Manage Document Metadata using Python

readme.md

View and Update Metadata of PDF, Microsoft Word, Powerpoint and Excel Spreadsheets via Python applications.

https://products.aspose.com/total/python-net/metadata/

add-properties-in-word-documents.py

docMetadata = aw.Document(my_dir + "Properties.docx")

customProperties = docMetadata.custom_document_properties
            
if (customProperties.get_by_name("Authorized") != None) :
    return
            
customProperties.add("Authorized", True)
customProperties.add("Authorized By", "John Smith")
customProperties.add("Authorized Date", datetime.today())
customProperties.add("Authorized Revision", doc.built_in_document_properties.revision_number)
customProperties.add("Authorized Amount", 123.45)

extract-and-view-pdf-metadata.py

import aspose.pdf as ap 

pdf_document = ap.Document(DIR_INPUT_METADATA + "GetFileInfo.pdf")

doc_info = pdf_document.info

print("Author :", doc_info.author)
print("Creation Date :", doc_info.creation_date)
print("Keywords :", doc_info.keywords)
print("Modify Date :", doc_info.mod_date)
print("Subject :", doc_info.subject)
print("Title :", doc_info.title)

update-pdf-metadata.py

import aspose.pdf as pdf
import datetime

pdfDoc = pdf.Document("input.pdf")

meta = pdf.DocumentInfo(pdfDoc)
meta.creator = "Creator Info"
meta.producer = "Producer Info"
meta.trapped = 'True'
meta.author = "Author info"
meta.creation_date = datetime.datetime.now()

pdfDoc.save("UpdatedMeta.pdf")

view-and-remove-excel-spreadsheet-properties.py

 wkb = self.Workbook(self.dataDir + "Book1.xls")

customProperties = wkb.getWorksheets().getCustomDocumentProperties()

#customProperty1 = customProperties.get(3)

customProperty2 = customProperties.get("Owner")

publisher = customProperties.add("Publisher", "Aspose")

wkb.save(self.dataDir + "Test_Workbook.xls")

customProperties.remove("Publisher")

wkb.save(dataDir + "Test_Workbook_RemovedProperty.xls")

view-and-update-powerpoint-properties.py

import aspose.slides as slides


with slides.Presentation(path + "AccessModifyingProperties.pptx") as presentation:

    documentProperties = presentation.document_properties


    for i in range(documentProperties.count_of_custom_properties):

        print("Custom Property Name : " + documentProperties.get_custom_property_name(i))
        print("Custom Property Value : " + documentProperties.get_custom_property_value[documentProperties.get_custom_property_name(i)])

        documentProperties.set_custom_property_value(documentProperties.get_custom_property_name(i), "New Value " + str(i + 1))

    presentation.save("CustomDemoModified_out.pptx", slides.export.SaveFormat.PPTX)

view-word-document-properties.py

doc = aw.Document(docs_base.my_dir + "Properties.docx")
            
print("1. Document name: 0", doc.original_file_name)
print("2. Built-in Properties")
            
for prop in doc.built_in_document_properties :
    print("0 : 1", prop.name, prop.value)

print("3. Custom Properties")
            
for prop in doc.custom_document_properties :
    print("0 : 1", prop.name, prop.value)