Home > Others

Regular expressions to remove all HTML tags

Source: Internet
Author: User
Developer on Alibaba Coud: Build your first app with APIs, SDKs, and tutorials on the Alibaba Cloud. Read more ＞
Protected string str = "<table> <tr> <td> sdasasdsdd </td> </tr> </table> <br> <p> sds </p> aaassss <br> say yes ";

Protected void Page_Load (object sender, EventArgs e)
{

// String regexstr = @ "<[^>] *>"; // remove all tags

// @ "<Script [^>] *?>. *? </Script> "// remove all scripts and delete the intermediate part.

// String regexstr = @ "] *>"; // remove the regular expression of the image.

// String regexstr = @ "<(?! Br). *?> "; // Remove all tags with only br left

// String regexstr = @ "<table [^>] *?>. *? </Table> "; // remove all contents in the table.

String regexstr = @ "<(?! Img | br | p |/p). *?> "; // Remove all tags, with only img, br, and p left.

Str = Regex. Replace (str, regexstr, string. Empty, RegexOptions. IgnoreCase );

}

 

 

 

 

 

ASP. NET removes all HTML tags <type = "text/javascript"> function StorePage () {d = document; t = d. selection? (D. selection. type! = 'None '? D. selection. createRange (). text: '') :( d. getSelection? D. getSelection (): ''); void (keyit = window. open ('HTTP: // www.365key.com/storeit.aspx? T = '+ escape (d. title) + '& u =' + escape (d. location. href) + '& c =' + escape (t), 'keyit', 'scrollbars = no, width = 475, height = 575, left = 75, top = 20, status = no, resizable = yes '); keyit. focus ();}
Note: using System. Text. RegularExpressions is required first;

/** // <Summary>
/// Remove HTML tags
/// </Summary>
/// <Param name = "NoHTML"> including the source code of HTML </param>
/// <Returns> removed text </returns>
Public static string NoHTML (string Htmlstring)
{
// Delete the script
Htmlstring = Regex. Replace (Htmlstring, @ "<script [^>] *?>. *? </Script> "," ", RegexOptions. IgnoreCase );
// Delete HTML
Htmlstring = Regex. Replace (Htmlstring, @ "<(. [^>] *)>", "", RegexOptions. IgnoreCase );
Htmlstring = Regex. Replace (Htmlstring, @ "([\ r \ n]) [\ s] +", "", RegexOptions. IgnoreCase );
Htmlstring = Regex. Replace (Htmlstring, @ "-->", "", RegexOptions. IgnoreCase );
Htmlstring = Regex. Replace (Htmlstring, @ "<! --. * "," ", RegexOptions. IgnoreCase );

Htmlstring = Regex. Replace (Htmlstring, @ "& (quot | #34);", "\" ", RegexOptions. IgnoreCase );
Htmlstring = Regex. Replace (Htmlstring, @ "& (amp | #38);", "&", RegexOptions. IgnoreCase );
Htmlstring = Regex. Replace (Htmlstring, @ "& (lt | #60);", "<", RegexOptions. IgnoreCase );
Htmlstring = Regex. Replace (Htmlstring, @ "& (gt | #62);", ">", RegexOptions. IgnoreCase );
Htmlstring = Regex. Replace (Htmlstring, @ "& (nbsp | #160);", "", RegexOptions. IgnoreCase );
Htmlstring = Regex. Replace (Htmlstring, @ "& (iexcl | #161);", "\ xa1", RegexOptions. IgnoreCase );
Htmlstring = Regex. Replace (Htmlstring, @ "& (cent | #162);", "\ xa2", RegexOptions. IgnoreCase );
Htmlstring = Regex. Replace (Htmlstring, @ "& (pound | #163);", "\ xa3", RegexOptions. IgnoreCase );
Htmlstring = Regex. Replace (Htmlstring, @ "& (copy | #169);", "\ xa9", RegexOptions. IgnoreCase );
Htmlstring = Regex. Replace (Htmlstring, @ "& # (\ d +);", "", RegexOptions. IgnoreCase );

Htmlstring. Replace ("<","");
Htmlstring. Replace ("> ","");
Htmlstring. Replace ("\ r \ n ","");
Htmlstring = HttpContext. Current. Server. HtmlEncode (Htmlstring). Trim ();

Return Htmlstring;
}

/** // Extract the C # function of the text in HTML code
/// <Summary>
/// Remove HTML tags
/// </Summary>
/// <Param name = "strHtml"> including the source code of HTML </param>
/// <Returns> removed text </returns>
Using System;
Using System. Text. RegularExpressions;
Public class StripHTMLTest {
Public static void Main (){
String s = StripHTML ("<HTML> <HEAD> <TITLE> China shilong Information Platform </TITLE> </HEAD> <BODY> faddfs dragon Information Platform </BODY> </ HTML> ");
Console. WriteLine (s );
}

