Documentation – Aksesibilitas dan Tagged PDFs di Python

Python-Net: Buat Tagged PDF dengan Python

Fri, 12 Jun 2026 00:00:00 +0000

Membuat Tagged PDF berarti menambahkan (atau membuat) elemen tertentu ke dokumen yang akan memungkinkan dokumen divalidasi sesuai dengan persyaratan PDF/UA. Elemen-elemen ini sering disebut Structure Elements.

Membuat Tagged PDF (Skenario Sederhana)

Untuk membuat elemen struktur dalam Tagged PDF Document, Aspose.PDF menawarkan metode untuk membuat elemen struktur menggunakan ITaggedContent antarmuka. Contoh ini membuat dokumen Tagged PDF — sebuah PDF dengan struktur semantik, menjadikannya lebih mudah diakses dan mematuhi standar seperti PDF/UA. Potongan kode berikut menunjukkan cara membuat Tagged PDF yang berisi 2 elemen: header dan paragraf.

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)

Membuat Tagged PDF (Lanjutan)

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)

Kami akan mendapatkan dokumen berikut setelah pembuatan:

Penggayaan Struktur Teks

Tagged PDFs adalah dokumen terstruktur yang menyediakan fitur aksesibilitas dan makna semantik pada kontennya.

Contoh ini membuat dokumen PDF dengan fitur aksesibilitas dengan menggunakan struktur konten bertag. Ini menunjukkan cara membuat elemen paragraf dengan gaya khusus dan metadata dokumen yang tepat.

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)

Mengilustrasikan Structure Elements

Tagged PDFs sangat penting untuk kepatuhan aksesibilitas dan menyediakan konten terstruktur yang dapat ditafsirkan dengan tepat oleh pembaca layar dan teknologi bantuan lainnya. Potongan kode berikut menunjukkan cara membuat dokumen PDF ber-tag dengan gambar tersemat:

Buat PDF bertanda dengan gambar.
Konfigurasikan dokumen.
Buat dan konfigurasikan gambar.
Atur posisi.
Simpan dokumen.

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)

Validasi Tagged PDF

Aspose.PDF for Python via .NET menyediakan kemampuan untuk memvalidasi Dokumen PDF/UA Tagged PDF. Metode ‘validate_tagged_pdf’ memvalidasi dokumen PDF terhadap standar PDF/UA-1, yang merupakan bagian dari spesifikasi ISO 14289 untuk dokumen PDF yang dapat diakses. Ini memastikan bahwa PDF dapat diakses oleh pengguna dengan disabilitas dan teknologi bantuan.

Struktur Dokumen. Penandaan semantik yang tepat dan struktur logis.
Teks Alternatif. Teks alt untuk gambar dan elemen non‑teks.
Urutan Membaca. Urutan logis untuk pembaca layar.
Warna dan Kontras. Rasio kontras yang cukup.
Formulir. Bidang formulir yang dapat diakses dan label.
Navigasi. Penanda buku yang tepat dan struktur navigasi.

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}")

Sesuaikan posisi Struktur Teks

Potongan kode berikut menunjukkan cara menyesuaikan posisi Struktur Teks dalam dokumen Tagged PDF:

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)

Konversi PDF ke PDF/UA-1 dengan Tagging Otomatis

Potongan kode ini menjelaskan cara mengonversi PDF standar menjadi file yang mematuhi PDF/UA-1 (Aksesibilitas Universal) menggunakan Aspose.PDF for Python via .NET.

PDF/UA memastikan bahwa dokumen dapat diakses oleh pengguna dengan disabilitas dan kompatibel dengan teknologi bantu seperti pembaca layar. Selama konversi, perpustakaan dapat secara otomatis menghasilkan pohon struktur logis dan menerapkan tag semantik menggunakan auto-tagging bawaan serta pengenalan heading.

Dengan mengonfigurasi PdfFormatConversionOptions dan mengaktifkan AutoTaggingSettings, Anda dapat secara efisien mengubah PDF yang ada menjadi dokumen yang dapat diakses tanpa harus mengedit struktur secara manual.

Muat dokumen sumber.
Buat Opsi Konversi PDF/UA.
Aktifkan Penandaan Otomatis.
Konfigurasikan Pengenalan Heading.
Lampirkan konfigurasi penandaan ke opsi konversi.
Jalankan proses konversi.
Simpan PDF yang dapat diakses.

