Xbase++ Requires Chilkat v11.7.0+

Extract Text from a Two-Column PDF

See more PDF Text Extraction Examples

Demonstrates how multi-column pages are read. By default the columns are detected and each column is read top to bottom before the next ("columns": "auto"); "columns": "none" reads the full page width line by line, which interleaves the columns. The quality report tells how many columns were found. Xbase++

LOCAL nSuccess
LOCAL oPdf
LOCAL oJson
LOCAL oJsonOut

nSuccess := 0

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

//  The two-column PDF used in this example is available at two_column_article.pdf

oPdf := CreateObject("Chilkat.Pdf")
nSuccess := oPdf:LoadFile("qa_data/pdf/two_column_article.pdf")
IF (nSuccess == 0)
    ? oPdf:LastErrorText
    oPdf:destroy()
    RETURN
ENDIF

oJson := CreateObject("Chilkat.JsonObject")
oJsonOut := CreateObject("Chilkat.JsonObject")

//  With the default options the columns are detected, and the text of the left column
//  comes before the text of the right column.
nSuccess := oPdf:ExtractText("text", oJson, oJsonOut)
IF (nSuccess == 0)
    ? oPdf:LastErrorText
    oPdf:destroy()
    oJson:destroy()
    oJsonOut:destroy()
    RETURN
ENDIF

? "Columns detected: " + Str(oJsonOut:IntOf("quality.pages[0].columns"))
? "Reading order: " + oJsonOut:StringOf("quality.pages[0].readingOrderSource")
? oJsonOut:StringOf("text")

//  "none" switches column detection off: the page is read across its full width, line by line,
//  so each output line holds a line of the left column followed by a line of the right column.
//  This is rarely wanted, but it shows what the detection does.
oJson:UpdateString("columns", "none")
oJson:UpdateString("layout", "lines")
nSuccess := oPdf:ExtractText("text", oJson, oJsonOut)
IF (nSuccess == 0)
    ? oPdf:LastErrorText
    oPdf:destroy()
    oJson:destroy()
    oJsonOut:destroy()
    RETURN
ENDIF

? "---- columns: none ----"
? oJsonOut:StringOf("text")

//  Sample output (abbreviated):

//  Columns detected: 2
//  Reading order: visual
//  The Harbor Lighthouse, Season Two
//  
//  The harbor lighthouse was built in 1874 to mark the entrance to the inner channel. It operated continuously until 1968, ...
//  
//  The restoration society took ownership in 2021 with three goals: ...
//  ...
//  The lantern room frame was stripped, primed and repainted in the original dark green. ...
//  ...
//  ---- columns: none ----
//  The Harbor Lighthouse, Season Two
//  The harbor lighthouse was built in 1874 to The lantern room frame was stripped, primed
//  mark the entrance to the inner channel. It and repainted in the original dark green. New
//  ...

oPdf:destroy()
oJson:destroy()
oJsonOut:destroy()