How to strip HTML tags from a string in SQL Server?

Solution 1:

There is a UDF that will do that described here:

User Defined Function to Strip HTML

CREATE FUNCTION [dbo].[udf_StripHTML] (@HTMLText VARCHAR(MAX))
RETURNS VARCHAR(MAX) AS
BEGIN
    DECLARE @Start INT
    DECLARE @End INT
    DECLARE @Length INT
    SET @Start = CHARINDEX('<',@HTMLText)
    SET @End = CHARINDEX('>',@HTMLText,CHARINDEX('<',@HTMLText))
    SET @Length = (@End - @Start) + 1
    WHILE @Start > 0 AND @End > 0 AND @Length > 0
    BEGIN
        SET @HTMLText = STUFF(@HTMLText,@Start,@Length,'')
        SET @Start = CHARINDEX('<',@HTMLText)
        SET @End = CHARINDEX('>',@HTMLText,CHARINDEX('<',@HTMLText))
        SET @Length = (@End - @Start) + 1
    END
    RETURN LTRIM(RTRIM(@HTMLText))
END
GO

Edit: note this is for SQL Server 2005, but if you change the keyword MAX to something like 4000, it will work in SQL Server 2000 as well.

Solution 2:

Derived from @Goner Doug answer, with a few things updated:
- using REPLACE where possible
- conversion of predefined entities like é (I chose the ones I needed :-)
- some conversion of list tags <ul> and <li>

ALTER FUNCTION [dbo].[udf_StripHTML]
--by Patrick Honorez --- www.idevlop.com
--inspired by http://stackoverflow.com/questions/457701/best-way-to-strip-html-tags-from-a-string-in-sql-server/39253602#39253602
(
@HTMLText varchar(MAX)
)
RETURNS varchar(MAX)
AS
BEGIN
DECLARE @Start  int
DECLARE @End    int
DECLARE @Length int

set @HTMLText = replace(@htmlText, '<br>',CHAR(13) + CHAR(10))
set @HTMLText = replace(@htmlText, '<br/>',CHAR(13) + CHAR(10))
set @HTMLText = replace(@htmlText, '<br />',CHAR(13) + CHAR(10))
set @HTMLText = replace(@htmlText, '<li>','- ')
set @HTMLText = replace(@htmlText, '</li>',CHAR(13) + CHAR(10))

set @HTMLText = replace(@htmlText, '&rsquo;' collate Latin1_General_CS_AS, ''''  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&quot;' collate Latin1_General_CS_AS, '"'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&amp;' collate Latin1_General_CS_AS, '&'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&euro;' collate Latin1_General_CS_AS, '€'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&lt;' collate Latin1_General_CS_AS, '<'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&gt;' collate Latin1_General_CS_AS, '>'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&oelig;' collate Latin1_General_CS_AS, 'oe'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&nbsp;' collate Latin1_General_CS_AS, ' '  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&copy;' collate Latin1_General_CS_AS, '©'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&laquo;' collate Latin1_General_CS_AS, '«'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&reg;' collate Latin1_General_CS_AS, '®'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&plusmn;' collate Latin1_General_CS_AS, '±'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&sup2;' collate Latin1_General_CS_AS, '²'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&sup3;' collate Latin1_General_CS_AS, '³'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&micro;' collate Latin1_General_CS_AS, 'µ'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&middot;' collate Latin1_General_CS_AS, '·'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&ordm;' collate Latin1_General_CS_AS, 'º'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&raquo;' collate Latin1_General_CS_AS, '»'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&frac14;' collate Latin1_General_CS_AS, '¼'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&frac12;' collate Latin1_General_CS_AS, '½'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&frac34;' collate Latin1_General_CS_AS, '¾'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&Aelig' collate Latin1_General_CS_AS, 'Æ'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&Ccedil;' collate Latin1_General_CS_AS, 'Ç'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&Egrave;' collate Latin1_General_CS_AS, 'È'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&Eacute;' collate Latin1_General_CS_AS, 'É'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&Ecirc;' collate Latin1_General_CS_AS, 'Ê'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&Ouml;' collate Latin1_General_CS_AS, 'Ö'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&agrave;' collate Latin1_General_CS_AS, 'à'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&acirc;' collate Latin1_General_CS_AS, 'â'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&auml;' collate Latin1_General_CS_AS, 'ä'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&aelig;' collate Latin1_General_CS_AS, 'æ'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&ccedil;' collate Latin1_General_CS_AS, 'ç'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&egrave;' collate Latin1_General_CS_AS, 'è'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&eacute;' collate Latin1_General_CS_AS, 'é'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&ecirc;' collate Latin1_General_CS_AS, 'ê'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&euml;' collate Latin1_General_CS_AS, 'ë'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&icirc;' collate Latin1_General_CS_AS, 'î'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&ocirc;' collate Latin1_General_CS_AS, 'ô'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&ouml;' collate Latin1_General_CS_AS, 'ö'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&divide;' collate Latin1_General_CS_AS, '÷'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&oslash;' collate Latin1_General_CS_AS, 'ø'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&ugrave;' collate Latin1_General_CS_AS, 'ù'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&uacute;' collate Latin1_General_CS_AS, 'ú'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&ucirc;' collate Latin1_General_CS_AS, 'û'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&uuml;' collate Latin1_General_CS_AS, 'ü'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&quot;' collate Latin1_General_CS_AS, '"'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&amp;' collate Latin1_General_CS_AS, '&'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&lsaquo;' collate Latin1_General_CS_AS, '<'  collate Latin1_General_CS_AS)
set @HTMLText = replace(@htmlText, '&rsaquo;' collate Latin1_General_CS_AS, '>'  collate Latin1_General_CS_AS)


