SQL Server

Extract all HTML Objects from a Web Page

See more MHT / HTML Email Examples

Demonstrates how to download a Web page (at a URL) and extract all HTML objects. Eg. images, links, CSS files, JavaScript files, etc. 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

    -- This example assumes the Chilkat API to have been previously unlocked.
    -- See Global Unlock Sample for sample code.

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

    -- Download a URL into an in-memory MHT web archive contained
    -- in a string variable.
    -- The following URL is randomly picked and was valid at the time of writing this example:
    DECLARE @mhtDoc nvarchar(4000)
    EXEC sp_OAMethod @mht, 'GetMHT', @mhtDoc OUT, 'https://www.tetonlodge.com/'
    EXEC sp_OAGetProperty @mht, 'LastMethodSuccess', @iTmp0 OUT
    IF @iTmp0 <> 1
      BEGIN
        EXEC sp_OAGetProperty @mht, 'LastErrorText', @sTmp0 OUT
        PRINT @sTmp0
        EXEC @hr = sp_OADestroy @mht
        RETURN
      END

    -- Extract the HTML and embedded objects:
    DECLARE @unpackDir nvarchar(4000)
    SELECT @unpackDir = 'C:/AAWorkarea/mhtTesting/'
    DECLARE @htmlFilename nvarchar(4000)
    SELECT @htmlFilename = 'lodge.html'
    DECLARE @partsSubdir nvarchar(4000)
    SELECT @partsSubdir = 'objects'

    -- Extract to C:/AAWorkarea/mhtTesting/lodge.html.
    -- images and other embedded objects are placed in
    -- C:/AAWorkarea/mhtTesting/objects.  Directories are automatically
    -- created if they don't already exist.
    EXEC sp_OAMethod @mht, 'UnpackMHTString', @success OUT, @mhtDoc, @unpackDir, @htmlFilename, @partsSubdir
    IF @success <> 1
      BEGIN
        EXEC sp_OAGetProperty @mht, 'LastErrorText', @sTmp0 OUT
        PRINT @sTmp0
      END
    ELSE
      BEGIN

        PRINT 'Unpacked!'
      END

    EXEC @hr = sp_OADestroy @mht


END
GO