Documentation – Python 中的可访问性和标记 PDF

Python-Net: 使用 Python 创建带标签的 PDF

Mon, 08 Jun 2026 00:00:00 +0000

创建带标签的 PDF 意味着在文档中添加（或创建）某些元素，使文档能够根据 PDF/UA 要求进行验证。这些元素通常被称为结构元素。

创建带标签的 PDF（简单场景）

为了在带标签的 PDF 文档中创建结构元素，Aspose.PDF 提供了使用以下方法创建结构元素的方法 ItaggedContent 接口。此示例创建了带标签的 PDF 文档，即具有语义结构的 PDF，使其更易于访问且符合 PDF/UA 等标准。以下代码片段显示如何创建带标签的 PDF，其中包含 2 个元素：标题和段落。

import aspose.pdf as ap
import sys
from os import path

def create_tagged_pdf_document_simple(outfile):

    # Create PDF Document
    with ap.Document() as document:
        # Get Content for working with TaggedPdf
        tagged_content = document.tagged_content
        root_element = tagged_content.root_element

        # Set Title and Language for Document
        tagged_content.set_title("Tagged Pdf Document")
        tagged_content.set_language("en-US")
        main_header = tagged_content.create_header_element()
        main_header.set_text("Main Header")
        paragraph_element = tagged_content.create_paragraph_element()
        paragraph_element.set_text(
            "Lorem ipsum dolor sit amet, consectetur adipiscing elit. "
            + "Aenean nec lectus ac sem faucibus imperdiet. Sed ut erat ac magna ullamcorper hendrerit. "
            + "Cras pellentesque libero semper, gravida magna sed, luctus leo. Fusce lectus odio, laoreet "
            + "nec ullamcorper ut, molestie eu elit. Interdum et malesuada fames ac ante ipsum primis in faucibus. "
            + "Aliquam lacinia sit amet elit ac consectetur. Donec cursus condimentum ligula, vitae volutpat "
            + "sem tristique eget. Nulla in consectetur massa. Vestibulum vitae lobortis ante. Nulla ullamcorper "
            + "pellentesque justo rhoncus accumsan. Mauris ornare eu odio non lacinia. Aliquam massa leo, rhoncus "
            + "ac iaculis eget, tempus et magna. Sed non consectetur elit. Sed vulputate, quam sed lacinia luctus, "
            + "ipsum nibh fringilla purus, vitae posuere risus odio id massa. Cras sed venenatis lacus."
        )
        root_element.append_child(main_header, True)
        root_element.append_child(paragraph_element, True)

        # Save Tagged PDF Document
        document.save(outfile)

创建带标签的 PDF（高级）

import aspose.pdf as ap
import sys
from os import path

def create_tagged_pdf_document_adv(outfile):
    # Create PDF Document
    with ap.Document() as document:
        # Get Content for working with TaggedPdf
        tagged_content = document.tagged_content
        root_element = tagged_content.root_element

        # Set Title and Language for Document
        tagged_content.set_title("Tagged Pdf Document")
        tagged_content.set_language("en-US")

        # Create Header Level 1
        header1 = tagged_content.create_header_element(1)
        header1.set_text("Header Level 1")

        # Create Paragraph with Quotes
        paragraph_with_quotes = tagged_content.create_paragraph_element()
        paragraph_with_quotes.structure_text_state.font = (
            ap.text.FontRepository.find_font("Arial")
        )
        position_settings = ap.tagged.PositionSettings()
        position_settings.margin = ap.MarginInfo(10, 5, 10, 5)
        paragraph_with_quotes.adjust_position(position_settings)

        # Create Span Element
        span_element1 = tagged_content.create_span_element()
        span_element1.set_text(
            "Lorem ipsum dolor sit amet, consectetur adipiscing elit. Aenean nec lectus ac sem faucibus imperdiet. "
            "Sed ut erat ac magna ullamcorper hendrerit. Cras pellentesque libero semper, gravida magna sed, "
            "luctus leo. Fusce lectus odio, laoreet nec ullamcorper ut, molestie eu elit. Interdum et malesuada "
            "fames ac ante ipsum primis in faucibus. Aliquam lacinia sit amet elit ac consectetur. Donec cursus "
            "condimentum ligula, vitae volutpat sem tristique eget. Nulla in consectetur massa. Vestibulum vitae "
            "lobortis ante. Nulla ullamcorper pellentesque justo rhoncus accumsan. Mauris ornare eu odio non "
            "lacinia. Aliquam massa leo, rhoncus ac iaculis eget, tempus et magna. Sed non consectetur elit."
        )

        # Create Quote Element
        quote_element = tagged_content.create_quote_element()
        quote_element.set_text(
            "Sed vulputate, quam sed lacinia luctus, ipsum nibh fringilla purus, vitae posuere risus odio id massa."
        )
        quote_element.structure_text_state.font_style = (
            ap.text.FontStyles.BOLD | ap.text.FontStyles.ITALIC
        )

        # Create Another Span Element
        span_element2 = tagged_content.create_span_element()
        span_element2.set_text(" Sed non consectetur elit.")

        # Append Children to Paragraph
        paragraph_with_quotes.append_child(span_element1, True)
        paragraph_with_quotes.append_child(quote_element, True)
        paragraph_with_quotes.append_child(span_element2, True)

        # Append Header and Paragraph to Root Element
        root_element.append_child(header1, True)
        root_element.append_child(paragraph_with_quotes, True)

        # Save Tagged PDF Document
        document.save(outfile)

创建后我们将获得以下文档：

设置文本结构样式

带标签的 PDF 是结构化文档，为内容提供可访问性功能和语义含义。

该示例使用带标签的内容结构创建具有无障碍功能的 PDF 文档。它演示了如何使用自定义样式和适当的文档元数据制作段落元素。

import aspose.pdf as ap
import sys
from os import path

def add_style(outfile):

    # Create PDF Document
    with ap.Document() as document:
        # Get Content for work with TaggedPdf
        tagged_content = document.tagged_content

        # Set Title and Language for Document
        tagged_content.set_title("Tagged Pdf Document")
        tagged_content.set_language("en-US")

        paragraph_element = tagged_content.create_paragraph_element()
        tagged_content.root_element.append_child(paragraph_element, True)

        paragraph_element.structure_text_state.font_size = 18.0
        paragraph_element.structure_text_state.foreground_color = ap.Color.red
        paragraph_element.structure_text_state.font_style = ap.text.FontStyles.ITALIC

        paragraph_element.set_text("Red italic text.")

        # Save Tagged PDF Document
        document.save(outfile)

说明结构元素

带标签的 PDF 对于无障碍访问合规性至关重要，可提供可由屏幕阅读器和其他辅助技术正确解释的结构化内容。以下代码片段显示了如何使用嵌入式图像创建带标签的 PDF 文档：

使用图像创建带标签的 PDF。
配置文档。
创建和配置图。
设置定位。
保存文档。

import aspose.pdf as ap
import sys
from os import path

def illustrate_structure_elements(imagefile, outfile):
    # Create PDF Document
    with ap.Document() as document:
        # Get Content for work with TaggedPdf
        tagged_content = document.tagged_content

        # Set Title and Language for Document
        tagged_content.set_title("Tagged Pdf Document")
        tagged_content.set_language("en-US")
        figure1 = tagged_content.create_figure_element()
        tagged_content.root_element.append_child(figure1, True)
        figure1.alternative_text = "Figure One"
        figure1.title = "Image 1"
        figure1.set_tag("Fig1")
        figure1.set_image(imagefile, 300)
        # Adjust position
        position_settings = ap.tagged.PositionSettings()
        margin_info = ap.MarginInfo()
        margin_info.left = 50
        margin_info.top = 20
        position_settings.margin = margin_info
        figure1.adjust_position(position_settings)

        # Save Tagged PDF Document
        document.save(outfile)

验证带标签的 PDF

通过 .NET for Python 的 Aspose.PDF 提供了验证带有 PDF/UA 标签的 PDF 文档的功能。“validate_tagged_pdf” 方法根据 PDF/UA-1 标准验证 PDF 文档，该标准是 ISO 14289 可访问的 PDF 文档规范的一部分。这可确保残障用户和辅助技术用户可以访问 PDF。

