如何从 SQL Server 中的字符串中去除 HTML 标签？

Question

我在 SQL Server 2005 中有包含 HTML 标记的数据，我想去掉所有这些，只留下标记之间的文本。理想情况下，还可以将 < 替换为 < 等。

有没有一种简单的方法可以做到这一点，或者有人已经得到了一些示例 T-SQL 代码？

我没有能力添加扩展存储过程等，因此更喜欢纯 T-SQL 方法（最好是向后兼容 SQL 2000）。

我只是想用去除 HTML 来检索数据，而不是更新它，所以理想情况下它会被编写为用户定义的函数，以便于重用。

所以例如转换这个：

<B>Some useful text</B>&nbsp;
<A onclick="return openInfo(this)"
   href="http://there.com/3ce984e88d0531bac5349"
   target=globalhelp>
   <IMG title="Source Description" height=15 alt="Source Description" 
        src="/ri/new_info.gif" width=15 align=top border=0>
</A>&gt;&nbsp;<b>more text</b></TD></TR>

到这里：

Some useful text > more text

Answer 1

有一个 UDF 可以执行此处描述的操作：

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

编辑：注意这是针对 SQL Server 2005 的，但如果将关键字 MAX 更改为 4000 之类的值，它也可以在 SQL Server 2000 中使用。

Answer 2

如果您的 HTML 格式正确，我认为这是一个更好的解决方案：

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')

Answer 3

试试这个。这是RedFilter 发布的版本的修改版本...此 SQL 删除了除 BR、B 和 P 之外的所有标签以及任何附带的属性：

CREATE FUNCTION [dbo].[StripHtml] (@HTMLText VARCHAR(MAX))
RETURNS VARCHAR(MAX)
AS
BEGIN
 DECLARE @Start  INT
 DECLARE @End    INT
 DECLARE @Length INT
 DECLARE @TempStr varchar(255)

 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
   IF (UPPER(SUBSTRING(@HTMLText, @Start, 3)) <> '<BR') AND (UPPER(SUBSTRING(@HTMLText, @Start, 2)) <> '<P') AND (UPPER(SUBSTRING(@HTMLText, @Start, 2)) <> '<B') AND (UPPER(SUBSTRING(@HTMLText, @Start, 3)) <> '</B')
   BEGIN
      SET @HTMLText = STUFF(@HTMLText,@Start,@Length,'')
   END
    
   SET @Start = CHARINDEX('<',@HTMLText, @End)
   SET @End = CHARINDEX('>',@HTMLText,CHARINDEX('<',@HTMLText, @Start))
   SET @Length = (@End - @Start) - 1
 END

 RETURN RTRIM(LTRIM(@HTMLText))
END

Answer 4

这不是一个全新的解决方案，而是对 afwebservant 解决方案的更正：

--note comments to see the corrections

CREATE FUNCTION [dbo].[StripHTML] (@HTMLText VARCHAR(MAX))  
RETURNS VARCHAR(MAX)  
AS  
BEGIN  
 DECLARE @Start  INT  
 DECLARE @End    INT  
 DECLARE @Length INT  
 --DECLARE @TempStr varchar(255) (this is not used)  

 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  
   IF (UPPER(SUBSTRING(@HTMLText, @Start, 4)) <> '<BR>') AND (UPPER(SUBSTRING(@HTMLText, @Start, 5)) <> '</BR>')  
    begin  
      SET @HTMLText = STUFF(@HTMLText,@Start,@Length,'')  
      end  
-- this ELSE and SET is important
   ELSE  
      SET @Length = 0;  

-- minus @Length here below is important
   SET @Start = CHARINDEX('<',@HTMLText, @End-@Length)  
   SET @End = CHARINDEX('>',@HTMLText,CHARINDEX('<',@HTMLText, @Start))  
-- instead of -1 it should be +1
   SET @Length = (@End - @Start) + 1  
 END  

 RETURN RTRIM(LTRIM(@HTMLText))  
END  

Answer 5

这是此函数的更新版本，其中包含 RedFilter answer（Pinal 的原始版本）与 LazyCoders 添加和 goodeye 错字更正以及我自己添加的用于处理 HTML 内的内联 <STYLE> 标签。

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 & with the '&' character (this needs to be done first, as
-- '&' might be double encoded as '&')
SET @Start = CHARINDEX('&', @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('&', @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

Answer 6

源自@Goner Doug 的回答，更新了一些内容：
- 尽可能使用 REPLACE
- 预定义实体的转换，例如 é（我选择了我需要的实体 :-)
- 列表标签的一些转换<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

Answer 7

如何将 XQuery 与单列一起使用：

DECLARE @MalformedXML xml, @StrippedText varchar(max)
SET @MalformedXML = @xml.query('for $x in //. return ($x)//text()')
SET @StrippedText = CAST(@MalformedXML as varchar(max))

这将遍历所有元素并仅返回 text()。

要避免元素之间的文本没有空格连接，请使用：

DECLARE @MalformedXML xml, @StrippedText varchar(max)
SET @MalformedXML = @xml.query('for $x in //. return concat((($x)//text())[1]," ")')
SET @StrippedText = CAST(@MalformedXML as varchar(max))

并回复“您如何将其用于列：

  SELECT CAST(html_column.query('for $x in //. return concat((($x)//text()) as varchar(max))
  FROM table

对于上面的代码，确保你的html_column的数据类型是xml，如果不是，你需要将html的转换版本保存为xml。当您加载 HTML 数据时，我会将其作为一个单独的练习来执行，因为如果 SQL 发现格式错误的 xml，它将引发错误，例如不匹配的开始/结束标签，无效字符。

当您想要构建搜索短语、剥离 HTML 等时，它们非常适合。

请注意，这会返回 xml 类型，因此在适当的地方将 CAST 或 COVERT 转换为文本。这种数据类型的 xml 版本没有用，因为它不是格式良好的 XML。

Answer 8

Patrick Honorez 代码需要稍作改动。

它返回包含< 或> 的html 的不完整结果

这是因为该部分下面的代码

-- 删除标签之间的任何内容

实际上会将 替换为空。解决方法是在末尾应用以下两行：

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)

Answer 9

这是一个不需要 UDF 的版本，即使 HTML 包含没有匹配结束标签的标签也可以工作。

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

Answer 10

虽然 Arvin Amir 的答案接近于一个完整的单线解决方案，但您可以在任何地方使用；他的 select 语句中有一个小错误（缺少行尾），我想处理最常见的字符引用。

我最终做的是：

SELECT replace(replace(replace(CAST(CAST(replace([columnNameHere], '&', '&') as xml).query('for $x in //. return concat((($x)//text())[1]," ")') as varchar(max)), '&', '&'), ' ', ' '), ' ', ' ')
FROM [tableName]

没有字符参考代码可以简化为：

SELECT CAST(CAST([columnNameHere] as xml).query('for $x in //. return concat((($x)//text())[1]," ")') as varchar(max))
FROM [tableName]

Answer 11

如果您不想使用 UDF 功能，请尝试此操作。

SELECT COLUMN1, TRY_CONVERT(xml, COLUMN2).value('.', 'nvarchar(max)') as COL2, COLUMN3
FROM   DBO.TABLENAME