SDK de procesamiento de documentos para su próxima aplicación Python

import os
from groupdocs.merger import License as MergerLicense, Merger
from groupdocs.conversion import License as ConversionLicense, Converter
from groupdocs.conversion.options.convert import PdfConvertOptions, PdfFormats

# Aplicar licencia
license_path = os.path.abspath("./GroupDocs.Total.lic")
if os.path.exists(license_path):
    merger_license = MergerLicense()
    merger_license.set_license(license_path)

    conversion_license = ConversionLicense()
    conversion_license.set_license(license_path)

# Fusionar dos archivos DOCX en un solo documento
with Merger("./part-a.docx") as merger:
    merger.join("./part-b.docx")
    merger.save("./output-merged.docx")

# Convertir el DOCX fusionado a PDF (PDF/A-2b para cumplimiento archivístico)
with Converter("./output-merged.docx") as converter:
    options = PdfConvertOptions()
    options.pdf_options.pdf_format = PdfFormats.PDF_A_2B
    converter.convert("./final-delivery.pdf", options)

import os
from groupdocs.viewer import License as ViewerLicense, Viewer
from groupdocs.viewer.options import HtmlViewOptions
from groupdocs.metadata import License as MetadataLicense, Metadata
from groupdocs.metadata.search import AnySpecification

# Aplicar licencia
license_path = os.path.abspath("./GroupDocs.Total.lic")

if os.path.exists(license_path):
    viewer_license = ViewerLicense()
    viewer_license.set_license(license_path)

    metadata_license = MetadataLicense()
    metadata_license.set_license(license_path)

# Renderizar la primera página a HTML (o imagen) para vista previa/miniatura
with Viewer("bussiness-plan.docx") as viewer:
    view_options = HtmlViewOptions.for_embedded_resources()
    viewer.view(view_options, [1]) 

# Leer metadatos (título, autor, propiedades personalizadas)
with Metadata("bussiness-plan.docx") as metadata:
   props = metadata.find_properties(AnySpecification())
   for prop in props:
       print(prop.name, prop.value)

import os
from groupdocs.comparison import License as ComparisonLicense, Comparer
from groupdocs.redaction import License as RedactionLicense, Redactor
from groupdocs.redaction.options import SaveOptions
from groupdocs.redaction.redactions import ReplacementOptions, RegexRedaction

# Aplicar licencia
license_path = os.path.abspath("./GroupDocs.Total.lic")

if os.path.exists(license_path):
    comparison_license = ComparisonLicense()
    comparison_license.set_license(license_path)

    redaction_license = RedactionLicense()
    redaction_license.set_license(license_path)

# Comparar dos versiones del documento
with Comparer("./proposal_v1.docx") as comparer:
    comparer.add("./proposal_v2.docx")
    comparer.compare("./proposal_diffs.docx")

# Definir patrones para redactar información personal y de la empresa
replacement_options = ReplacementOptions("[REDACTED]")
phone_pattern = r"\b(?:\+?1[-.\s]?)?(?:\(?\d{3}\)?[-.\s]?)\d{3}[-.\s]?\d{4}\b"
email_pattern = r"[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,}"

# Definir las redacciones a aplicar
redactions = [
    RegexRedaction(email_pattern, replacement_options),
    RegexRedaction(phone_pattern, replacement_options),
]

# Aplicar las redacciones al documento
with Redactor("./proposal_diffs.docx") as redactor:
    for redaction in redactions:
        redactor.apply(redaction)

    # Establecer opciones de guardado para mantener el formato del archivo origen
    save_options = SaveOptions()
    save_options.add_suffix = True
    save_options.rasterize_to_pdf = False
    save_options.redacted_file_suffix = "redacted"

    # Guardar el documento redactado
    redactor.save(save_options)