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)

Buat Tagged PDF dengan FormField Tanda Tangan yang Dapat Diakses

Buat dokumen PDF baru.
Akses konten yang ditandai.
Buat bidang Form tanda tangan.
Tambahkan bidang ke AcroForm.
Buat elemen form dalam struktur tag.
Tautkan elemen Structure ke field Form.
Tambahkan elemen Form ke pohon struktur logis.
Simpan dokumen.

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)

Buat Tagged PDF dengan Halaman Daftar Isi (TOC)

Contoh ini menunjukkan cara membuat dokumen Tagged PDF dengan halaman Daftar Isi (TOC) yang terstruktur menggunakan Aspose.PDF for Python via .NET.

Buat dokumen PDF baru.
Buat halaman daftar isi khusus.
Buat dan daftarkan elemen TOC dalam pohon struktur logis.
Tambahkan halaman konten.
Buat elemen header.
Buat elemen /TOCI.
Tautkan header ke TOC.
Simpan dokumen.

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)

Buat PDF Tagged Lanjutan dengan Daftar Isi Hierarkis (TOC)

Dengan menggunakan Aspose.PDF for Python via .NET, Anda dapat membuat dokumen PDF yang canggih, sepenuhnya ber-tag, dengan Daftar Isi (TOC) yang terstruktur dan hierarkis.

Buat dokumen dan aktifkan konten Tagged.
Tambahkan dan konfigurasikan halaman TOC.
Buat elemen struktur /TOC.
Tautkan judul halaman TOC ke elemen header.
Tambahkan halaman konten utama dan header pertama.
Buat entri TOC untuk header.
Buat subseksi bersarang dengan struktur daftar.
Tambahkan bagian Tingkat Atas kedua.
Simpan dokumen.

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)

Topik Tagged PDF Terkait

Ekstrak Konten Bertanda dari Tagged PDF untuk memeriksa pohon struktur logis setelah pembuatan.
Mengatur Properti Elemen Struktur untuk menyempurnakan judul, bahasa, teks alt, dan teks ekspansi.
Bekerja dengan Tabel dalam Tagged PDF ketika dokumen yang dapat diakses Anda menyertakan tabel terstruktur.

Python-Net: Ekstrak Konten Ber-tag dari PDF di Python

Fri, 12 Jun 2026 00:00:00 +0000

Dalam artikel ini, Anda akan mempelajari cara mengekstrak konten ber-tag dari dokumen PDF menggunakan Python.

Gunakan contoh-contoh ini ketika Anda perlu memeriksa tagged PDF, membaca pohon struktur logis, atau memvalidasi bahwa elemen struktur dibuat dengan benar untuk alur kerja aksesibilitas.

Mendapatkan Konten Tagged PDF

Untuk mendapatkan konten Dokumen PDF dengan Tagged Text, Aspose.PDF menawarkan tagged_content properti dari Document kelas.

Buat dokumen PDF berlabel penuh yang canggih dengan Daftar Isi (TOC) yang terstruktur dan hierarkis:

Buat objek Document baru.
Akses properti tagged_content.
Setel judul dokumen menggunakan ‘set_title()’.
Setel bahasa dokumen menggunakan ‘set_language()’.
Simpan dokumen.

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)

Mendapatkan Struktur Akar

Tagged PDF berisi pohon struktur logis yang mendefinisikan struktur semantik dokumen. StructTreeRoot mewakili akar pohon logis ini, sementara RootElement menyediakan antarmuka untuk berinteraksi dengan elemen struktur tingkat atas dokumen.

Potongan kode berikut menunjukkan cara mendapatkan struktur root dari Tagged PDF Document:

Buat dokumen tagged PDF baru.
Akses tagged content dan atur metadata.
Akses StructTreeRoot dan RootElement.
Simpan PDF ber-tag.

