Strip Hyperlinks Out Of An HTML String For Export to Excel ASP.NET

[Jared]

Hi

I have been trying to find an easy way to strip the hyperlinks out of
an html string to make exporting ASP.NET GridView's to Excel a bit more
user friendly. Couldn't find anything in these groups, so I have
written this code which will work fine as long as you don't use the ">"
character in your hyperlink name.

Hope somebody finds it useful.

Jared
public static string fnStripHyperLin kFromHTML(strin g strHTML)
{
string strHTMLFinal = "";

int intPlaceHolderS tart = 0;
int intPlaceHolderE nd = strHTML.IndexOf ("<a href");

strHTMLFinal += strHTML.Substri ng(0, intPlaceHolderE nd);

intPlaceHolderS tart = intPlaceHolderE nd;

while (intPlaceHolder End > -1)
{
intPlaceHolderS tart = strHTML.IndexOf (">",
intPlaceHolderS tart) + 1;
intPlaceHolderE nd = strHTML.IndexOf ("</a>",
intPlaceHolderS tart);
strHTMLFinal += strHTML.Substri ng(intPlaceHold erStart,
(intPlaceHolder End - intPlaceHolderS tart));
intPlaceHolderS tart = intPlaceHolderE nd + 4;
intPlaceHolderE nd = strHTML.IndexOf ("<a href",
intPlaceHolderS tart);
if (intPlaceHolder End > -1)
{
strHTMLFinal +=
strHTML.Substri ng(intPlaceHold erStart, (intPlaceHolder End -
intPlaceHolderS tart));
intPlaceHolderS tart = intPlaceHolderE nd;
}
else
{
strHTMLFinal +=
strHTML.Substri ng(intPlaceHold erStart);
}

}
return strHTMLFinal;
}

[Ben Voigt]

"Jared" <ja***********@ gmail.com> wrote in message
news:11******** **************@ f6g2000cwb.goog legroups.com...

Hi

I have been trying to find an easy way to strip the hyperlinks out of
an html string to make exporting ASP.NET GridView's to Excel a bit more
user friendly. Couldn't find anything in these groups, so I have
written this code which will work fine as long as you don't use the ">"
character in your hyperlink name.
And no nested anchor tags, and all lowercase, and no one put another
attribute ahead of href... You should use a DOM parser. With the Microsoft
one, you could just find each anchor tag and set outerHTML=inner HTML thereby
removing the anchor.

Hope somebody finds it useful.

Jared
public static string fnStripHyperLin kFromHTML(strin g strHTML)
{
string strHTMLFinal = "";

int intPlaceHolderS tart = 0;
int intPlaceHolderE nd = strHTML.IndexOf ("<a href");

strHTMLFinal += strHTML.Substri ng(0, intPlaceHolderE nd);

intPlaceHolderS tart = intPlaceHolderE nd;

while (intPlaceHolder End > -1)
{
intPlaceHolderS tart = strHTML.IndexOf (">",
intPlaceHolderS tart) + 1;
intPlaceHolderE nd = strHTML.IndexOf ("</a>",
intPlaceHolderS tart);
strHTMLFinal += strHTML.Substri ng(intPlaceHold erStart,
(intPlaceHolder End - intPlaceHolderS tart));
intPlaceHolderS tart = intPlaceHolderE nd + 4;
intPlaceHolderE nd = strHTML.IndexOf ("<a href",
intPlaceHolderS tart);
if (intPlaceHolder End > -1)
{
strHTMLFinal +=
strHTML.Substri ng(intPlaceHold erStart, (intPlaceHolder End -
intPlaceHolderS tart));
intPlaceHolderS tart = intPlaceHolderE nd;
}
else
{
strHTMLFinal +=
strHTML.Substri ng(intPlaceHold erStart);
}

}
return strHTMLFinal;
}

[Peter Bromberg [C# MVP]]

using System.Text.Reg ularExpressions ;
//replace any and all of script / body /embed / object / frameset / frame /
iframe / meta / link /style with "")
strContent = Regex.Replace(s trContent,
@"</?(?i:script|bod y|embed|object| frameset|frame| iframe|meta|lin k|style)(.|\n)* ?>", "");
Just use the "a" tag and that should do it, e.g.,

strContent = Regex.Replace(s trContent, @"</?(?i:a)(.|\n)*? >", "");
Peter
--
Co-founder, Eggheadcafe.com developer portal:
http://www.eggheadcafe.com
UnBlog:
http://petesbloggerama.blogspot.com


"Jared" wrote:

Hi

I have been trying to find an easy way to strip the hyperlinks out of
an html string to make exporting ASP.NET GridView's to Excel a bit more
user friendly. Couldn't find anything in these groups, so I have
written this code which will work fine as long as you don't use the ">"
character in your hyperlink name.

Hope somebody finds it useful.

Jared
public static string fnStripHyperLin kFromHTML(strin g strHTML)
{
string strHTMLFinal = "";

int intPlaceHolderS tart = 0;
int intPlaceHolderE nd = strHTML.IndexOf ("<a href");

strHTMLFinal += strHTML.Substri ng(0, intPlaceHolderE nd);

intPlaceHolderS tart = intPlaceHolderE nd;

while (intPlaceHolder End > -1)
{
intPlaceHolderS tart = strHTML.IndexOf (">",
intPlaceHolderS tart) + 1;
intPlaceHolderE nd = strHTML.IndexOf ("</a>",
intPlaceHolderS tart);
strHTMLFinal += strHTML.Substri ng(intPlaceHold erStart,
(intPlaceHolder End - intPlaceHolderS tart));
intPlaceHolderS tart = intPlaceHolderE nd + 4;
intPlaceHolderE nd = strHTML.IndexOf ("<a href",
intPlaceHolderS tart);
if (intPlaceHolder End > -1)
{
strHTMLFinal +=
strHTML.Substri ng(intPlaceHold erStart, (intPlaceHolder End -
intPlaceHolderS tart));
intPlaceHolderS tart = intPlaceHolderE nd;
}
else
{
strHTMLFinal +=
strHTML.Substri ng(intPlaceHold erStart);
}

}
return strHTMLFinal;
}