Compare Word, PDF, and PPT Documents in Python

document-comparison-in-python.md

Learn how to Compare Word, PDF, and PPT Documents in Python

document-comparison-in-python_compare_docx.py

# This code example demonstrates how to compare two Word files in Python
import aspose.words as aw
from datetime import date

# load first document
doc = aw.Document("Document.docx")

# load second document
doc2 = aw.Document("Document2.docx")

# compare documents
doc.compare(doc2, "user", date.today())

# save the document to get the revisions
if (doc.revisions.count > 0):
    doc.save("Compared_Document.docx")
else:
    print("Documents are equal")

document-comparison-in-python_compare_pdf.py

# This code example demonstrates how to compare two PDF files in Python
import aspose.words as aw
from datetime import date

# Load PDF files
PDF1 = aw.Document("Document.pdf")
PDF2 = aw.Document("Document2.pdf")

# Convert PDF files to Word format
PDF1.save("first.docx", aw.SaveFormat.DOCX)
PDF2.save("second.docx", aw.SaveFormat.DOCX)

# Load converted Word documents 
DOC1 = aw.Document("first.docx")
DOC2 = aw.Document("second.docx")

# Set comparison options
options = aw.comparing.CompareOptions()            
options.ignore_formatting = True
options.ignore_headers_and_footers = True
options.ignore_case_changes = True
options.ignore_tables = True
options.ignore_fields = True
options.ignore_comments = True
options.ignore_textboxes = True
options.ignore_footnotes = True

# DOC1 will contain changes as revisions after comparison
DOC1.compare(DOC2, "user", date.today(), options)

if (DOC1.revisions.count > 0):
    # Save resultant file as PDF
    DOC1.save("compared.pdf", aw.SaveFormat.PDF)
else:
    print("Documents are equal")

document-comparison-in-python_compare_slides.py

# This code example demonstrates how to compare two PowerPoint presentation slides in Python
import aspose.slides as slides

with slides.Presentation("AccessSlides.pptx") as p1:
    with slides.Presentation("HelloWorld.pptx") as p2:
        for i in range(len(p1.masters)):
            for j in range(len(p2.masters)):
                if p1.masters[i] == p2.masters[j]:
                    print("Presentation1 MasterSlide#{0} is equal to Presentation2 MasterSlide#{1}".format(i,j))
                else:
                    print("Presentation1 MasterSlide#{0} is not equal to Presentation2 MasterSlide#{1}".format(i,j))