SQL Server

Using the Disk Cache

See more Spider Examples

The Chilkat Spider component has disk caching capabilities. To setup a disk cache, create a new directory anywhere on your local hard drive and set the CacheDir property to the path. For example, you might create "c:/spiderCache/". The UpdateCache property controls whether downloaded pages are saved to the cache. The FetchFromCache property controls whether the cache is first checked for pages. The LastFromCache property tells whether the last URL fetched came from cache or not. 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
    DECLARE @iTmp0 int
    -- Important: Do not use nvarchar(max).  See the warning about using nvarchar(max).
    DECLARE @sTmp0 nvarchar(4000)
    DECLARE @success int
    SELECT @success = 0

    DECLARE @spider int
    EXEC @hr = sp_OACreate 'Chilkat.Spider', @spider OUT
    IF @hr <> 0
    BEGIN
        PRINT 'Failed to create ActiveX component'
        RETURN
    END

    -- Set our cache directory and make sure saving-to-cache and fetching-from-cache
    -- are both turned on:
    EXEC sp_OASetProperty @spider, 'CacheDir', 'c:/spiderCache/'
    EXEC sp_OASetProperty @spider, 'FetchFromCache', 1
    EXEC sp_OASetProperty @spider, 'UpdateCache', 1

    -- If you run this code twice, you'll find that the 2nd run is extremely fast
    -- because the pages will be retrieved from cache.

    -- 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/'

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

    SELECT @i = 0
    WHILE @i <= 9
      BEGIN

        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.
        -- The reason for waiting a short time before the next fetch is to prevent
        -- undue stress on the web server.  However, if the last page was retrieved
        -- from cache, there is no need to pause.
        EXEC sp_OAGetProperty @spider, 'LastFromCache', @iTmp0 OUT
        IF @iTmp0 <> 1
          BEGIN
            EXEC sp_OAMethod @spider, 'SleepMs', NULL, 1000
          END
        SELECT @i = @i + 1
      END

    EXEC @hr = sp_OADestroy @spider


END
GO