Lua Requires Chilkat v11.7.0+

Get the Text Block Below a PDF Caption

See more PDF Text Extraction Examples

Demonstrates the "label" option with labelValue "below", which captures the block of text directly under a caption such as "Ship To", ending at the next gap or heading. Combined with layout "lines", the lines of an address block are kept separate. Lua

local chilkat = require("chilkat")

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

-- The packing slip used in this example is available at packing_slip.pdf

local pdf = chilkat.Pdf.new()
local success = pdf:load_file("qa_data/pdf/packing_slip.pdf")
if not success then
    print(pdf.last_error_text)
    return
end

local json = chilkat.JsonObject.new()
local jsonOut = chilkat.JsonObject.new()

-- The packing slip has the captions "Bill To" and "Ship To" side by side,
-- each with an address block below it.
json:update_string("label", "Ship To")

-- "below" means the value is the block of text directly under the label.
json:update_string("labelValue", "below")

-- With the default "flow" layout the lines of the block would be joined into one paragraph.
-- "lines" keeps each line of the address on its own line.
json:update_string("layout", "lines")

success = pdf:extract_text("text", json, jsonOut)
if not success then
    print(pdf.last_error_text)
    return
end

print("Ship To:")
print(jsonOut:string_of("text"))
print("")

json:update_string("label", "Bill To")
success = pdf:extract_text("text", json, jsonOut)
if not success then
    print(pdf.last_error_text)
    return
end

print("Bill To:")
print(jsonOut:string_of("text"))
print("")

-- A caption over a short paragraph works the same way.  Here the flow layout is better,
-- because the two lines are one piece of text.
json:update_string("label", "Special Instructions")
json:update_string("layout", "flow")
success = pdf:extract_text("text", json, jsonOut)
if not success then
    print(pdf.last_error_text)
    return
end

print("Special Instructions:")
print(jsonOut:string_of("text"))

-- Sample output:

-- Ship To:
-- Frank Delgado
-- c/o Harbor Pet Boarding
-- 9 Ferry Lane
-- Portside, WA 98001
--
-- Bill To:
-- Frank Delgado
-- Apartment 3B
-- 41 Mill Street
-- Portside, WA 98000
--
-- Special Instructions:
-- Leave the carton with the boarding office if no one answers. Do not leave it outside; the cat tree is not packed for rain.