SQL Server Requires Chilkat v11.7.0+

Exclude or Include Running Headers and Page Numbers

See more PDF Text Extraction Examples

Demonstrates the "repeatedHeadersFooters" filter. Text repeated at the same position on most pages, such as a running header and "Page N of 4" footers, is left out by default; set the filter to "include" to keep it. 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 four-page PDF used in this example is available at running_header.pdf

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

    EXEC sp_OAMethod @pdf, 'LoadFile', @success OUT, 'qa_data/pdf/running_header.pdf'
    IF @success = 0
      BEGIN
        EXEC sp_OAGetProperty @pdf, 'LastErrorText', @sTmp0 OUT
        PRINT @sTmp0
        EXEC @hr = sp_OADestroy @pdf
        RETURN
      END

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

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

    --  Every page has the header "Harbor Lighthouse Society - Annual Report 2026" at the top right
    --  and "Page N of 4" at the bottom.  By default both are excluded, so the text of page 2 is just
    --  its heading and paragraphs.
    EXEC sp_OAMethod @json, 'UpdateString', @success OUT, 'pages', '2'
    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

    PRINT '---- default (repeated headers and footers excluded) ----'
    EXEC sp_OAMethod @jsonOut, 'StringOf', @sTmp0 OUT, 'text'
    PRINT @sTmp0

    --  Include them.  The detection looks at the neighbouring pages even when only one page is
    --  selected, so a single page extracted on its own still loses its running head by default.
    EXEC sp_OAMethod @json, 'UpdateString', @success OUT, 'repeatedHeadersFooters', 'include'
    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

    PRINT '---- repeatedHeadersFooters: include ----'
    EXEC sp_OAMethod @jsonOut, 'StringOf', @sTmp0 OUT, 'text'
    PRINT @sTmp0

    --  Sample output:

    --  ---- default (repeated headers and footers excluded) ----
    --  The Work
    --  
    --  The restoration society took ownership in 2021 with three goals: make the structure watertight, return the tower to public access, and relight the lantern with a historically accurate lens. The first two were met in the second season, and the lens arrived on loan in November.
    --  
    --  The spiral stair is original and is the most fragile part of the building. Twelve of the ninety-one treads were cracked or missing, and the central column had corroded badly at the second landing. The treads were cast from patterns taken off an intact tread.
    --  ---- repeatedHeadersFooters: include ----
    --  Harbor Lighthouse Society - Annual Report 2026
    --  
    --  The Work
    --  
    --  The restoration society took ownership in 2021 with three goals: ...
    --  
    --  The spiral stair is original and is the most fragile part of the building. ...
    --  
    --  Page 2 of 4

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


END
GO