在 Python 中设置 Tagged PDF Structure Element 属性
Contents
[
Hide
]
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)
相关 Tagged PDF 主题
- 创建 Tagged PDF 在更新属性之前生成结构元素。
- 从已标记的 PDF 中提取标记内容 检查现有的结构节点和元数据。
- 在标记 PDF 中处理表格 如果您需要对表结构应用可访问属性。