文件结构。正确的语义标记和逻辑结构。
替代文本。图像和非文本元素的替代文本。
阅读顺序。屏幕阅读器的逻辑顺序。
颜色和对比度。足够的对比度。
表格。可访问的表单字段和标签。
导航。正确的书签和导航结构。

import aspose.pdf as ap
import sys
from os import path

def validate_tagged_pdf(infile, logfile):
    # Open PDF document
    with ap.Document(infile) as document:
        is_valid = document.validate(logfile, ap.PdfFormat.PDF_UA_1)
    print(f"Is Valid: {is_valid}")

调整文本结构的位置

以下代码片段显示了如何调整带标签的 PDF 文档中的文本结构位置：

import aspose.pdf as ap
import sys
from os import path

def adjust_position(outfile):
    # Create PDF Document
    with ap.Document() as document:
        # Get Content for work with TaggedPdf
        tagged_content = document.tagged_content

        # Set Title and Language for Document
        tagged_content.set_title("Tagged Pdf Document")
        tagged_content.set_language("en-US")

        # Create paragraph
        paragraph = tagged_content.create_paragraph_element()
        tagged_content.root_element.append_child(paragraph, True)
        paragraph.set_text("Text.")

        # Adjust position
        position_settings = ap.tagged.PositionSettings()
        margin_info = ap.MarginInfo()
        margin_info.left = 300
        margin_info.top = 20
        margin_info.right = 0
        margin_info.bottom = 0
        position_settings.margin = margin_info
        position_settings.horizontal_alignment = ap.HorizontalAlignment.NONE
        position_settings.vertical_alignment = ap.VerticalAlignment.NONE
        position_settings.is_first_paragraph_in_column = False
        position_settings.is_kept_with_next = False
        position_settings.is_in_new_page = False
        position_settings.is_in_line_paragraph = False
        paragraph.adjust_position(position_settings)

        # Save Tagged PDF Document
        document.save(outfile)

使用自动标记将 PDF 转换为 PDF/UA-1

此代码片段解释了如何使用适用于 Python 的 Aspose.PDF 通过.NET 将标准 PDF 转换为符合 PDF/UA-1（通用无障碍访问）的文件。

PDF/UA 确保残障用户可以访问文档，并与屏幕阅读器等辅助技术兼容。在转换过程中，该库可以自动生成逻辑结构树并使用内置的自动标记和标题识别应用语义标签。

通过配置 PDF 格式转换选项和启用 “自动标记设置”，您可以高效地将现有 PDF 转换为可访问的文档，而无需手动编辑结构。

加载源文档。
创建 PDF/UA 转换选项。
启用自动标记。
配置航向识别。
将标记配置附加到转换选项。
运行转换过程。
保存可访问的 PDF。

import aspose.pdf as ap
import sys
from os import path

def convert_to_pdf_ua_with_automatic_tagging(infile, outfile, logfile):
    # Create PDF Document
    with ap.Document(infile) as document:
        # Create conversion options
        options = ap.PdfFormatConversionOptions(
            logfile, ap.PdfFormat.PDF_UA_1, ap.ConvertErrorAction.DELETE
        )
        # Create auto-tagging settings
        # aspose.pdf.AutoTaggingSettings.default may be used to set the same settings as given below
        auto_tagging_settings = ap.AutoTaggingSettings()
        # Enable auto-tagging during the conversion process
        auto_tagging_settings.enable_auto_tagging = True
        # Use the heading recognition strategy that's optimal for the given document structure
        auto_tagging_settings.heading_recognition_strategy = (
            ap.HeadingRecognitionStrategy.AUTO
        )
        # Assign auto-tagging settings to be used during the conversion process
        options.auto_tagging_settings = auto_tagging_settings
        # During the conversion, the document logical structure will be automatically created
        document.convert(options)
        # Save PDF document
        document.save(outfile)

使用可访问的签名表单字段创建带标签的 PDF

创建新的 PDF 文档。
访问带标签的内容。
创建签名表单字段。
将该字段添加到 AcroForm。
在标签结构中创建表单元素。
将 “结构” 元素链接到 “表单” 字段。
将表单元素追加到逻辑结构树中。
保存文档。

import aspose.pdf as ap
import sys
from os import path

def create_pdf_with_tagged_form_field(outfile):
    # Create PDF document
    with ap.Document() as document:
        document.pages.add()
        # Get Content for work with TaggedPdf
        tagged_content = document.tagged_content
        root_element = tagged_content.root_element
        # Create a visible signature form field (AcroForm)
        signature_field = ap.forms.SignatureField(
            document.pages[1], ap.Rectangle(50, 50, 100, 100, True)
        )
        signature_field.partial_name = "Signature1"
        signature_field.alternate_name = "signature 1"

        # Add the signature field to the document's AcroForm
        document.form.add(signature_field)

        # Create a /Form structure element in the tag tree
        form = tagged_content.create_form_element()
        form.alternative_text = "form 1"

        # Link the /Form tag to the signature field via an /OBJR reference
        form.tag(signature_field)

        # Add the /Form structure element to the document’s logical structure tree
        root_element.append_child(form, True)

        # Save PDF document
        document.save(outfile)

使用目录 (TOC) 页面创建带标签的 PDF

此示例说明如何使用适用于 Python 的 Aspose.PDF 通过.NET 创建带有结构化目录 (TOC) 页面的带标签的 PDF 文档。

创建新的 PDF 文档。
创建专用的目录页面。
在逻辑结构树中创建和注册 TOC 元素。
添加内容页面。
创建标题元素。
创建 /TOCI 元素。
将标题链接到目录。
保存文档。

import aspose.pdf as ap
import sys
from os import path

def create_pdf_with_toc_page(outfile):
    # Create PDF document
    with ap.Document() as document:
        # Get tagged content for the PDF structure
        content = document.tagged_content
        root_element = content.root_element
        content.set_language("en-US")
        # Add the table of contents (TOC) page
        toc_page = document.pages.add()
        toc_page.toc_info = ap.TocInfo()
        # Create a TOC structure element
        toc_element = content.create_toc_element()
        # Add the TOC element to the document structure tree
        root_element.append_child(toc_element, True)
        # Add a content page
        document.pages.add()
        # Create a header element and set its text
        header = content.create_header_element(1)
        header.set_text("1. Header")
        # Add the header to the document structure
        root_element.append_child(header, True)
        # Create a TOC item (TOCI) element
        toci = content.create_toci_element()
        # Add the TOCI element to the TOC element
        toc_element.append_child(toci, True)
        # Add an entry to the TOC page and link it to the TOCI element
        header.add_entry_to_toc_page(toc_page, toci)
        # Add a logical reference to the header within the TOCI element
        toci.add_ref(header)
        # Save PDF document
        document.save(outfile)

使用分层目录 (TOC) 创建带有高级标签的 PDF

通过.NET 使用 Python 版 Aspose.PDF，您可以创建具有结构化和分层目录表 (TOC) 的高级、带完整标签的 PDF 文档。

创建文档并启用带标签的内容。
添加和配置 TOC 页面。
创建 /TOC 结构元素。
将 TOC 页面标题链接到标题元素。
添加主内容页面和第一个标题。
为标题创建 TOC 条目。
使用列表结构创建嵌套小节。
添加第二个顶级版块。
保存文档。

