SQL Server

GetBaseDomain

See more Spider Examples

The GetBaseDomain method is a utility function that converts a domain into a "domain base", which is useful for grouping URLs. For example: abc.chilkatsoft.com, xyz.chilkatsoft.com, and blog.chilkatsoft.com all have the same base domain: chilkatsoft.com. Things get more complicated when considering country domains (.au, .uk, .se, .cn, etc.) and government, state, and .us domains. Also, domains such as blogspot, wordpress, etc, are treated specially so that "xyz.blogspot.com" has a base domain of "xyz.blogspot.com". Note: If you find other domains that should be treated similarly to blogspot.com, send a request to support@chilkatsoft.com. SQL Server

-- Important: See this note about string length limitations for strings returned by sp_OAMethod calls.
--
CREATE PROCEDURE ChilkatSample
AS
BEGIN
    DECLARE @hr int
    -- Important: Do not use nvarchar(max).  See the warning about using nvarchar(max).
    DECLARE @sTmp0 nvarchar(4000)
    DECLARE @spider int
    EXEC @hr = sp_OACreate 'Chilkat.Spider', @spider OUT
    IF @hr <> 0
    BEGIN
        PRINT 'Failed to create ActiveX component'
        RETURN
    END

    EXEC sp_OAMethod @spider, 'GetBaseDomain', @sTmp0 OUT, 'www.chilkatsoft.com'
    PRINT @sTmp0
    EXEC sp_OAMethod @spider, 'GetBaseDomain', @sTmp0 OUT, 'blog.chilkatsoft.com'
    PRINT @sTmp0
    EXEC sp_OAMethod @spider, 'GetBaseDomain', @sTmp0 OUT, 'www.news.com.au'
    PRINT @sTmp0
    EXEC sp_OAMethod @spider, 'GetBaseDomain', @sTmp0 OUT, 'blogs.bbc.co.uk'
    PRINT @sTmp0
    EXEC sp_OAMethod @spider, 'GetBaseDomain', @sTmp0 OUT, 'xyz.blogspot.com'
    PRINT @sTmp0
    EXEC sp_OAMethod @spider, 'GetBaseDomain', @sTmp0 OUT, 'www.heaids.org.za'
    PRINT @sTmp0
    EXEC sp_OAMethod @spider, 'GetBaseDomain', @sTmp0 OUT, 'www.hec.gov.pk'
    PRINT @sTmp0
    EXEC sp_OAMethod @spider, 'GetBaseDomain', @sTmp0 OUT, 'www.e-mrs.org'
    PRINT @sTmp0
    EXEC sp_OAMethod @spider, 'GetBaseDomain', @sTmp0 OUT, 'cra.curtin.edu.au'
    PRINT @sTmp0

    -- Prints: 
    -- chilkatsoft.com
    -- chilkatsoft.com
    -- news.com.au
    -- bbc.co.uk
    -- xyz.blogspot.com
    -- heaids.org.za
    -- hec.gov.pk
    -- e-mrs.org
    -- curtin.edu.a

    EXEC @hr = sp_OADestroy @spider


END
GO