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)

Mengakses Elemen Anak

Tagged PDF berisi pohon struktur logis yang mendefinisikan hierarki semantik dokumen (judul, paragraf, formulir, daftar, dll.). Mengakses dan memodifikasi elemen struktur ini memungkinkan Anda untuk:

Memeriksa metadata seperti judul, bahasa, actual_text, dan properti terkait aksesibilitas
Perbarui properti untuk meningkatkan aksesibilitas atau lokalisasi
Sesuaikan struktur dokumen logis secara programatik untuk kepatuhan PDF/UA

Potongan kode berikut menunjukkan cara mengakses elemen anak dari Dokumen Tagged PDF:

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)

Topik Tagged PDF Terkait

Buat Tagged PDF untuk membuat dokumen bertanda yang dapat diakses sebelum memeriksa strukturnya.
Mengatur Properti Elemen Struktur untuk memperbarui properti semantik setelah mengekstrak elemen struktur.
Bekerja dengan Tabel dalam Tagged PDF untuk alur kerja aksesibilitas tabel ber‑tag.

Python-Net: Atur Properti Elemen Struktur Tagged PDF di Python

Fri, 12 Jun 2026 00:00:00 +0000

Elemen struktur mendefinisikan hierarki semantik dari sebuah dokumen PDF, seperti bagian, judul, paragraf, atau tabel. Dengan mengatur properti seperti title, language, alternative_text, actual_text, dan expansion_text, Anda meningkatkan aksesibilitas dan makna semantik PDF untuk teknologi bantu seperti pembaca layar.

Potongan kode berikut menunjukkan cara mengatur properti elemen struktur dari Dokumen Tagged PDF:

Buat dokumen tagged PDF baru.
Atur metadata dokumen.
Buat elemen struktur.
Atur properti aksesibilitas.
Simpan PDF ber-tag.

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)

Mengatur Elemen Struktur Teks

Untuk mengatur elemen struktur teks dari Tagged PDF Document, Aspose.PDF menawarkan Elemen Paragraf kelas. Cuplikan kode berikut menunjukkan cara mengatur elemen struktur teks dari Tagged PDF Document:

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)

Mengatur Elemen Struktur Blok Teks

Contoh Python ini menggunakan Aspose.PDF untuk membuat Tagged PDF yang mencakup hierarki terstruktur dari header dan paragraf, meningkatkan fitur semantik dan aksesibilitas dokumen.

Buat dokumen tagged PDF baru.
Atur metadata dokumen.
Akses elemen struktur root.
Buat header multi-tingkat.
Tambahkan header ke struktur root.
Buat elemen paragraf.
Tambahkan paragraf ke struktur akar.
Simpan PDF ber-tag.

Potongan kode berikut menunjukkan cara mengatur elemen struktur blok teks dari Dokumen Tagged PDF:

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)

Pengaturan Elemen Struktur Inline

Buat elemen teks inline (/Span) dalam header dan paragraf pada PDF ber‑tag menggunakan Aspose.PDF for Python via .NET.

Potongan kode berikut menunjukkan cara mengatur elemen struktur inline dari Dokumen Tagged PDF:

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)

Mengatur Nama Tag Kustom

Tetapkan Nama Tag Kustom untuk Struktur dan Elemen Inline dalam Tagged PDF Menggunakan Aspose.PDF untuk Python.

Potongan kode berikut menunjukkan cara mengatur nama tag khusus:

Buat dokumen tagged PDF baru.
Atur metadata dokumen.
Buat elemen section.
Buat elemen paragraf dengan tag khusus.
Buat elemen span inline dengan tag khusus.
Simpan PDF ber-tag.

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)

Menambahkan Elemen Struktur ke dalam Elemen

Fitur ini didukung oleh versi 19.4 atau lebih tinggi.

Buat tautan dan elemen gambar dalam PDF bertag menggunakan Aspose.PDF for Python via .NET.

Potongan kode berikut menunjukkan cara mengatur elemen struktur dalam paragraf dengan teks Dokumen Tagged PDF:

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)

Pengaturan Elemen Struktur Tautan

Aspose.PDF for Python via .NET API juga memungkinkan Anda menambahkan elemen struktur tautan.