import aspose.pdf as ap
import sys
from os import path

def create_pdf_with_toc_page_advanced(outfile):
    # Create PDF document
    with ap.Document() as document:
        # Get tagged content for the PDF structure
        content = document.tagged_content
        root_element = content.root_element
        content.set_language("en-US")
        # Add the table of contents (TOC) page
        toc_page = document.pages.add()
        toc_page.toc_info = ap.TocInfo()
        toc_page.toc_info.title = ap.text.TextFragment("Table of Contents")
        # Create a TOC structure element
        toc_element = content.create_toc_element()
        # Create a header element for the TOC page title
        header_for_toc_page_title = content.create_header_element(1)
        toc_element.link_toc_page_title_to_header_element(
            toc_page, header_for_toc_page_title
        )
        # Add the TOC page title header and TOC element to the document structure tree
        root_element.append_child(header_for_toc_page_title, True)
        root_element.append_child(toc_element, True)
        # Add a content page
        document.pages.add()
        # Create a header element and set its text
        header = content.create_header_element(1)
        header.set_text("1. Header")
        # Add the header to the document structure
        root_element.append_child(header, True)
        # Create a TOC item (TOCI) element
        toci = content.create_toci_element()
        # Add the TOCI element to the TOC element
        toc_element.append_child(toci, True)
        # Add an entry to the TOC page and link it to the TOCI element
        header.add_entry_to_toc_page(toc_page, toci)
        # Add a logical reference to the header within the TOCI element
        toci.add_ref(header)
        # Create a list element for TOCI subitems
        list_element = content.create_list_element()
        for i in range(1, 4):
            # Create a list item (LI) element
            li = content.create_list_li_element()
            # Add the list item to the list element
            list_element.append_child(li, True)
            # Create a sub-header element and set its properties
            sub_header = content.create_header_element(2)
            sub_header.structure_text_state.font_size = 14
            sub_header.language = "en-US"
            sub_header.set_text(f"1.{i} subheader ")
            # Add an entry to the TOC page and link it to the LI element
            sub_header.add_entry_to_toc_page(toc_page, li)
            # Add a logical reference to the subheader element
            li.add_ref(sub_header)
            # Create a paragraph element and set its text and language
            p = content.create_paragraph_element()
            p.set_text(
                "Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum."
            )
            p.language = "en-US"
            # Add the sub-header and paragraph to the document structure
            root_element.append_child(sub_header, True)
            root_element.append_child(p, True)
        # Add the list element as a child to the TOCI element
        toci.append_child(list_element, True)
        # --- Additional TOC header example ---
        # Create a second header element (see comments above for header 1)
        header2 = content.create_header_element(1)
        header2.set_text("2. Header")
        root_element.append_child(header2, True)

        toci2 = content.create_toci_element()
        toc_element.append_child(toci2, True)

        header2.add_entry_to_toc_page(toc_page, toci2)
        toci2.add_ref(header2)
        # Save the PDF document
        document.save(outfile)

Python-Net: 在 Python 中从 PDF 中提取带标签的内容

Mon, 08 Jun 2026 00:00:00 +0000

在本文中，您将学习如何使用 Python 从 PDF 文档中提取带标签的内容。

当您需要检查带标签的 PDF、阅读逻辑结构树或验证结构元素是否为无障碍工作流程正确创建时，请使用这些示例。

获取带标签的 PDF 内容

为了获取带有标签文本的 PDF 文档的内容，Aspose.PDF 提供已标记内容的财产文档班级。

使用结构化和分层的目录 (TOC) 创建高级、带完整标签的 PDF 文档：

创建新的 Document 对象。
访问 tagged_content 属性。
使用 “set_title ()” 设置文档标题。
使用 “set_language ()” 设置文档语言。
保存文档。

import aspose.pdf as ap
from aspose.pycore import cast
import sys
from os import path

# region Extract Tagged Content from PDF
def get_tagged_content(outfile):
    # Create PDF Document
    with ap.Document() as document:
        # Get Content for work with Tagged PDF
        tagged_content = document.tagged_content

        # Work with Tagged PDF content
        # Set Title and Language for Document
        tagged_content.set_title("Simple Tagged Pdf Document")
        tagged_content.set_language("en-US")

        # Save Tagged PDF Document
        document.save(outfile)

获取根结构

带标签的 PDF 包含定义文档语义结构的逻辑结构树。StructTreeRoot 代表该逻辑树的根，而 rootElement 则提供了与文档的顶级结构元素进行交互的接口。

以下代码片段显示了如何获取带标签的 PDF 文档的根结构：

创建新的带标签的 PDF 文档。
访问带标签的内容并设置元数据。
访问 StructTreeRoot 和 rootElement。
保存带标签的 PDF。

import aspose.pdf as ap
from aspose.pycore import cast
import sys
from os import path

def get_root_structure(outfile):

    # Create PDF Document
    with ap.Document() as document:
        # Get Content for work with Tagged PDF
        tagged_content = document.tagged_content

        # Set Title and Language for Document
        tagged_content.set_title("Tagged Pdf Document")
        tagged_content.set_language("en-US")

        # Properties StructTreeRootElement and RootElement are used for access to
        # StructTreeRoot object of pdf document and to root structure element (Document structure element).
        struct_tree_root_element = tagged_content.struct_tree_root_element
        root_element = tagged_content.root_element

        print(f"StructTreeRootElement: {struct_tree_root_element}")
        print(f"RootElement: {root_element}")

        # Save Tagged PDF Document
        document.save(outfile)

访问子元素

带标签的 PDF 包含逻辑结构树，用于定义文档的语义层次结构（标题、段落、表单、列表等）。访问和修改这些结构元素允许您：

检查元数据，例如标题、语言、actual_text 和无障碍相关属性
更新属性以改善可访问性或本地化
以编程方式调整逻辑文档结构以符合 PDF/UA

以下代码片段显示了如何访问带标签的 PDF 文档的子元素：

import aspose.pdf as ap
from aspose.pycore import cast
import sys
from os import path

def access_child_elements(infile, outfile):

    # Open PDF Document
    with ap.Document(infile) as document:
        # Get Content for work with Tagged PDF
        tagged_content = document.tagged_content

        # Access to root element(s)
        element_list = tagged_content.struct_tree_root_element.child_elements

        for element in element_list:
            if isinstance(element, ap.logicalstructure.StructureElement):
                structure_element = cast(ap.logicalstructure.StructureElement, element)
                # Get properties
                print(
                    "StructureElement properties - "
                    f"title: {structure_element.title}, "
                    f"language: {structure_element.language}, "
                    f"actual_text: {structure_element.actual_text}, "
                    f"expansion_text: {structure_element.expansion_text}, "
                    f"alternative_text: {structure_element.alternative_text}"
                )

        # Access to child elements of first element in root element
        element_list = tagged_content.root_element.child_elements[1].child_elements
        for element in element_list:
            if isinstance(element, ap.logicalstructure.StructureElement):
                structure_element = element

                # Set properties
                structure_element.title = "title"
                structure_element.language = "fr-FR"
                structure_element.actual_text = "actual text"
                structure_element.expansion_text = "exp"
                structure_element.alternative_text = "alt"

        # Save Tagged PDF Document
        document.save(outfile)

Python-Net: 在 Python 中设置 Tagged PDF Structure Element 属性

Mon, 08 Jun 2026 00:00:00 +0000

Structure elements 定义 PDF 文档的语义层次结构，例如章节、标题、段落或表格。通过设置 title、language、alternative_text、actual_text 和 expansion_text 等属性，您可以提升 PDF 对屏幕阅读器等辅助技术的可访问性和语义意义。

以下代码片段展示了如何设置标记 PDF 文档的结构元素属性：

创建一个新的标记 PDF 文档。
设置文档元数据。
创建结构元素。
设置可访问性属性。
保存 Tagged PDF。

import aspose.pdf as ap
import sys
from os import path

def set_properties(outfile):
    # Create PDF Document
    with ap.Document() as document:
        # Get Content for work with Tagged PDF
        tagged_content = document.tagged_content

        # Set Title and Language for Document
        tagged_content.set_title("Tagged Pdf Document")
        tagged_content.set_language("en-US")

        # Create Structure Elements
        root_element = tagged_content.root_element

        section_element = tagged_content.create_sect_element()
        root_element.append_child(section_element, True)

        header_element = tagged_content.create_header_element(1)
        section_element.append_child(header_element, True)
        header_element.set_text("The Header")

        header_element.title = "Title"
        header_element.language = "en-US"
        header_element.alternative_text = "Alternative Text"
        header_element.expansion_text = "Expansion Text"
        header_element.actual_text = "Actual Text"

        # Save Tagged PDF Document
        document.save(outfile)

设置文本结构元素

为了设置 Tagged PDF 文档的文本结构元素，Aspose.PDF 提供段落元素类。以下代码片段展示了如何设置 Tagged PDF 文档的文本结构元素：

import aspose.pdf as ap
import sys
from os import path

def set_text_elements(outfile):
    # Create PDF Document
    with ap.Document() as document:
        # Get Content for work with Tagged PDF
        tagged_content = document.tagged_content

