Python Requires Chilkat v11.7.0+

Get Every Occurrence of a Label in a PDF

See more PDF Text Extraction Examples

Demonstrates the "labelOccurrence" option. When the same label appears more than once (for example "Total:" on each of several receipts), "first" (the default) uses the first occurrence, "all" returns every occurrence with its page, and a number selects one occurrence. 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 PDF used in this example (three receipts, one per page) is available at three_receipts.pdf

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

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

# Each of the three pages is a receipt with a "Total:" line.
json.UpdateString("label","Total")
json.UpdateString("labelValue","right")

# By default only the first occurrence (in reading order) is used.
success = pdf.ExtractText("text",json,jsonOut)
if (success == False):
    print(pdf.LastErrorText)
    sys.exit()

print("First total: " + jsonOut.StringOf("text"))

# labelOccurrence "all" returns every occurrence.  The "text" member holds the values joined
# by line breaks, and labelMatches has one entry per occurrence with its page.
json.UpdateString("labelOccurrence","all")
success = pdf.ExtractText("text",json,jsonOut)
if (success == False):
    print(pdf.LastErrorText)
    sys.exit()

i = 0
count_i = jsonOut.SizeOfArray("labelMatches")
while i < count_i :
    jsonOut.I = i
    print("Page " + str(jsonOut.IntOf("labelMatches[i].page")) + " total: " + jsonOut.StringOf("labelMatches[i].text"))
    i = i + 1

# A number selects one occurrence: 2 is the second.
json.UpdateInt("labelOccurrence",2)
success = pdf.ExtractText("text",json,jsonOut)
if (success == False):
    print(pdf.LastErrorText)
    sys.exit()

print("Second total: " + jsonOut.StringOf("text"))

# The occurrences are counted over the selected pages, so combining "pages" with the label
# is another way to pick one receipt:
json.UpdateString("labelOccurrence","first")
json.UpdateString("pages","3")
json.UpdateString("label","Receipt No.")
success = pdf.ExtractText("text",json,jsonOut)
if (success == False):
    print(pdf.LastErrorText)
    sys.exit()

print("Receipt number on page 3: " + jsonOut.StringOf("text"))

# Sample output:

# First total: $19.86
# Page 1 total: $19.86
# Page 2 total: $17.34
# Page 3 total: $23.62
# Second total: $17.34
# Receipt number on page 3: 1003