SQL Server Requires Chilkat v11.7.0+

Extract Text from a PDF that Forbids Copying

See more PDF Text Extraction Examples

Demonstrates a PDF that opens without a password but whose permissions do not allow copying text. The "text", "markdown", "search" and "tables" operations fail with that reason; "assess" always works. Loading the PDF with the OwnerPassword property set grants owner rights, and extraction works. SQL Server

--
CREATE PROCEDURE ChilkatSample
AS
BEGIN
    DECLARE @hr int
    DECLARE @sTmp0 nvarchar(4000)
    DECLARE @success int
    SELECT @success = 0

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

    --  The PDF used in this example (owner password: owner-secret; copying not permitted) is available at no_copy_permission.pdf

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

    DECLARE @json int
    EXEC @hr = sp_OACreate 'Chilkat.JsonObject', @json OUT

    DECLARE @jsonOut int
    EXEC @hr = sp_OACreate 'Chilkat.JsonObject', @jsonOut OUT

    --  The PDF opens without a password.
    EXEC sp_OAMethod @pdf, 'LoadFile', @success OUT, 'qa_data/pdf/no_copy_permission.pdf'
    IF @success = 0
      BEGIN
        EXEC sp_OAGetProperty @pdf, 'LastErrorText', @sTmp0 OUT
        PRINT @sTmp0
        EXEC @hr = sp_OADestroy @pdf
        EXEC @hr = sp_OADestroy @json
        EXEC @hr = sp_OADestroy @jsonOut
        RETURN
      END

    --  Extracting text is refused, because the PDF's permissions do not allow copying.
    EXEC sp_OAMethod @pdf, 'ExtractText', @success OUT, 'text', @json, @jsonOut
    IF @success = 0
      BEGIN

        EXEC sp_OAGetProperty @pdf, 'LastErrorText', @sTmp0 OUT
        PRINT 'Extraction refused: ' + @sTmp0
      END

    --  "assess" reports only counts and ratings, never text, so it is always allowed.
    EXEC sp_OAMethod @pdf, 'ExtractText', @success OUT, 'assess', @json, @jsonOut
    IF @success = 0
      BEGIN
        EXEC sp_OAGetProperty @pdf, 'LastErrorText', @sTmp0 OUT
        PRINT @sTmp0
        EXEC @hr = sp_OADestroy @pdf
        EXEC @hr = sp_OADestroy @json
        EXEC @hr = sp_OADestroy @jsonOut
        RETURN
      END

    EXEC sp_OAMethod @jsonOut, 'StringOf', @sTmp0 OUT, 'quality.rating'
    PRINT 'rating: ' + @sTmp0

    --  Load with the owner password to get owner rights, which include copying.
    EXEC sp_OASetProperty @pdf, 'OwnerPassword', 'owner-secret'
    EXEC sp_OAMethod @pdf, 'LoadFile', @success OUT, 'qa_data/pdf/no_copy_permission.pdf'
    IF @success = 0
      BEGIN
        EXEC sp_OAGetProperty @pdf, 'LastErrorText', @sTmp0 OUT
        PRINT @sTmp0
        EXEC @hr = sp_OADestroy @pdf
        EXEC @hr = sp_OADestroy @json
        EXEC @hr = sp_OADestroy @jsonOut
        RETURN
      END

    EXEC sp_OAMethod @pdf, 'ExtractText', @success OUT, 'text', @json, @jsonOut
    IF @success = 0
      BEGIN
        EXEC sp_OAGetProperty @pdf, 'LastErrorText', @sTmp0 OUT
        PRINT @sTmp0
        EXEC @hr = sp_OADestroy @pdf
        EXEC @hr = sp_OADestroy @json
        EXEC @hr = sp_OADestroy @jsonOut
        RETURN
      END
    EXEC sp_OAMethod @jsonOut, 'StringOf', @sTmp0 OUT, 'text'
    PRINT @sTmp0

    --  Sample output:

    --  Extraction refused: ChilkatLog:
    --    ExtractText:
    --      ...
    --        The PDF's permissions do not allow copying or extracting text (load it with the owner password to extract).
    --      ...
    --  rating: good
    --  Visitor Leaflet
    --  
    --  Welcome to the harbor lighthouse. The tower is open on weekends from July to September.
    --  
    --  Please keep to the marked paths and do not climb on the breakwater.
    --  
    --  The lantern room is closed in high winds.

    EXEC @hr = sp_OADestroy @pdf
    EXEC @hr = sp_OADestroy @json
    EXEC @hr = sp_OADestroy @jsonOut


END
GO