Public static string StripHTML (string strHtml ){
String [] aryReg = {
@ "<Script [^>] *?>. *? </Script> ",

@ "<(\/\ S *)?!? (\ W + :)? \ W +) (\ w + (\ s * =? \ S * (["" ']) (bytes) *? \ 7 | \ w +) |. {0}) | \ s )*? (\/\ S *)?> ",
@ "([\ R \ n]) [\ s] + ",
@ "& (Quot | #34 );",
@ "& (Amp | #38 );",
@ "& (Lt | #60 );",
@ "& (Gt | #62 );",
@ "& (Nbsp | #160 );",
@ "& (Iexcl | #161 );",
@ "& (Cent | #162 );",
@ "& (Pound | #163 );",
@ "& (Copy | #169 );",
@ "& # (\ D + );",
@ "--> ",
@ "<! --. * \ N"
};

String [] aryRep = {
"",
"",
"",
"\"",
"&",
"<",
"> ",
"",
"\ Xa1", // chr (161 ),
"\ Xa2", // chr (162 ),
"\ Xa3", // chr (163 ),
"\ Xa9", // chr (169 ),
"",
"\ R \ n ",
""
};

String newReg = aryReg [0];
String strOutput = strHtml;
For (int I = 0; I <aryReg. Length; I ++ ){
Regex regex = new Regex (aryReg [I], RegexOptions. IgnoreCase );
StrOutput = regex. Replace (strOutput, aryRep [I]);
}
StrOutput. Replace ("<","");
StrOutput. Replace ("> ","");
StrOutput. Replace ("\ r \ n ","");
Return strOutput;
}
}

Write a static method
Remove HTML tags # Remove HTML tags from region
/** // <Summary>
/// Remove HTML tags
/// </Summary>
/// <Param name = "HTMLStr"> HTMLStr </param>
Public static string ParseTags (string HTMLStr)
{
Return System. Text. RegularExpressions. Regex. Replace (HTMLStr, "<[^>] *> ","");
}

# Endregion

Retrieve the image address in the text # region retrieve the image address in the text
/** // <Summary>
/// Retrieve the image address in the text
/// </Summary>
/// <Param name = "HTMLStr"> HTMLStr </param>
Public static string GetImgUrl (string HTMLStr)
{
String str = string. Empty;
String sPattern = @ "^ ] *> ";
Regex r = new Regex (@ "] * \ s * src \ s * = \ s * ([']?) (? <Url> \ S + )'? [^>] *> ",
RegexOptions. Compiled );
Match m = r. Match (HTMLStr. ToLower ());
If (m. Success)
Str = m. Result ("$ {url }");
Return str;
}

# Endregion

 

This article is an English version of an article which is originally in the Chinese language on aliyun.com and is provided for information purposes only. This website makes no representation or warranty of any kind, either expressed or implied, as to the accuracy, completeness ownership or reliability of the article or any translations thereof. If you have any concerns or complaints relating to the article, please send an email, providing a detailed description of the concern or complaint, to info-contact@alibabacloud.com. A staff member will contact you within 5 working days. Once verified, infringing content will be removed immediately.

Related Keywords:
regular expression remove html tags remove all html tags php remove all tags remove all html tags from string in php how to remove html tags in php perl remove html tags ckeditor remove html tags

Contact Us

The content source of this page is from Internet, which doesn't represent Alibaba Cloud's opinion; products and services mentioned on that page don't have any relationship with Alibaba Cloud. If the content of the page makes you feel confusing, please write us an email, we will handle the problem within 5 days after receiving your email.

If you find any instances of plagiarism from the community, please send an email to: info-contact@alibabacloud.com and provide relevant evidence. A staff member will contact you within 5 working days.

What's Trending
Top 10 Tags
datastax versions naming convention zookeeper client class definition md5 microsoft sql server 2005 data structures exception handling error handling
Top 10 Keywords
microsoft download center down wordpress address url site address url wordpress address url windows installer 4 0 download 302 not found web address url definition site address url wordpress db2 integer mac os installation step by step pdf abbreviation for return

A Free Trial That Lets You Build Big!

Start building with 50+ products and up to 12 months usage for Elastic Compute Service

Get Started for Free

  • Sales Support

    1 on 1 presale consultation

    Chat Contact Sales

  • After-Sales Support

    24/7 Technical Support 6 Free Tickets per Quarter Faster Response

    Open a Ticket

  • Alibaba Cloud offers highly flexible support services tailored to meet your exact needs.

    Learn More