Python Requires Chilkat v11.7.0+

Search a PDF with a Regular Expression

See more PDF Text Extraction Examples

Demonstrates searching a PDF with a regular expression (regex: true), limiting the number of results (maxResults), and matching whole words only (wholeWord). 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 is available at order_records.pdf

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

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

# Find every order number.  With regex set to true, the query is a regular expression.
json.UpdateString("query","ORD-[0-9]{4}-[0-9]{4}")
json.UpdateBool("regex",True)
# We only want the matched text, so no context is needed.
json.UpdateInt("context",0)

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

print("Order numbers found: " + str(jsonOut.IntOf("count")))
i = 0
count_i = jsonOut.SizeOfArray("matches")
while i < count_i :
    jsonOut.I = i
    print(jsonOut.StringOf("matches[i].text"))
    i = i + 1

# Find the e-mail addresses, but stop after the first three.
json.UpdateString("query","[a-z0-9._]+@[a-z]+[.][a-z]+")
json.UpdateInt("maxResults",3)
success = pdf.ExtractText("search",json,jsonOut)
if (success == False):
    print(pdf.LastErrorText)
    sys.exit()

print("First three e-mail addresses:")
i = 0
count_i = jsonOut.SizeOfArray("matches")
while i < count_i :
    jsonOut.I = i
    print(jsonOut.StringOf("matches[i].text"))
    i = i + 1

# wholeWord: true matches only whole words.  The word "cat" appears once in the PDF,
# but it is also inside "catalog" and "category".
json.Delete("maxResults")
json.UpdateBool("regex",False)
json.UpdateString("query","cat")
success = pdf.ExtractText("search",json,jsonOut)
if (success == False):
    print(pdf.LastErrorText)
    sys.exit()

print("Occurrences of cat (any): " + str(jsonOut.IntOf("count")))

json.UpdateBool("wholeWord",True)
success = pdf.ExtractText("search",json,jsonOut)
if (success == False):
    print(pdf.LastErrorText)
    sys.exit()

print("Occurrences of cat (whole word): " + str(jsonOut.IntOf("count")))

# Sample output:

# Order numbers found: 9
# ORD-2026-0301
# ORD-2026-0302
# ORD-2026-0303
# ORD-2026-0304
# ORD-2026-0305
# ORD-2026-0306
# ORD-2026-0307
# ORD-2026-0308
# ORD-2026-0307
# First three e-mail addresses:
# alice.moore@example.com
# bkumar@example.org
# carla@example.net
# Occurrences of cat (any): 3
# Occurrences of cat (whole word): 1