-- Remove anything between <STYLE> tags
SET @Start = CHARINDEX('<STYLE', @HTMLText)
SET @End = CHARINDEX('</STYLE>', @HTMLText, CHARINDEX('<', @HTMLText)) + 7
SET @Length = (@End - @Start) + 1

WHILE (@Start > 0 AND @End > 0 AND @Length > 0) BEGIN
SET @HTMLText = STUFF(@HTMLText, @Start, @Length, '')
SET @Start = CHARINDEX('<STYLE', @HTMLText)
SET @End = CHARINDEX('</STYLE>', @HTMLText, CHARINDEX('</STYLE>', @HTMLText)) + 7
SET @Length = (@End - @Start) + 1
END

-- Remove anything between <whatever> tags
SET @Start = CHARINDEX('<', @HTMLText)
SET @End = CHARINDEX('>', @HTMLText, CHARINDEX('<', @HTMLText))
SET @Length = (@End - @Start) + 1

WHILE (@Start > 0 AND @End > 0 AND @Length > 0) BEGIN
SET @HTMLText = STUFF(@HTMLText, @Start, @Length, '')
SET @Start = CHARINDEX('<', @HTMLText)
SET @End = CHARINDEX('>', @HTMLText, CHARINDEX('<', @HTMLText))
SET @Length = (@End - @Start) + 1
END

RETURN LTRIM(RTRIM(@HTMLText))

END

Solution 3:

If your HTML is well formed, I think this is a better solution:

create function dbo.StripHTML( @text varchar(max) ) returns varchar(max) as
begin
    declare @textXML xml
    declare @result varchar(max)
    set @textXML = REPLACE( @text, '&', '' );
    with doc(contents) as
    (
        select chunks.chunk.query('.') from @textXML.nodes('/') as chunks(chunk)
    )
    select @result = contents.value('.', 'varchar(max)') from doc
    return @result
end
go

select dbo.StripHTML('This <i>is</i> an <b>html</b> test')

Solution 4:

Here's an updated version of this function that incorporates the RedFilter answer (Pinal's original) with the LazyCoders additions and the goodeye typo corrections AND my own addition to handle in-line <STYLE> tags inside the HTML.

ALTER FUNCTION [dbo].[udf_StripHTML]
(
@HTMLText varchar(MAX)
)
RETURNS varchar(MAX)
AS
BEGIN
DECLARE @Start  int
DECLARE @End    int
DECLARE @Length int

-- Replace the HTML entity &amp; with the '&' character (this needs to be done first, as
-- '&' might be double encoded as '&amp;amp;')
SET @Start = CHARINDEX('&amp;', @HTMLText)
SET @End = @Start + 4
SET @Length = (@End - @Start) + 1

WHILE (@Start > 0 AND @End > 0 AND @Length > 0) BEGIN
SET @HTMLText = STUFF(@HTMLText, @Start, @Length, '&')
SET @Start = CHARINDEX('&amp;', @HTMLText)
SET @End = @Start + 4
SET @Length = (@End - @Start) + 1
END

-- Replace the HTML entity &lt; with the '<' character
SET @Start = CHARINDEX('&lt;', @HTMLText)
SET @End = @Start + 3
SET @Length = (@End - @Start) + 1

WHILE (@Start > 0 AND @End > 0 AND @Length > 0) BEGIN
SET @HTMLText = STUFF(@HTMLText, @Start, @Length, '<')
SET @Start = CHARINDEX('&lt;', @HTMLText)
SET @End = @Start + 3
SET @Length = (@End - @Start) + 1
END

-- Replace the HTML entity &gt; with the '>' character
SET @Start = CHARINDEX('&gt;', @HTMLText)
SET @End = @Start + 3
SET @Length = (@End - @Start) + 1

