Python Requires Chilkat v11.7.0+

Audit a PDF First, Optimize Only If It Is Worth It

See more PDF Optimization Examples

Demonstrates deciding whether to rewrite a PDF at all. "audit" costs a fraction of a second and changes nothing, so a batch job can audit every file and optimize only those where enough would be saved. Here the threshold is a tenth of the file; a file already as small as it can be is left alone. 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 watersense_accomplishments.pdf

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

json = chilkat2.JsonObject()
jsonOut = chilkat2.JsonObject()
success = pdf.Optimize("audit",json,jsonOut)
if (success == False):
    print(pdf.LastErrorText)
    sys.exit()

fileSize = jsonOut.IntOf("fileSize")
estimated = jsonOut.IntOf("estimatedSavings.total")
print("fileSize:  " + str(fileSize))
print("estimated: " + str(estimated))

# Only bother when at least a tenth of the file would go.
if (estimated > (fileSize / 10)):
    print("Worth optimizing.")
    success = pdf.Optimize("optimize",json,jsonOut)
    if (success == False):
        print(pdf.LastErrorText)
        sys.exit()

    success = pdf.WriteFile("qa_output/watersense_optimized.pdf")
    if (success == False):
        print(pdf.LastErrorText)
        sys.exit()

    print("bytesSaved: " + str(jsonOut.IntOf("bytesSaved")))
else:
    print("Already small enough; left as it is.")