        # Set Title and Language for Document
        tagged_content.set_title("Tagged Pdf Document")
        tagged_content.set_language("en-US")

        # Get Root Structure Elements
        root_element = tagged_content.root_element

        paragraph_element = tagged_content.create_paragraph_element()

        # Set Text to Text Structure Element
        paragraph_element.set_text("Paragraph.")
        root_element.append_child(paragraph_element, True)

        # Save Tagged PDF Document
        document.save(outfile)

设置文本块结构元素

此 Python 示例使用 Aspose.PDF 创建一个带有结构化层次标题和段落的 Tagged PDF，提升文档的语义和可访问性特性。

创建一个新的标记 PDF 文档。
设置文档元数据。
访问根结构元素。
创建多级标题。
将标题追加到根结构。
创建一个段落元素。
将段落追加到根结构。
保存 Tagged PDF。

以下代码片段展示了如何设置 Tagged PDF 文档的文本块结构元素：

import aspose.pdf as ap
import sys
from os import path

def set_text_block_elements(outfile):
    # Create PDF Document
    with ap.Document() as document:
        # Get Content for work with Tagged PDF
        tagged_content = document.tagged_content
        # Set Title and Language for Document
        tagged_content.set_title("Tagged Pdf Document")
        tagged_content.set_language("en-US")
        # Get Root Structure Element
        root_element = tagged_content.root_element
        h1 = tagged_content.create_header_element(1)
        h2 = tagged_content.create_header_element(2)
        h3 = tagged_content.create_header_element(3)
        h4 = tagged_content.create_header_element(4)
        h5 = tagged_content.create_header_element(5)
        h6 = tagged_content.create_header_element(6)
        h1.set_text("H1. Header of Level 1")
        h2.set_text("H2. Header of Level 2")
        h3.set_text("H3. Header of Level 3")
        h4.set_text("H4. Header of Level 4")
        h5.set_text("H5. Header of Level 5")
        h6.set_text("H6. Header of Level 6")
        root_element.append_child(h1, True)
        root_element.append_child(h2, True)
        root_element.append_child(h3, True)
        root_element.append_child(h4, True)
        root_element.append_child(h5, True)
        root_element.append_child(h6, True)
        p = tagged_content.create_paragraph_element()
        p.set_text(
            "P. Lorem ipsum dolor sit amet, consectetur adipiscing elit. "
            "Aenean nec lectus ac sem faucibus imperdiet. Sed ut erat ac magna ullamcorper hendrerit."
            " Cras pellentesque libero semper, gravida magna sed, luctus leo. "
            "Fusce lectus odio, laoreet nec ullamcorper ut, molestie eu elit. "
            "Interdum et malesuada fames ac ante ipsum primis in faucibus. "
            "Aliquam lacinia sit amet elit ac consectetur. "
            "Donec cursus condimentum ligula, vitae volutpat sem tristique eget. "
            "Nulla in consectetur massa. Vestibulum vitae lobortis ante. "
            "Nulla ullamcorper pellentesque justo rhoncus accumsan. "
            "Mauris ornare eu odio non lacinia. Aliquam massa leo, rhoncus ac iaculis eget, tempus et magna. "
            "Sed non consectetur elit. Sed vulputate, quam sed lacinia luctus, ipsum nibh fringilla purus, "
            "vitae posuere risus odio id massa. Cras sed venenatis lacus."
        )
        root_element.append_child(p, True)
        # Save Tagged PDF Document
        document.save(outfile)

设置内联结构元素

使用 Aspose.PDF for Python via .NET 在 Tagged PDF 的标题和段落中创建内联文本元素（/Span）。

以下代码片段展示了如何设置 Tagged PDF 文档的内联结构元素：

import aspose.pdf as ap
import sys
from os import path

def set_inline_elements(outfile):
    # Create PDF Document
    with ap.Document() as document:
        # Get Content for work with Tagged PDF
        tagged_content = document.tagged_content

        # Set Title and Language for Document
        tagged_content.set_title("Tagged Pdf Document")
        tagged_content.set_language("en-US")

        # Get Root Structure Element
        root_element = tagged_content.root_element

        header_element_h1 = tagged_content.create_header_element(1)
        header_element_h2 = tagged_content.create_header_element(2)
        header_element_h3 = tagged_content.create_header_element(3)
        header_element_h4 = tagged_content.create_header_element(4)
        header_element_h5 = tagged_content.create_header_element(5)
        header_element_h6 = tagged_content.create_header_element(6)
        root_element.append_child(header_element_h1, True)
        root_element.append_child(header_element_h2, True)
        root_element.append_child(header_element_h3, True)
        root_element.append_child(header_element_h4, True)
        root_element.append_child(header_element_h5, True)
        root_element.append_child(header_element_h6, True)

        span_element_h11 = tagged_content.create_span_element()
        span_element_h11.set_text("H1. ")
        header_element_h1.append_child(span_element_h11, True)
        span_element_h12 = tagged_content.create_span_element()
        span_element_h12.set_text("Level 1 Header")
        header_element_h1.append_child(span_element_h12, True)

        span_element_h21 = tagged_content.create_span_element()
        span_element_h21.set_text("H2. ")
        header_element_h2.append_child(span_element_h21, True)
        span_element_h22 = tagged_content.create_span_element()
        span_element_h22.set_text("Level 2 Header")
        header_element_h2.append_child(span_element_h22, True)

        span_element_h31 = tagged_content.create_span_element()
        span_element_h31.set_text("H3. ")
        header_element_h3.append_child(span_element_h31, True)
        span_element_h32 = tagged_content.create_span_element()
        span_element_h32.set_text("Level 3 Header")
        header_element_h3.append_child(span_element_h32, True)

        span_element_h41 = tagged_content.create_span_element()
        span_element_h41.set_text("H4. ")
        header_element_h4.append_child(span_element_h41, True)
        span_element_h42 = tagged_content.create_span_element()
        span_element_h42.set_text("Level 4 Header")
        header_element_h4.append_child(span_element_h42, True)

        span_element_h51 = tagged_content.create_span_element()
        span_element_h51.set_text("H5. ")
        header_element_h5.append_child(span_element_h51, True)
        span_element_h52 = tagged_content.create_span_element()
        span_element_h52.set_text("Level 5 Header")
        header_element_h5.append_child(span_element_h52, True)

        span_element_h61 = tagged_content.create_span_element()
        span_element_h61.set_text("H6. ")
        header_element_h6.append_child(span_element_h61, True)
        span_element_h62 = tagged_content.create_span_element()
        span_element_h62.set_text("Level 6 Header")
        header_element_h6.append_child(span_element_h62, True)

        paragraph_element = tagged_content.create_paragraph_element()
        paragraph_element.set_text("P. ")
        root_element.append_child(paragraph_element, True)
        span_element_1 = tagged_content.create_span_element()
        span_element_1.set_text(
            "Lorem ipsum dolor sit amet, consectetur adipiscing elit. "
        )
        paragraph_element.append_child(span_element_1, True)
        span_element_2 = tagged_content.create_span_element()
        span_element_2.set_text("Aenean nec lectus ac sem faucibus imperdiet. ")
        paragraph_element.append_child(span_element_2, True)
        span_element_3 = tagged_content.create_span_element()
        span_element_3.set_text("Sed ut erat ac magna ullamcorper hendrerit. ")
        paragraph_element.append_child(span_element_3, True)
        span_element_4 = tagged_content.create_span_element()
        span_element_4.set_text(
            "Cras pellentesque libero semper, gravida magna sed, luctus leo. "
        )
        paragraph_element.append_child(span_element_4, True)
        span_element_5 = tagged_content.create_span_element()
        span_element_5.set_text(
            "Fusce lectus odio, laoreet nec ullamcorper ut, molestie eu elit. "
        )
        paragraph_element.append_child(span_element_5, True)
        span_element_6 = tagged_content.create_span_element()
        span_element_6.set_text(
            "Interdum et malesuada fames ac ante ipsum primis in faucibus. "
        )
        paragraph_element.append_child(span_element_6, True)
        span_element_7 = tagged_content.create_span_element()
        span_element_7.set_text(
            "Aliquam lacinia sit amet elit ac consectetur. Donec cursus condimentum ligula, vitae volutpat sem tristique eget. "
        )
        paragraph_element.append_child(span_element_7, True)
        span_element_8 = tagged_content.create_span_element()
        span_element_8.set_text(
            "Nulla in consectetur massa. Vestibulum vitae lobortis ante. Nulla ullamcorper pellentesque justo rhoncus accumsan. "
        )
        paragraph_element.append_child(span_element_8, True)
        span_element_9 = tagged_content.create_span_element()
        span_element_9.set_text(
            "Mauris ornare eu odio non lacinia. Aliquam massa leo, rhoncus ac iaculis eget, tempus et magna. Sed non consectetur elit. "
        )
        paragraph_element.append_child(span_element_9, True)
        span_element_10 = tagged_content.create_span_element()
        span_element_10.set_text(
            "Sed vulputate, quam sed lacinia luctus, ipsum nibh fringilla purus, vitae posuere risus odio id massa. Cras sed venenatis lacus."
        )
        paragraph_element.append_child(span_element_10, True)

