Tcl Requires Chilkat v11.7.0+

Extract One Section of a PDF by its Heading

See more PDF Text Extraction Examples

Demonstrates "labelValue": "section", which returns everything from a heading up to the next heading of the same or higher level. With the "markdown" operation the section keeps its own sub-headings. 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 sectioned_doc.pdf

set pdf [new_CkPdf]

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

set json [new_CkJsonObject]

set jsonOut [new_CkJsonObject]

#  The document has the sections Introduction, Opening Hours, Terms and Conditions (with the
#  sub-sections Admission, Safety and Liability) and Contact.  Get the Terms and Conditions:
#  everything after that heading up to the next heading of the same level (Contact).  The heading
#  itself is not part of the value; labelMatches[0].label has it.
CkJsonObject_UpdateString $json "label" "Terms and Conditions"
CkJsonObject_UpdateString $json "labelValue" "section"

set success [CkPdf_ExtractText $pdf "markdown" $json $jsonOut]
if {$success == 0} then {
    puts [CkPdf_lastErrorText $pdf]
    delete_CkPdf $pdf
    delete_CkJsonObject $json
    delete_CkJsonObject $jsonOut
    exit
}

puts [CkJsonObject_stringOf $jsonOut markdown]

#  The same with the "text" operation gives the section as plain text.
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 "---- as text ----"
puts [CkJsonObject_stringOf $jsonOut text]

#  Sample output:

#  ### Admission
#  
#  Admission is free. Groups of more than ten should book in advance so that a volunteer can be assigned to them.
#  
#  ### Safety
#  
#  No more than eight people may be on the stair at one time. Children under twelve must be accompanied by an adult, and the lantern room is closed in high winds.
#  
#  ### Liability
#  
#  Visitors climb the tower at their own risk. The society carries public liability insurance but accepts no responsibility for personal property.
#  ---- as text ----
#  Admission
#  
#  Admission is free. Groups of more than ten should book in advance so that a volunteer can be assigned to them.
#  
#  Safety
#  
#  No more than eight people may be on the stair at one time. Children under twelve must be accompanied by an adult, and the lantern room is closed in high winds.
#  
#  Liability
#  
#  Visitors climb the tower at their own risk. The society carries public liability insurance but accepts no responsibility for personal property.

delete_CkPdf $pdf
delete_CkJsonObject $json
delete_CkJsonObject $jsonOut