Python Requires Chilkat v11.7.0+

Remove a PDF's Old Revisions

See more PDF Optimization Examples

Demonstrates dropOldRevisions. A PDF that has been edited and saved several times carries every earlier revision: the superseded objects are still in the file, reachable through the older cross-reference sections. The audit reports them as "oldRevisions", and dropping them is often the single largest saving in a real document. Dropping them requires a full rewrite, which is why it invalidates existing digital signatures. 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 grand_canyon_hiking_guide.pdf

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

# How much of this file is superseded revisions?
json = chilkat2.JsonObject()
jsonOut = chilkat2.JsonObject()
success = pdf.Optimize("audit",json,jsonOut)
if (success == False):
    print(pdf.LastErrorText)
    sys.exit()

print("fileSize:     " + str(jsonOut.IntOf("fileSize")))
print("oldRevisions: " + str(jsonOut.IntOf("usage.oldRevisions.bytes")))

# Drop them, and nothing else, so that the saving is attributable.
json.UpdateBool("compressUncompressed",False)
json.UpdateBool("recompressFlate",False)
json.UpdateBool("replaceLegacyFilters",False)
json.UpdateBool("imagePredictors",False)
json.UpdateBool("dedupeStreams",False)
json.UpdateBool("dedupeObjects",False)
json.UpdateBool("removeUnreferenced",False)
json.UpdateBool("removeUnusedResources",False)
json.UpdateBool("removeUnusedLayers",False)
json.UpdateBool("coalesceContent",False)
json.UpdateBool("tidyContent",False)
json.UpdateBool("subsetFonts",False)
json.UpdateBool("dropOldRevisions",True)

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

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

# The saving is an estimate: what the old revisions occupied is known exactly, but the writer
# decides the final layout.  Measure the written file for the real number.
fac = chilkat2.FileAccess()
print("bytesSaved (reported): " + str(jsonOut.IntOf("bytesSaved")))
print("written file:          " + str(fac.FileSize("qa_output/grand_canyon_one_revision.pdf")))