        # Save Tagged PDF Document
        document.save(outfile)

设置自定义标签名称

使用 Aspose.PDF for Python 为带标签的 PDF 设置结构和内联元素的自定义标签名称。

以下代码片段展示了如何设置自定义标签名称：

创建一个新的标记 PDF 文档。
设置文档元数据。
创建一个section元素。
创建带有自定义标签的段落元素。
创建带有自定义标签的内联 span 元素。
保存 Tagged PDF。

import aspose.pdf as ap
import sys
from os import path

def set_tag_name(outfile):
    # Create PDF Document
    with ap.Document() as document:
        # Get Content for work with Tagged PDF
        tagged_content = document.tagged_content

        # Set Title and Language for Document
        tagged_content.set_title("Tagged Pdf Document")
        tagged_content.set_language("en-US")

        # Create Logical Structure Elements
        section_element = tagged_content.create_sect_element()
        tagged_content.root_element.append_child(section_element, True)

        paragraph_element1 = tagged_content.create_paragraph_element()
        paragraph_element2 = tagged_content.create_paragraph_element()
        paragraph_element3 = tagged_content.create_paragraph_element()
        paragraph_element4 = tagged_content.create_paragraph_element()

        paragraph_element1.set_text("P1. ")
        paragraph_element2.set_text("P2. ")
        paragraph_element3.set_text("P3. ")
        paragraph_element4.set_text("P4. ")

        paragraph_element1.set_tag("P1")
        paragraph_element2.set_tag("Para")
        paragraph_element3.set_tag("Para")
        paragraph_element4.set_tag("Paragraph")

        section_element.append_child(paragraph_element1, True)
        section_element.append_child(paragraph_element2, True)
        section_element.append_child(paragraph_element3, True)
        section_element.append_child(paragraph_element4, True)

        span_element1 = tagged_content.create_span_element()
        span_element2 = tagged_content.create_span_element()
        span_element3 = tagged_content.create_span_element()
        span_element4 = tagged_content.create_span_element()

        span_element1.set_text("Span 1.")
        span_element2.set_text("Span 2.")
        span_element3.set_text("Span 3.")
        span_element4.set_text("Span 4.")

        span_element1.set_tag("SPAN")
        span_element2.set_tag("Sp")
        span_element3.set_tag("Sp")
        span_element4.set_tag("TheSpan")

        paragraph_element1.append_child(span_element1, True)
        paragraph_element2.append_child(span_element2, True)
        paragraph_element3.append_child(span_element3, True)
        paragraph_element4.append_child(span_element4, True)

        # Save Tagged PDF Document
        document.save(outfile)

将结构元素添加到元素中

此功能在 19.4 版或更高版本中受支持。

使用 Aspose.PDF for Python via .NET 在标记 PDF 中创建链接和图像元素。

下面的代码片段演示了如何在段落中使用 Tagged PDF 文档的文本设置结构元素：

import aspose.pdf as ap
import sys
from os import path

def set_elements(imagefile, outfile):
    # Create PDF document
    with ap.Document() as document:
        tagged_content = document.tagged_content

        # Setting Title and Nature Language for document
        tagged_content.set_title("Link Elements Example")
        tagged_content.set_language("en-US")

        # Getting Root structure element (Document structure element)
        root_element = tagged_content.root_element

        paragraph_element_1 = tagged_content.create_paragraph_element()
        root_element.append_child(paragraph_element_1, True)
        link_element_1 = tagged_content.create_link_element()
        paragraph_element_1.append_child(link_element_1, True)
        link_element_1.hyperlink = ap.WebHyperlink("http://google.com")
        link_element_1.set_text("Google")
        link_element_1.alternate_descriptions = "Link to Google"

        paragraph_element_2 = tagged_content.create_paragraph_element()
        root_element.append_child(paragraph_element_2, True)
        link_element_2 = tagged_content.create_link_element()
        paragraph_element_2.append_child(link_element_2, True)
        link_element_2.hyperlink = ap.WebHyperlink("http://google.com")
        span_element_2 = tagged_content.create_span_element()
        span_element_2.set_text("Google")
        link_element_2.append_child(span_element_2, True)
        link_element_2.alternate_descriptions = "Link to Google"

        paragraph_element_3 = tagged_content.create_paragraph_element()
        root_element.append_child(paragraph_element_3, True)
        link_element_3 = tagged_content.create_link_element()
        paragraph_element_3.append_child(link_element_3, True)
        link_element_3.hyperlink = ap.WebHyperlink("http://google.com")
        span_element_31 = tagged_content.create_span_element()
        span_element_31.set_text("G")
        span_element_32 = tagged_content.create_span_element()
        span_element_32.set_text("Google")
        link_element_3.append_child(span_element_31, True)
        link_element_3.set_text("-")
        link_element_3.append_child(span_element_32, True)
        link_element_3.alternate_descriptions = "Link to Google"

        paragraph_element_4 = tagged_content.create_paragraph_element()
        root_element.append_child(paragraph_element_4, True)
        link_element_4 = tagged_content.create_link_element()
        paragraph_element_4.append_child(link_element_4, True)
        link_element_4.hyperlink = ap.WebHyperlink("http://google.com")
        link_element_4.set_text(
            "The multiline link: Google Google Google Google Google Google Google Google Google Google Google Google Google Google Google Google Google Google Google Google"
        )
        link_element_4.alternate_descriptions = "Link to Google (multiline)"

        paragraph_element_5 = tagged_content.create_paragraph_element()
        root_element.append_child(paragraph_element_5, True)
        link_element_5 = tagged_content.create_link_element()
        paragraph_element_5.append_child(link_element_5, True)
        link_element_5.hyperlink = ap.WebHyperlink("http://google.com")
        figure_element_5 = tagged_content.create_figure_element()
        figure_element_5.set_image(imagefile, 1200)
        figure_element_5.alternative_text = "Google icon"
        link_layout_attributes = link_element_5.attributes.get_attributes(
            ap.logicalstructure.AttributeOwnerStandard.LAYOUT
        )
        placement_attribute = ap.logicalstructure.StructureAttribute(
            ap.logicalstructure.AttributeKey.PLACEMENT
        )
        placement_attribute.set_name_value(
            ap.logicalstructure.AttributeName.PLACEMENT_BLOCK
        )
        link_layout_attributes.set_attribute(placement_attribute)
        link_element_5.append_child(figure_element_5, True)
        link_element_5.alternate_descriptions = "Link to Google"

        # Save Tagged PDF Document
        document.save(outfile)

设置链接结构元素

Aspose.PDF for Python via .NET API 还允许您添加链接结构元素。

下面的代码片段演示了如何向 Tagged PDF 文档中添加链接结构元素：

import aspose.pdf as ap
import sys
from os import path

def add_link_element(outfile):
    # Create PDF document
    with ap.Document() as document:
        tagged_content = document.tagged_content

        # Setting Title and Nature Language for document
        tagged_content.set_title("Text Elements Example")
        tagged_content.set_language("en-US")

