(SQL Server) Avoid URLs Matching Any of a Set of Patterns

Demonstrates how to use "avoid patterns" to prevent spidering any URL that matches a wildcarded pattern. This example avoids URLs containing the substrings "java", "python", or "perl".

Chilkat ActiveX Downloads ActiveX for 32-bit and 64-bit Windows

-- Important: See this note about string length limitations for strings returned by sp_OAMethod calls.
--
CREATE PROCEDURE ChilkatSample
AS
BEGIN
    DECLARE @hr int
    DECLARE @iTmp0 int
    -- Important: Do not use nvarchar(max).  See the warning about using nvarchar(max).
    DECLARE @sTmp0 nvarchar(4000)
    DECLARE @spider int
    -- Use "Chilkat_9_5_0.Spider" for versions of Chilkat < 10.0.0
    EXEC @hr = sp_OACreate 'Chilkat.Spider', @spider OUT
    IF @hr <> 0
    BEGIN
        PRINT 'Failed to create ActiveX component'
        RETURN
    END

    -- The spider object crawls a single web site at a time.  As you'll see
    -- in later examples, you can collect outbound links and use them to 
    -- crawl the web.  For now, we'll simply spider 10 pages of chilkatsoft.com
    EXEC sp_OAMethod @spider, 'Initialize', NULL, 'www.chilkatsoft.com'

    -- Add the 1st URL:
    EXEC sp_OAMethod @spider, 'AddUnspidered', NULL, 'http://www.chilkatsoft.com/'

    -- Avoid URLs matching these patterns:
    EXEC sp_OAMethod @spider, 'AddAvoidPattern', NULL, '*java*'
    EXEC sp_OAMethod @spider, 'AddAvoidPattern', NULL, '*python*'
    EXEC sp_OAMethod @spider, 'AddAvoidPattern', NULL, '*perl*'

    -- Begin crawling the site by calling CrawlNext repeatedly.
    DECLARE @i int

    SELECT @i = 0
    WHILE @i <= 9
      BEGIN
        DECLARE @success int

        EXEC sp_OAMethod @spider, 'CrawlNext', @success OUT
        IF @success = 1
          BEGIN
            -- Show the URL of the page just spidered.
            EXEC sp_OAGetProperty @spider, 'LastUrl', @sTmp0 OUT
            PRINT @sTmp0
            -- The HTML is available in the LastHtml property
          END
        ELSE
          BEGIN
            -- Did we get an error or are there no more URLs to crawl?
            EXEC sp_OAGetProperty @spider, 'NumUnspidered', @iTmp0 OUT
            IF @iTmp0 = 0
              BEGIN

                PRINT 'No more URLs to spider'
              END
            ELSE
              BEGIN
                EXEC sp_OAGetProperty @spider, 'LastErrorText', @sTmp0 OUT
                PRINT @sTmp0
              END
          END
        -- Sleep 1 second before spidering the next URL.
        EXEC sp_OAMethod @spider, 'SleepMs', NULL, 1000
        SELECT @i = @i + 1
      END

    EXEC @hr = sp_OADestroy @spider


END
GO