Xbase++ 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. 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 PDF used in this example is available at sectioned_doc.pdf

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

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

//  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.
oJson:UpdateString("label", "Terms and Conditions")
oJson:UpdateString("labelValue", "section")

nSuccess := oPdf:ExtractText("markdown", oJson, oJsonOut)
IF (nSuccess == 0)
    ? oPdf:LastErrorText
    oPdf:destroy()
    oJson:destroy()
    oJsonOut:destroy()
    RETURN
ENDIF

? oJsonOut:StringOf("markdown")

//  The same with the "text" operation gives the section as plain text.
nSuccess := oPdf:ExtractText("text", oJson, oJsonOut)
IF (nSuccess == 0)
    ? oPdf:LastErrorText
    oPdf:destroy()
    oJson:destroy()
    oJsonOut:destroy()
    RETURN
ENDIF

? "---- as text ----"
? oJsonOut:StringOf("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.

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