Python 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. Chilkat2-Python

import sys
import chilkat2

success = False

# 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

pdf = chilkat2.Pdf()
success = pdf.LoadFile("qa_data/pdf/packing_slip.pdf")
if (success == False):
    print(pdf.LastErrorText)
    sys.exit()

json = chilkat2.JsonObject()
jsonOut = chilkat2.JsonObject()

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

# "below" means the value is the block of text directly under the label.
json.UpdateString("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.UpdateString("layout","lines")

success = pdf.ExtractText("text",json,jsonOut)
if (success == False):
    print(pdf.LastErrorText)
    sys.exit()

print("Ship To:")
print(jsonOut.StringOf("text"))
print("")

json.UpdateString("label","Bill To")
success = pdf.ExtractText("text",json,jsonOut)
if (success == False):
    print(pdf.LastErrorText)
    sys.exit()

print("Bill To:")
print(jsonOut.StringOf("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.UpdateString("label","Special Instructions")
json.UpdateString("layout","flow")
success = pdf.ExtractText("text",json,jsonOut)
if (success == False):
    print(pdf.LastErrorText)
    sys.exit()

print("Special Instructions:")
print(jsonOut.StringOf("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.