WHILE (@Start > 0 AND @End > 0 AND @Length > 0) BEGIN
SET @HTMLText = STUFF(@HTMLText, @Start, @Length, '>')
SET @Start = CHARINDEX('&gt;', @HTMLText)
SET @End = @Start + 3
SET @Length = (@End - @Start) + 1
END

-- Replace the HTML entity &amp; with the '&' character
SET @Start = CHARINDEX('&amp;amp;', @HTMLText)
SET @End = @Start + 4
SET @Length = (@End - @Start) + 1

WHILE (@Start > 0 AND @End > 0 AND @Length > 0) BEGIN
SET @HTMLText = STUFF(@HTMLText, @Start, @Length, '&')
SET @Start = CHARINDEX('&amp;amp;', @HTMLText)
SET @End = @Start + 4
SET @Length = (@End - @Start) + 1
END

-- Replace the HTML entity &nbsp; with the ' ' character
SET @Start = CHARINDEX('&nbsp;', @HTMLText)
SET @End = @Start + 5
SET @Length = (@End - @Start) + 1

WHILE (@Start > 0 AND @End > 0 AND @Length > 0) BEGIN
SET @HTMLText = STUFF(@HTMLText, @Start, @Length, ' ')
SET @Start = CHARINDEX('&nbsp;', @HTMLText)
SET @End = @Start + 5
SET @Length = (@End - @Start) + 1
END

-- Replace any <br> tags with a newline
SET @Start = CHARINDEX('<br>', @HTMLText)
SET @End = @Start + 3
SET @Length = (@End - @Start) + 1

WHILE (@Start > 0 AND @End > 0 AND @Length > 0) BEGIN
SET @HTMLText = STUFF(@HTMLText, @Start, @Length, CHAR(13) + CHAR(10))
SET @Start = CHARINDEX('<br>', @HTMLText)
SET @End = @Start + 3
SET @Length = (@End - @Start) + 1
END

-- Replace any <br/> tags with a newline
SET @Start = CHARINDEX('<br/>', @HTMLText)
SET @End = @Start + 4
SET @Length = (@End - @Start) + 1

WHILE (@Start > 0 AND @End > 0 AND @Length > 0) BEGIN
SET @HTMLText = STUFF(@HTMLText, @Start, @Length, CHAR(13) + CHAR(10))
SET @Start = CHARINDEX('<br/>', @HTMLText)
SET @End = @Start + 4
SET @Length = (@End - @Start) + 1
END

-- Replace any <br /> tags with a newline
SET @Start = CHARINDEX('<br />', @HTMLText)
SET @End = @Start + 5
SET @Length = (@End - @Start) + 1

WHILE (@Start > 0 AND @End > 0 AND @Length > 0) BEGIN
SET @HTMLText = STUFF(@HTMLText, @Start, @Length, CHAR(13) + CHAR(10))
SET @Start = CHARINDEX('<br />', @HTMLText)
SET @End = @Start + 5
SET @Length = (@End - @Start) + 1
END

-- Remove anything between <STYLE> tags
SET @Start = CHARINDEX('<STYLE', @HTMLText)
SET @End = CHARINDEX('</STYLE>', @HTMLText, CHARINDEX('<', @HTMLText)) + 7
SET @Length = (@End - @Start) + 1

WHILE (@Start > 0 AND @End > 0 AND @Length > 0) BEGIN
SET @HTMLText = STUFF(@HTMLText, @Start, @Length, '')
SET @Start = CHARINDEX('<STYLE', @HTMLText)
SET @End = CHARINDEX('</STYLE>', @HTMLText, CHARINDEX('</STYLE>', @HTMLText)) + 7
SET @Length = (@End - @Start) + 1
END

-- Remove anything between <whatever> tags
SET @Start = CHARINDEX('<', @HTMLText)
SET @End = CHARINDEX('>', @HTMLText, CHARINDEX('<', @HTMLText))
SET @Length = (@End - @Start) + 1

WHILE (@Start > 0 AND @End > 0 AND @Length > 0) BEGIN
SET @HTMLText = STUFF(@HTMLText, @Start, @Length, '')
SET @Start = CHARINDEX('<', @HTMLText)
SET @End = CHARINDEX('>', @HTMLText, CHARINDEX('<', @HTMLText))
SET @Length = (@End - @Start) + 1
END

RETURN LTRIM(RTRIM(@HTMLText))

END

Solution 5:

Here is a version that doesn't require an UDF and works even if the HTML contains tags without matching closing tags.

TRY_CAST(REPLACE(REPLACE(REPLACE([HtmlCol], '>', '/> '), '</', '<'), '--/>', '-->') AS XML).value('.', 'NVARCHAR(MAX)')