Cuplikan kode berikut menunjukkan cara menambahkan elemen struktur tautan ke Dokumen Tagged PDF:

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)

Pengaturan Elemen Struktur Catatan

API Aspose.PDF for Python via .NET juga memungkinkan Anda untuk menambahkan ElemenCatatan pada dokumen Tagged PDF. Potongan kode berikut menunjukkan cara menambahkan elemen catatan dalam Tagged PDF Document:

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)

Cara mengatur Bahasa dan Judul

Aspose.PDF for Python via .NET API juga memungkinkan Anda mengatur bahasa dan judul untuk sebuah dokumen sesuai spesifikasi PDF/UA. Bahasa dapat diatur untuk seluruh dokumen maupun untuk elemen struktural terpisahnya. Potongan kode berikut menunjukkan cara mengatur bahasa dan judul dalam Dokumen Tagged PDF:

Buat dokumen tagged PDF baru.
Atur judul dokumen dan bahasa.
Buat elemen header.
Tambahkan paragraf dengan bahasa tertentu.
Simpan PDF ber-tag.

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)

Topik Tagged PDF Terkait

Buat Tagged PDF untuk menghasilkan elemen struktur sebelum memperbarui propertinya.
Ekstrak Tagged Content dari Tagged PDFs untuk memeriksa node struktur yang ada dan metadata.
Bekerja dengan Tabel dalam Tagged PDF jika Anda perlu menerapkan properti aksesibel ke struktur tabel.

Python-Net: Bekerja dengan Tabel dalam Tagged PDF di Python

Fri, 12 Jun 2026 00:00:00 +0000

Buat Tabel dalam Tagged PDF

Dengan mengikuti langkah-langkah di atas, Anda dapat membuat tabel yang kaya secara semantik dan dapat diakses dalam dokumen PDF menggunakan Aspose.PDF for Python. File yang dihasilkan memenuhi standar kepatuhan PDF/UA-1, memastikan kompatibilitas dengan pembaca layar dan teknologi bantu. Ini ideal untuk kasus penggunaan yang melibatkan kepatuhan regulasi, audit aksesibilitas, dan penerbitan konten inklusif.

Potongan kode berikut menunjukkan, cara membuat tabel dalam dokumen Tagged PDF:

Buat dokumen tagged PDF baru.
Atur metadata dokumen.
Buat struktur tabel.
Buat baris header tabel.
Buat baris tubuh tabel dengan sel.
Buat baris footer tabel.
Set atribut ringkasan tabel.
Simpan Tagged 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)

Elemen Tabel Gaya

Buat dokumen tagged PDF baru.
Atur judul dokumen dan bahasa.
Buat elemen struktur tabel.
Konfigurasikan baris dan kolom yang berulang.
Tambahkan header, isi, dan footer.
Simpan dokumen PDF ber-tag.

Potongan kode berikut menunjukkan cara memberi gaya pada tabel dalam dokumen Tagged PDF:

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)

Gaya Baris Tabel

Aspose.PDF for Python via .NET memungkinkan penataan baris tabel dalam dokumen Tagged PDF. Untuk menata baris tabel, Anda dapat menggunakan properti dari TableTRElement class. Berikut adalah daftar properti yang dapat Anda gunakan untuk menata baris tabel:

Potongan kode berikut menunjukkan cara menata baris tabel dalam dokumen Tagged PDF:

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)

Gaya Sel Tabel

Aspose.PDF for Python via .NET memungkinkan penataan sel tabel dalam dokumen Tagged PDF. Untuk menata sel tabel, Anda dapat menggunakan properti dari Elemen Sel Tabel kelas. Berikut adalah daftar properti yang dapat Anda gunakan untuk menata sel tabel:

Potongan kode berikut menunjukkan cara menata sel tabel dalam dokumen Tagged PDF:

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)

Sesuaikan posisi tabel

Sesuaikan posisi tabel dalam tagged PDF sambil mempertahankan fitur aksesibilitas menggunakan Aspose.PDF for Python via .NET.

Potongan kode berikut menunjukkan cara menyesuaikan posisi tabel dalam dokumen Tagged PDF:

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)

Topik Tagged PDF Terkait

Buat Tagged PDF untuk membangun struktur dokumen aksesibel secara keseluruhan di sekitar konten tabel Anda.
Ekstrak Tagged Content dari Tagged PDFs untuk memeriksa elemen struktur terkait tabel setelah pembuatan.
Mengatur Properti Elemen Struktur untuk menyempurnakan metadata yang dapat diakses pada sel tabel dan elemen struktur lainnya.