面向下一个 Python 应用的文档处理 SDK

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

# 应用许可证
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)

# 将两个 DOCX 文件合并为单个文档
with Merger("./part-a.docx") as merger:
    merger.join("./part-b.docx")
    merger.save("./output-merged.docx")

# 将合并后的 DOCX 转换为 PDF（PDF/A-2b，用于归档合规）
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

# 应用许可证
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)

# 将首页渲染为 HTML（或图像）用于预览/缩略图
with Viewer("bussiness-plan.docx") as viewer:
    view_options = HtmlViewOptions.for_embedded_resources()
    viewer.view(view_options, [1]) 

# 读取元数据（标题、作者、自定义属性）
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

# 应用许可证
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)

# 比较文档的两个版本
with Comparer("./proposal_v1.docx") as comparer:
    comparer.add("./proposal_v2.docx")
    comparer.compare("./proposal_diffs.docx")

# 定义用于编辑删除个人和公司信息的模式
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,}"

# 定义要执行的编辑删除
redactions = [
    RegexRedaction(email_pattern, replacement_options),
    RegexRedaction(phone_pattern, replacement_options),
]

# 对文档执行编辑删除
with Redactor("./proposal_diffs.docx") as redactor:
    for redaction in redactions:
        redactor.apply(redaction)

    # 设置保存选项以保持源文件格式
    save_options = SaveOptions()
    save_options.add_suffix = True
    save_options.rasterize_to_pdf = False
    save_options.redacted_file_suffix = "redacted"

    # 保存已编辑删除的文档
    redactor.save(save_options)