        # Getting Root structure element (Document structure element)
        root_element = tagged_content.root_element

        paragraph_element_1 = tagged_content.create_paragraph_element()
        root_element.append_child(paragraph_element_1, True)
        span_element_11 = tagged_content.create_span_element()
        span_element_11.set_text("Span_11")
        span_element_12 = tagged_content.create_span_element()
        span_element_12.set_text(" and Span_12.")
        paragraph_element_1.set_text("Paragraph with ")
        paragraph_element_1.append_child(span_element_11, True)
        paragraph_element_1.append_child(span_element_12, True)

        paragraph_element_2 = tagged_content.create_paragraph_element()
        root_element.append_child(paragraph_element_2, True)
        span_element_21 = tagged_content.create_span_element()
        span_element_21.set_text("Span_21")
        span_element_22 = tagged_content.create_span_element()
        span_element_22.set_text("Span_22.")
        paragraph_element_2.append_child(span_element_21, True)
        paragraph_element_2.set_text(" and ")
        paragraph_element_2.append_child(span_element_22, True)

        paragraph_element_3 = tagged_content.create_paragraph_element()
        root_element.append_child(paragraph_element_3, True)
        span_element_31 = tagged_content.create_span_element()
        span_element_31.set_text("Span_31")
        span_element_32 = tagged_content.create_span_element()
        span_element_32.set_text(" and Span_32")
        paragraph_element_3.append_child(span_element_31, True)
        paragraph_element_3.append_child(span_element_32, True)
        paragraph_element_3.set_text(".")

        paragraph_element_4 = tagged_content.create_paragraph_element()
        root_element.append_child(paragraph_element_4, True)
        span_element_41 = tagged_content.create_span_element()
        span_element_411 = tagged_content.create_span_element()
        span_element_411.set_text("Span_411, ")
        span_element_41.set_text("Span_41, ")
        span_element_41.append_child(span_element_411, True)
        span_element_42 = tagged_content.create_span_element()
        span_element_421 = tagged_content.create_span_element()
        span_element_421.set_text("Span 421 and ")
        span_element_42.append_child(span_element_421, True)
        span_element_42.set_text("Span_42")
        paragraph_element_4.append_child(span_element_41, True)
        paragraph_element_4.append_child(span_element_42, True)
        paragraph_element_4.set_text(".")

        # Save Tagged PDF Document
        document.save(outfile)

设置 Note 结构元素

Aspose.PDF for Python via .NET API 还允许您添加注释元素在标记的 PDF 文档中。下面的代码片段展示了如何在 Tagged PDF 文档中添加 note 元素：

import aspose.pdf as ap
import sys
from os import path

def set_note_element(outfile):
    # Create PDF Document
    with ap.Document() as document:
        tagged_content = document.tagged_content

        tagged_content.set_title("Sample of Note Elements")
        tagged_content.set_language("en-US")

        # Add Paragraph Element
        paragraph_element = tagged_content.create_paragraph_element()
        tagged_content.root_element.append_child(paragraph_element, True)

        # Add NoteElement
        note_element_1 = tagged_content.create_note_element()
        paragraph_element.append_child(note_element_1, True)
        note_element_1.set_text("Note with auto generate ID. ")

        # Add NoteElement
        note_element_2 = tagged_content.create_note_element()
        paragraph_element.append_child(note_element_2, True)
        note_element_2.set_text("Note with ID = 'note_002'. ")
        note_element_2.set_id("note_002")

        # Add NoteElement
        note_element_3 = tagged_content.create_note_element()
        paragraph_element.append_child(note_element_3, True)
        note_element_3.set_text("Note with ID = 'note_003'. ")
        note_element_3.set_id("note_003")

        # Must throw exception - Aspose.Pdf.Tagged.TaggedException : Structure element with ID='note_002' already exists
        # note_element_3.set_id("note_002")

        # Resultant document does not compliance to PDF/UA If ClearId() used for Note Structure Element
        # note_element_3.clear_id()

        # Save Tagged PDF Document
        document.save(outfile)

如何设置语言和标题

Aspose.PDF for Python via .NET API 还允许您根据 PDF/UA 规范为文档设置语言和标题。语言既可以为整个文档设置，也可以为其各个结构元素单独设置。以下代码片段展示了如何在 Tagged PDF Document 中设置语言和标题：

创建一个新的标记 PDF 文档。
设置文档标题和语言。
创建一个标题元素。
添加具有特定语言的段落。
保存 Tagged PDF。

import aspose.pdf as ap
import sys
from os import path

def set_language_and_title(outfile):
    # Create PDF Document
    with ap.Document() as document:
        # Get TaggedContent
        tagged_content = document.tagged_content

        # Set Title and Language
        tagged_content.set_title("Example Tagged Document")
        tagged_content.set_language("en-US")

        # Header (en-US, inherited from document)
        header_element = tagged_content.create_header_element(1)
        header_element.set_text("Phrase on different languages")
        tagged_content.root_element.append_child(header_element, True)

        # Paragraph (English)
        paragraph_element_en = tagged_content.create_paragraph_element()
        paragraph_element_en.set_text("Hello, World!")
        paragraph_element_en.language = "en-US"
        tagged_content.root_element.append_child(paragraph_element_en, True)

        # Paragraph (German)
        paragraph_element_de = tagged_content.create_paragraph_element()
        paragraph_element_de.set_text("Hallo Welt!")
        paragraph_element_de.language = "de-DE"
        tagged_content.root_element.append_child(paragraph_element_de, True)

        # Paragraph (French)
        paragraph_element_fr = tagged_content.create_paragraph_element()
        paragraph_element_fr.set_text("Bonjour le monde!")
        paragraph_element_fr.language = "fr-FR"
        tagged_content.root_element.append_child(paragraph_element_fr, True)

        # Paragraph (Spanish)
        paragraph_element_sp = tagged_content.create_paragraph_element()
        paragraph_element_sp.set_text("¡Hola Mundo!")
        paragraph_element_sp.language = "es-ES"
        tagged_content.root_element.append_child(paragraph_element_sp, True)

        # Save Tagged PDF Document
        document.save(outfile)

Python-Net: 在 Python 中处理 Tagged PDF 表格

Mon, 08 Jun 2026 00:00:00 +0000

在 Tagged PDF 中创建表格

通过遵循上述步骤，您可以使用 Aspose.PDF for Python 在 PDF 文档中生成语义丰富、可访问的表格。生成的文件符合 PDF/UA-1 合规标准，确保与屏幕阅读器和辅助技术的兼容性。这非常适用于涉及法规遵从、可访问性审计和包容性内容发布的使用场景。

以下代码片段展示了如何在 Tagged PDF 文档中创建表格：

创建一个新的标记 PDF 文档。
设置文档元数据。
创建表结构。
创建表头行。
创建表体行及其单元格。
创建表格页脚行。
设置表格摘要属性。
保存已标记的 PDF。

import aspose.pdf as ap
import sys
from os import path

def create_table(outfile):
    # Create PDF document
    with ap.Document() as document:
        tagged_content = document.tagged_content

        tagged_content.set_title("Example table")
        tagged_content.set_language("en-US")

