Tcl 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. Tcl

load ./chilkat.dll

set success 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

set pdf [new_CkPdf]

set success [CkPdf_LoadFile $pdf "qa_data/pdf/two_column_article.pdf"]
if {$success == 0} then {
    puts [CkPdf_lastErrorText $pdf]
    delete_CkPdf $pdf
    exit
}

set json [new_CkJsonObject]

set jsonOut [new_CkJsonObject]

#  With the default options the columns are detected, and the text of the left column
#  comes before the text of the right column.
set success [CkPdf_ExtractText $pdf "text" $json $jsonOut]
if {$success == 0} then {
    puts [CkPdf_lastErrorText $pdf]
    delete_CkPdf $pdf
    delete_CkJsonObject $json
    delete_CkJsonObject $jsonOut
    exit
}

puts "Columns detected: [CkJsonObject_IntOf $jsonOut {quality.pages[0].columns}]"
puts "Reading order: [CkJsonObject_stringOf $jsonOut {quality.pages[0].readingOrderSource}]"
puts [CkJsonObject_stringOf $jsonOut 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.
CkJsonObject_UpdateString $json "columns" "none"
CkJsonObject_UpdateString $json "layout" "lines"
set success [CkPdf_ExtractText $pdf "text" $json $jsonOut]
if {$success == 0} then {
    puts [CkPdf_lastErrorText $pdf]
    delete_CkPdf $pdf
    delete_CkJsonObject $json
    delete_CkJsonObject $jsonOut
    exit
}

puts "---- columns: none ----"
puts [CkJsonObject_stringOf $jsonOut 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
#  ...

delete_CkPdf $pdf
delete_CkJsonObject $json
delete_CkJsonObject $jsonOut