PureBasic Requires Chilkat v11.7.0+

Search for Text in a PDF

See more PDF Text Extraction Examples

Demonstrates the "search" operation, which finds every occurrence of a string in a PDF and returns each match with its page number and the text around it. Matching ignores case unless caseSensitive is true. PureBasic

IncludeFile "CkPdf.pb"
IncludeFile "CkJsonObject.pb"

Procedure ChilkatExample()

    success.i = 0

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

    ;  The three-page PDF used in this example is available at search_context.pdf

    pdf.i = CkPdf::ckCreate()
    If pdf.i = 0
        Debug "Failed to create object."
        ProcedureReturn
    EndIf

    success = CkPdf::ckLoadFile(pdf,"qa_data/pdf/search_context.pdf")
    If success = 0
        Debug CkPdf::ckLastErrorText(pdf)
        CkPdf::ckDispose(pdf)
        ProcedureReturn
    EndIf

    json.i = CkJsonObject::ckCreate()
    If json.i = 0
        Debug "Failed to create object."
        ProcedureReturn
    EndIf

    jsonOut.i = CkJsonObject::ckCreate()
    If jsonOut.i = 0
        Debug "Failed to create object."
        ProcedureReturn
    EndIf

    ;  The string to find.
    CkJsonObject::ckUpdateString(json,"query","chilkat")

    ;  The number of characters returned before and after each match.  The default is 40.
    CkJsonObject::ckUpdateInt(json,"context",30)

    success = CkPdf::ckExtractText(pdf,"search",json,jsonOut)
    If success = 0
        Debug CkPdf::ckLastErrorText(pdf)
        CkPdf::ckDispose(pdf)
        CkJsonObject::ckDispose(json)
        CkJsonObject::ckDispose(jsonOut)
        ProcedureReturn
    EndIf

    ;  "count" is the number of matches.  Each match has the page, the matched text as it appears
    ;  in the PDF, and the text before and after it.
    Debug "Matches: " + Str(CkJsonObject::ckIntOf(jsonOut,"count"))

    i.i = 0
    count_i.i = CkJsonObject::ckSizeOfArray(jsonOut,"matches")
    While i < count_i
        CkJsonObject::setCkI(jsonOut, i)
        Debug "page " + Str(CkJsonObject::ckIntOf(jsonOut,"matches[i].page")) + ": ..." + CkJsonObject::ckStringOf(jsonOut,"matches[i].before") + "[" + CkJsonObject::ckStringOf(jsonOut,"matches[i].text") + "]" + CkJsonObject::ckStringOf(jsonOut,"matches[i].after") + "..."
        i = i + 1
    Wend

    ;  The search ignores case by default.  Set caseSensitive to find only the exact spelling.
    CkJsonObject::ckUpdateBool(json,"caseSensitive",1)
    CkJsonObject::ckUpdateString(json,"query","Chilkat")
    success = CkPdf::ckExtractText(pdf,"search",json,jsonOut)
    If success = 0
        Debug CkPdf::ckLastErrorText(pdf)
        CkPdf::ckDispose(pdf)
        CkJsonObject::ckDispose(json)
        CkJsonObject::ckDispose(jsonOut)
        ProcedureReturn
    EndIf

    Debug "Case-sensitive matches for Chilkat: " + Str(CkJsonObject::ckIntOf(jsonOut,"count"))

    ;  Sample output:

    ;  Matches: 5
    ;  page 1: ...[Chilkat] River Field Notes The Chilkat...
    ;  page 1: ...Chilkat River Field Notes The [Chilkat] River runs for about fifty mi...
    ;  page 2: ...DAY ONE: UPPER [CHILKAT] FLATS Clear and cold, minus e...
    ;  page 2: ...he river is sometimes spelled [chilkat] in older records, and the val...
    ;  page 3: ...y because the fish run on the [Chilkat] was thinning. Two tagged bird...
    ;  Case-sensitive matches for Chilkat: 3


    CkPdf::ckDispose(pdf)
    CkJsonObject::ckDispose(json)
    CkJsonObject::ckDispose(jsonOut)


    ProcedureReturn
EndProcedure