.Text.RegularExpressions.Regex.Replace(Htmlstring,
@"
([\r\n])[\s]+
"
,
""
, System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring
=
System.Text.RegularExpressions.Regex.Replace(Htmlstring,
@"
-->
"
,
""
, System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring
=
System.Text.RegularExpressions.Regex.Replace(Htmlstring,
@"
<!--.*
"
,
""
, System.Text.RegularExpressions.RegexOptions.IgnoreCase);
//
Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"<A>.*</A>","");
//
Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"<[a-zA-Z]*=\.[a-zA-Z]*\?[a-zA-Z]+=\d&\w=%[a-zA-Z]*|[A-Z0-9]","");
Htmlstring
=
System.Text.RegularExpressions.Regex.Replace(Htmlstring,
@"
&(quot|#34);
"
,
"
\
""
, System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring
=
System.Text.RegularExpressions.Regex.Replace(Htmlstring,
@"
&(amp|#38);
"
,
"
&
"
, System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring
=
System.Text.RegularExpressions.Regex.Replace(Htmlstring,
@"
&(lt|#60);
"
,
"
<
"
, System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring
=
System.Text.RegularExpressions.Regex.Replace(Htmlstring,
@"
&(gt|#62);
"
,
"
>
"
, System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring
=
System.Text.RegularExpressions.Regex.Replace(Htmlstring,
@"
&(nbsp|#160);
"
,
"
"
, System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring
=
System.Text.RegularExpressions.Regex.Replace(Htmlstring,
@"
&(iexcl|#161);
"
,
"
\xa1
"
, System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring
=
System.Text.RegularExpressions.Regex.Replace(Htmlstring,
@"
&(cent|#162);
"
,
"
\xa2
"
, System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring
=
System.Text.RegularExpressions.Regex.Replace(Htmlstring,
@"
&(pound|#163);
"
,
"
\xa3
"
, System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring
=
System.Text.RegularExpressions.Regex.Replace(Htmlstring,
@"
&(copy|#169);
"
,
"
\xa9
"
, System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring
=
System.Text.RegularExpressions.Regex.Replace(Htmlstring,
@"
&#(\d+);
"
,
""
, System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring.Replace(
"
<
"
,
""
);
Htmlstring.Replace(
"
>
"
,
""
);
Htmlstring.Replace(
"
\r\n
"
,
""
);
//
Htmlstring=HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();
#endregion
return
Htmlstring.Trim();
}
public
static
string
DelWords(
string
strtitle)
{
string
strContent
=
strtitle;
strtitle
=
Regex.Replace(strContent,
"
(<H1.*?>|</H1>|</br>|<SPAN.*?>|</SPAN>|<FONT.*?>||<o:p></o:p>)
"
,
""
);
strContent
=
strtitle;
strContent
=
Regex.Replace(strContent,
"
(<IMG.*?>)
"
,
""
);
strContent
=
Regex.Replace(strContent,
"
(<P.*?>)
"
,
""
);
strContent
=
Regex.Replace(strContent,
"
(<P>)
"
,
""
);
strContent
=
Regex.Replace(strContent,
"
( )
"
,
""
);
strContent
=
Regex.Replace(strContent,
"
(”)
"
,
""
);
strContent
=
Regex.Replace(strContent,
"
(</P>)
"
,
""
);
strContent
=
Regex.Replace(strContent,
"
(</BR>)
"
,
""
);
strContent
=
Regex.Replace(strContent,
"
(<BR>)
"
,
""
);
strContent
=
strContent.Replace(
"
<?xml:namespace prefix = o ns = 'urn:schemas-microsoft-com:office:office'/>
"
,
""
);
return
strtitle;
}
查看全文
相关阅读:
Linux常用基本命令:三剑客命令之-awk数组用法
Linux常用基本命令:三剑客命令之-awk动作用法(1)
Linux常用基本命令:三剑客命令之-awk模式用法(2)
Linux常用基本命令:三剑客命令之-awk模式用法(1)
Linux常用基本命令:三剑客命令之-awk格式化动作
Linux常用基本命令:三剑客命令之-awk内置变量与自定义变量
Linux常用基本命令:三剑客命令之-awk输入输出分隔符
Linux常用基本命令:三剑客命令之-awk基础用法
Linux环境变量详解与应用
在js中怎么判断两个字符串相等
原文地址:https://www.cnblogs.com/cnaspnet/p/1216790.html
最新文章
request.GetResponse()超时的解决办法
jsoup 是一款Java 的HTML解析器,可直接解析某个URL地址
Spring开发工具Spring Tools Suite(STS)
开源的.NET任务调度框架-HangFire
开源配置管理平台-Apollo
Windows 不能复制文件到远程服务器的解决办法
如何离线安装Visual Studio 2017
如何给Elasticsearch安装中文分词器IK
处理用千牛导出淘宝数据,供Logstash到Elasticsearch使用。(NodeJS)
51单片机:独立按键与矩阵按键控制数码管
热门文章
一天:51单片机从入门到一个动态数码管显示数字控制
python爬虫入门urllib库的使用
Linux Shell脚本编程while语句案例
Linux Shell脚本编程case条件语句
linux shell脚本之-变量极速入门与进阶(2)
重定向,/dev/null, 1>, 2>什么意思?
linux shell脚本之-变量极速入门与进阶(1)
Debian、Ubuntu恢复误删除(或者说重装)的/var/lib/dpkg
Linux常用基本命令:三剑客命令之-awk 三元表达式
Linux常用基本命令:三剑客命令之-awk内置函数用法
Copyright © 2011-2022 走看看