        # Get root structure element
        root_element = tagged_content.root_element

        table_element = tagged_content.create_table_element()
        root_element.append_child(table_element, True)

        table_element.border = ap.BorderInfo(ap.BorderSide.ALL, 1.2, ap.Color.dark_blue)

        table_t_head_element = table_element.create_t_head()
        table_t_body_element = table_element.create_t_body()
        table_t_foot_element = table_element.create_t_foot()
        row_count = 50
        col_count = 4

        head_tr_element = table_t_head_element.create_tr()
        head_tr_element.alternative_text = "Head Row"
        head_tr_element.background_color = ap.Color.light_gray

        for column_index in range(col_count):
            th_element = head_tr_element.create_th()
            th_element.set_text(f"Head {column_index}")

            th_element.background_color = ap.Color.green_yellow
            th_element.border = ap.BorderInfo(ap.BorderSide.ALL, 4.0, ap.Color.gray)

            th_element.is_no_border = True
            th_element.margin = ap.MarginInfo(16.0, 2.0, 8.0, 2.0)

            th_element.alignment = ap.HorizontalAlignment.RIGHT

        for row_index in range(row_count):
            tr_element = table_t_body_element.create_tr()
            tr_element.alternative_text = f"Row {row_index}"

            for column_index in range(col_count):
                col_span = 1
                row_span = 1

                if column_index == 1 and row_index == 1:
                    col_span = 2
                    row_span = 2
                elif (row_index == 1 and column_index == 2) or (
                    row_index == 2 and column_index in (1, 2)
                ):
                    continue

                td_element = tr_element.create_td()
                td_element.set_text(f"Cell [{row_index}, {column_index}]")

                td_element.background_color = ap.Color.yellow
                td_element.border = ap.BorderInfo(ap.BorderSide.ALL, 4.0, ap.Color.gray)

                td_element.is_no_border = False
                td_element.margin = ap.MarginInfo(8.0, 2.0, 8.0, 2.0)

                td_element.alignment = ap.HorizontalAlignment.CENTER

                cell_text_state = ap.text.TextState()
                cell_text_state.foreground_color = ap.Color.dark_blue
                cell_text_state.font_size = 7.5
                cell_text_state.font_style = ap.text.FontStyles.BOLD
                cell_text_state.font = ap.text.FontRepository.find_font("Arial")
                td_element.default_cell_text_state = cell_text_state

                td_element.is_word_wrapped = True
                td_element.vertical_alignment = ap.VerticalAlignment.CENTER

                td_element.col_span = col_span
                td_element.row_span = row_span

        foot_tr_element = table_t_foot_element.create_tr()
        foot_tr_element.alternative_text = "Foot Row"
        foot_tr_element.background_color = ap.Color.light_sea_green

        for column_index in range(col_count):
            td_element = foot_tr_element.create_td()
            td_element.set_text(f"Foot {column_index}")

            td_element.alignment = ap.HorizontalAlignment.CENTER
            td_element.structure_text_state.font_size = 7
            td_element.structure_text_state.font_style = ap.text.FontStyles.BOLD

        table_attributes = table_element.attributes.get_attributes(
            ap.logicalstructure.AttributeOwnerStandard.TABLE
        )
        summary_attribute = ap.logicalstructure.StructureAttribute(
            ap.logicalstructure.AttributeKey.SUMMARY
        )
        summary_attribute.set_string_value("The summary text for table")
        table_attributes.set_attribute(summary_attribute)

        # Save Tagged PDF Document
        document.save(outfile)

样式表元素

创建一个新的标记 PDF 文档。
设置文档标题和语言。
创建表结构元素。
配置重复的行和列。
添加页眉、正文和页脚。
保存 Tagged PDF 文档。

以下代码片段展示了如何在 Tagged PDF 文档中为表格设置样式：

import aspose.pdf as ap
import sys
from os import path

def style_table(outfile):
    # Create PDF document
    with ap.Document() as document:
        tagged_content = document.tagged_content

        tagged_content.set_title("Example table style")
        tagged_content.set_language("en-US")

        # Get root structure element
        root_element = tagged_content.root_element

        # Create table structure element
        table_element = tagged_content.create_table_element()
        root_element.append_child(table_element, True)

        table_element.background_color = ap.Color.beige
        table_element.border = ap.BorderInfo(ap.BorderSide.ALL, 0.80, ap.Color.gray)
        table_element.alignment = ap.HorizontalAlignment.CENTER
        table_element.broken = ap.TableBroken.VERTICAL
        table_element.column_adjustment = ap.ColumnAdjustment.AUTO_FIT_TO_WINDOW
        table_element.column_widths = "80 80 80 80 80"
        table_element.default_cell_border = ap.BorderInfo(
            ap.BorderSide.ALL, 0.50, ap.Color.dark_blue
        )
        table_element.default_cell_padding = ap.MarginInfo(16.0, 2.0, 8.0, 2.0)
        table_element.default_cell_text_state.foreground_color = ap.Color.dark_cyan
        table_element.default_cell_text_state.font_size = 8.0
        table_element.default_column_width = "70"

        table_element.is_broken = False
        table_element.is_borders_included = True

        table_element.left = 0.0
        table_element.top = 40.0

        table_element.repeating_columns_count = 2
        table_element.repeating_rows_count = 3
        row_style = ap.text.TextState()
        row_style.background_color = ap.Color.light_coral
        table_element.repeating_rows_style = row_style

        table_t_head_element = table_element.create_t_head()
        table_t_body_element = table_element.create_t_body()
        table_t_foot_element = table_element.create_t_foot()
        row_count = 10
        col_count = 5

        head_tr_element = table_t_head_element.create_tr()
        head_tr_element.alternative_text = "Head Row"

        for col_index in range(col_count):
            th_element = head_tr_element.create_th()
            th_element.set_text(f"Head {col_index}")

        for row_index in range(row_count):
            tr_element = table_t_body_element.create_tr()
            tr_element.alternative_text = f"Row {row_index}"

            for col_index in range(col_count):
                td_element = tr_element.create_td()
                td_element.set_text(f"Cell [{row_index}, {col_index}]")

        foot_tr_element = table_t_foot_element.create_tr()
        foot_tr_element.alternative_text = "Foot Row"

        for col_index in range(col_count):
            td_element = foot_tr_element.create_td()
            td_element.set_text(f"Foot {col_index}")

        # Save Tagged PDF Document
        document.save(outfile)

样式表行

Aspose.PDF for Python via .NET 允许在 Tagged PDF 文档中为表格行设置样式。为了为表格行设置样式，您可以使用以下属性 TableTR 元素 class. 以下是您可以用于为表格行设置样式的属性列表：

以下代码片段展示了如何在 Tagged PDF 文档中为表格行设置样式：

import aspose.pdf as ap
import sys
from os import path

def style_table_row(outfile):
    # Create PDF document
    with ap.Document() as document:
        tagged_content = document.tagged_content

        tagged_content.set_title("Example table style")
        tagged_content.set_language("en-US")

        # Get root structure element
        root_element = tagged_content.root_element

        # Create table structure element
        table_element = tagged_content.create_table_element()
        root_element.append_child(table_element, True)
        table_t_head_element = table_element.create_t_head()
        table_t_body_element = table_element.create_t_body()
        table_t_foot_element = table_element.create_t_foot()
        row_count = 7
        col_count = 3
        head_tr_element = table_t_head_element.create_tr()
        head_tr_element.alternative_text = "Head Row"
        for col_index in range(col_count):
            th_element = head_tr_element.create_th()
            th_element.set_text(f"Head {col_index}")
        for row_index in range(row_count):
            tr_element = table_t_body_element.create_tr()
            tr_element.alternative_text = f"Row {row_index}"
            tr_element.background_color = ap.Color.light_goldenrod_yellow
            tr_element.border = ap.BorderInfo(
                ap.BorderSide.ALL, 0.75, ap.Color.dark_gray
            )
            tr_element.default_cell_border = ap.BorderInfo(
                ap.BorderSide.ALL, 0.50, ap.Color.blue
            )
            tr_element.min_row_height = 100.0
            tr_element.fixed_row_height = 120.0
            tr_element.is_in_new_page = row_index % 3 == 1
            tr_element.is_row_broken = True

            cell_text_state = ap.text.TextState()
            cell_text_state.foreground_color = ap.Color.red
            tr_element.default_cell_text_state = cell_text_state
            tr_element.default_cell_padding = ap.MarginInfo(16.0, 2.0, 8.0, 2.0)
            tr_element.vertical_alignment = ap.VerticalAlignment.BOTTOM
            for col_index in range(col_count):
                td_element = tr_element.create_td()
                td_element.set_text("Cell [{0}, {1}]".format(row_index, col_index))

        foot_tr_element = table_t_foot_element.create_tr()
        foot_tr_element.alternative_text = "Foot Row"

        for col_index in range(col_count):
            td_element = foot_tr_element.create_td()
            td_element.set_text("Foot {}".format(col_index))

        # Save Tagged PDF Document
        document.save(outfile)

表格单元格样式

Aspose.PDF for Python via .NET 允许在 Tagged PDF 文档中对表格单元格进行样式设置。为了对表格单元格进行样式设置，您可以使用属性表格单元格元素 class. 以下是您可以用来设置表格单元格样式的属性列表：

