Tcl Requires Chilkat v11.7.0+

Extract PDF Text to a StringBuilder and Save to a File

See more PDF Text Extraction Examples

Demonstrates ExtractTextSb, which writes the extracted text to a StringBuilder instead of returning it as a JSON string. Use it for large documents. The JSON output still receives the quality report. 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 PDF used in this example is available at long_report.pdf

set pdf [new_CkPdf]

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

puts "Number of pages: [CkPdf_get_NumPages $pdf]"

#  ExtractTextSb takes the same operation and options as ExtractText, but the text
#  goes to a StringBuilder.  This avoids building a very large JSON string for
#  documents with many pages.
set json [new_CkJsonObject]

set sbText [new_CkStringBuilder]

set jsonOut [new_CkJsonObject]

set success [CkPdf_ExtractTextSb $pdf "text" $json $sbText $jsonOut]
if {$success == 0} then {
    puts [CkPdf_lastErrorText $pdf]
    delete_CkPdf $pdf
    delete_CkJsonObject $json
    delete_CkStringBuilder $sbText
    delete_CkJsonObject $jsonOut
    exit
}

puts "Extracted [CkStringBuilder_get_Length $sbText] characters."

#  Save the text to a file.
set success [CkStringBuilder_WriteFile $sbText "qa_output/long_report.txt" "utf-8" 0]
if {$success == 0} then {
    puts [CkStringBuilder_lastErrorText $sbText]
    delete_CkPdf $pdf
    delete_CkJsonObject $json
    delete_CkStringBuilder $sbText
    delete_CkJsonObject $jsonOut
    exit
}

#  The JSON output does not contain the text, but it still has the quality report.
puts "Quality: [CkJsonObject_stringOf $jsonOut quality.rating]"
puts "{Pages with no text (need OCR): [}[CkJsonObject_stringOf $jsonOut quality.pagesNeedingOcr]]"

#  Sample output:

#  Number of pages: 3
#  Extracted 4522 characters.
#  Quality: good
#  Pages with no text (need OCR): []

delete_CkPdf $pdf
delete_CkJsonObject $json
delete_CkStringBuilder $sbText
delete_CkJsonObject $jsonOut