以下代码片段展示了如何在 Tagged PDF 文档中对表格单元格进行样式设置：

import aspose.pdf as ap
import sys
from os import path

def style_table_cell(outfile):
    # Create PDF document
    with ap.Document() as document:
        tagged_content = document.tagged_content

        tagged_content.set_title("Example table cell style")
        tagged_content.set_language("en-US")

        # Get root structure element
        root_element = tagged_content.root_element

        # Create table structure element
        table_element = tagged_content.create_table_element()
        root_element.append_child(table_element, True)

        table_t_head_element = table_element.create_t_head()
        table_t_body_element = table_element.create_t_body()
        table_t_foot_element = table_element.create_t_foot()
        row_count = 4
        col_count = 4

        head_tr_element = table_t_head_element.create_tr()
        head_tr_element.alternative_text = "Head Row"

        for col_index in range(col_count):
            th_element = head_tr_element.create_th()
            th_element.set_text("Head {}".format(col_index))

            th_element.background_color = ap.Color.green_yellow
            th_element.border = ap.BorderInfo(ap.BorderSide.ALL, 4.0, ap.Color.gray)

            th_element.is_no_border = True
            th_element.margin = ap.MarginInfo(16.0, 2.0, 8.0, 2.0)

            th_element.alignment = ap.HorizontalAlignment.RIGHT

        for row_index in range(row_count):
            tr_element = table_t_body_element.create_tr()
            tr_element.alternative_text = "Row {}".format(row_index)

            for col_index in range(col_count):
                col_span = 1
                row_span = 1

                if col_index == 1 and row_index == 1:
                    col_span = 2
                    row_span = 2
                elif (row_index == 1 and col_index == 2) or (
                    row_index == 2 and col_index in (1, 2)
                ):
                    continue

                td_element = tr_element.create_td()
                td_element.set_text("Cell [{}, {}]".format(row_index, col_index))

                td_element.background_color = ap.Color.yellow
                td_element.border = ap.BorderInfo(ap.BorderSide.ALL, 4.0, ap.Color.gray)

                td_element.is_no_border = False
                td_element.margin = ap.MarginInfo(8.0, 2.0, 8.0, 2.0)

                td_element.alignment = ap.HorizontalAlignment.CENTER

                cell_text_state = ap.text.TextState()
                cell_text_state.foreground_color = ap.Color.dark_blue
                cell_text_state.font_size = 7.5
                cell_text_state.font_style = ap.text.FontStyles.BOLD
                cell_text_state.font = ap.text.FontRepository.find_font("Arial")
                td_element.default_cell_text_state = cell_text_state

                td_element.is_word_wrapped = True
                td_element.vertical_alignment = ap.VerticalAlignment.CENTER

                td_element.col_span = col_span
                td_element.row_span = row_span

        foot_tr_element = table_t_foot_element.create_tr()
        foot_tr_element.alternative_text = "Foot Row"

        for col_index in range(col_count):
            td_element = foot_tr_element.create_td()
            td_element.set_text("Foot {}".format(col_index))

        # Save Tagged PDF Document
        document.save(outfile)

调整表格位置

使用 Aspose.PDF for Python via .NET 调整 Tagged PDF 中表格的位置，同时保持可访问性功能。

以下代码片段展示了如何在 Tagged PDF 文档中调整表格位置：

import aspose.pdf as ap
import sys
from os import path

def adjust_table_position(outfile):
    # Create PDF document
    with ap.Document() as document:
        # Create tagged content
        tagged_content = document.tagged_content
        tagged_content.set_title("Example table position")
        tagged_content.set_language("en-US")

        # Get root structure element
        root_element = tagged_content.root_element

        # Create table structure element
        table_element = tagged_content.create_table_element()
        root_element.append_child(table_element, True)

        # Create position settings
        position_settings = ap.tagged.PositionSettings()
        position_settings.horizontal_alignment = ap.HorizontalAlignment.NONE
        position_settings.margin = ap.MarginInfo(left=20, right=0, top=0, bottom=0)
        position_settings.vertical_alignment = ap.VerticalAlignment.NONE
        position_settings.is_first_paragraph_in_column = False
        position_settings.is_kept_with_next = False
        position_settings.is_in_new_page = False
        position_settings.is_in_line_paragraph = False

        # Adjust table position
        table_element.adjust_position(position_settings)

        table_t_head_element = table_element.create_t_head()
        table_t_body_element = table_element.create_t_body()
        table_t_foot_element = table_element.create_t_foot()
        row_count = 4
        col_count = 4

        head_tr_element = table_t_head_element.create_tr()
        head_tr_element.alternative_text = "Head Row"

        for col_index in range(col_count):
            th_element = head_tr_element.create_th()
            th_element.set_text(f"Head {col_index}")

            th_element.background_color = ap.Color.green_yellow
            th_element.border = ap.BorderInfo(ap.BorderSide.ALL, 4.0, ap.Color.gray)

            th_element.is_no_border = True
            th_element.margin = ap.MarginInfo(16.0, 2.0, 8.0, 2.0)

            th_element.alignment = ap.HorizontalAlignment.RIGHT

        for row_index in range(row_count):
            tr_element = table_t_body_element.create_tr()
            tr_element.alternative_text = f"Row {row_index}"

            for col_index in range(col_count):
                col_span = 1
                row_span = 1

                if col_index == 1 and row_index == 1:
                    col_span = 2
                    row_span = 2
                elif (row_index == 1 and col_index == 2) or (
                    row_index == 2 and col_index in (1, 2)
                ):
                    continue

                td_element = tr_element.create_td()
                td_element.set_text(f"Cell [{row_index}, {col_index}]")

                td_element.background_color = ap.Color.yellow
                td_element.border = ap.BorderInfo(ap.BorderSide.ALL, 4.0, ap.Color.gray)

                td_element.is_no_border = False
                td_element.margin = ap.MarginInfo(8.0, 2.0, 8.0, 2.0)

                td_element.alignment = ap.HorizontalAlignment.CENTER

                cell_text_state = ap.text.TextState()
                cell_text_state.foreground_color = ap.Color.dark_blue
                cell_text_state.font_size = 7.5
                cell_text_state.font_style = ap.text.FontStyles.BOLD
                cell_text_state.font = ap.text.FontRepository.find_font("Arial")
                td_element.default_cell_text_state = cell_text_state

                td_element.is_word_wrapped = True
                td_element.vertical_alignment = ap.VerticalAlignment.CENTER

                td_element.col_span = col_span
                td_element.row_span = row_span

        foot_tr_element = table_t_foot_element.create_tr()
        foot_tr_element.alternative_text = "Foot Row"

        for col_index in range(col_count):
            td_element = foot_tr_element.create_td()
            td_element.set_text(f"Foot {col_index}")

        # Save Tagged PDF Document
        document.save(outfile)

Documentation – Python 中的可访问性和标记 PDF

Python-Net: 使用 Python 创建带标签的 PDF

创建带标签的 PDF（简单场景）

创建带标签的 PDF（高级）

设置文本结构样式

说明结构元素

验证带标签的 PDF

调整文本结构的位置

使用自动标记将 PDF 转换为 PDF/UA-1

使用可访问的签名表单字段创建带标签的 PDF

使用目录 (TOC) 页面创建带标签的 PDF

使用分层目录 (TOC) 创建带有高级标签的 PDF

相关标签 PDF 主题

Python-Net: 在 Python 中从 PDF 中提取带标签的内容

获取带标签的 PDF 内容

获取根结构

访问子元素

相关标签 PDF 主题

Python-Net: 在 Python 中设置 Tagged PDF Structure Element 属性

设置文本结构元素

设置文本块结构元素

设置内联结构元素

设置自定义标签名称

将结构元素添加到元素中

设置链接结构元素

设置 Note 结构元素

如何设置语言和标题

相关 Tagged PDF 主题

Python-Net: 在 Python 中处理 Tagged PDF 表格

在 Tagged PDF 中创建表格

样式表元素

样式表行

表格单元格样式

调整表格位置

相关 Tagged PDF 主题