pip install Spire.Doc

from spire.doc import *
from spire.doc.common import *

# Create a new document object
doc = Document()

# Add a section to the document
section = doc.AddSection()

# Append a Table of Contents (TOC) paragraph
TOC_paragraph = section.AddParagraph()
TOC_paragraph.AppendTOC(1, 3)

# Create and set character format objects for font
character_format1 = CharacterFormat(doc)
character_format1.FontName = "Microsoft YaHei"

character_format2 = CharacterFormat(doc)
character_format2.FontName = "Microsoft YaHei"
character_format2.FontSize = 12

# Add a paragraph with Heading 1 style
paragraph = section.Body.AddParagraph()
paragraph.ApplyStyle(BuiltinStyle.Heading1)

# Add text and apply character formatting
text_range1 = paragraph.AppendText("Overview")
text_range1.ApplyCharacterFormat(character_format1)

# Insert normal content
paragraph = section.Body.AddParagraph()
text_range2 = paragraph.AppendText("Spire.Doc for Python is a professional Python Word development component that enables developers to easily integrate Word document creation, reading, editing, and conversion functionalities into their own Python applications. As a completely standalone component, Spire.Doc for Python does not require the installation of Microsoft Word on the runtime environment.")

# Add a paragraph with Heading 1 style
paragraph = section.Body.AddParagraph()
paragraph.ApplyStyle(BuiltinStyle.Heading1)
text_range1 = paragraph.AppendText("Main Functions")
text_range1.ApplyCharacterFormat(character_format1)

# Add a paragraph with Heading 2 style
paragraph = section.Body.AddParagraph()
paragraph.ApplyStyle(BuiltinStyle.Heading2)
textRange1 = paragraph.AppendText("Only Spire.Doc, No Microsoft Office Automation")
textRange1.ApplyCharacterFormat(character_format1)

# Add regular content
paragraph = section.Body.AddParagraph()
textRange2 = paragraph.AppendText("Spire.Doc for Python is a totally independent Python Word class library which doesn't require Microsoft Office installed on system. Microsoft Office Automation is proved to be unstable, slow and not scalable to produce MS Word documents. Spire.Doc for Python is many times faster than Microsoft Word Automation and with much better stability and scalability.")
textRange2.ApplyCharacterFormat(character_format2)

# Add a paragraph with Heading 3 style
paragraph = section.Body.AddParagraph()
paragraph.ApplyStyle(BuiltinStyle.Heading3)
textRange1 = paragraph.AppendText("Word Versions")
textRange1.ApplyCharacterFormat(character_format1)
paragraph = section.Body.AddParagraph()
textRange2 = paragraph.AppendText("Word97-03  Word2007  Word2010  Word2013  Word2016  Word2019")
textRange2.ApplyCharacterFormat(character_format2)

# Add a paragraph with Heading 2 style
paragraph = section.Body.AddParagraph()
paragraph.ApplyStyle(BuiltinStyle.Heading2)
textRange1 = paragraph.AppendText("Convert File Documents with High Quality")
textRange1.ApplyCharacterFormat(character_format1)

# Add regular content
paragraph = section.Body.AddParagraph()
textRange2 = paragraph.AppendText("By using Spire.Doc for Python, users can save Word Doc/Docx to stream, save as web response and convert Word Doc/Docx to XML, Markdown, RTF, EMF, TXT, XPS, EPUB, HTML, SVG, ODT and vice versa. Spire.Doc for Python also supports to convert Word Doc/Docx to PDF and HTML to image.")
textRange2.ApplyCharacterFormat(character_format2)

# Add a paragraph with Heading 2 style
paragraph = section.Body.AddParagraph()
paragraph.ApplyStyle(BuiltinStyle.Heading2)
extRange1 = paragraph.AppendText("Other Technical Features")
textRange1.ApplyCharacterFormat(character_format1)

# Add regular content
paragraph = section.Body.AddParagraph()
textRange2 = paragraph.AppendText("By using Spire.Doc for Python, developers can build any type of a 64-bit Python application to create and handle Word documents.")
textRange2.ApplyCharacterFormat(character_format2)

# Update the table of contents
doc.UpdateTableOfContents()

# Save the document
doc.SaveToFile("CreateTOCUsingHeadingStyles.docx", FileFormat.Docx2016)

# Release resources
doc.Dispose()

from spire.doc import *
from spire.doc.common import *

# Create a document object
doc = Document()

# Add a section to the document
section = doc.AddSection()

# Define Outline Level 1
titleStyle1 = ParagraphStyle(doc)
titleStyle1.Name = "T1S"
titleStyle1.ParagraphFormat.OutlineLevel = OutlineLevel.Level1
titleStyle1.CharacterFormat.Bold = True
titleStyle1.CharacterFormat.FontName = "Microsoft YaHei"
titleStyle1.CharacterFormat.FontSize = 18
titleStyle1.ParagraphFormat.HorizontalAlignment = HorizontalAlignment.Left
doc.Styles.Add(titleStyle1)

# Define Outline Level 2
titleStyle2 = ParagraphStyle(doc)
titleStyle2.Name = "T2S"
titleStyle2.ParagraphFormat.OutlineLevel = OutlineLevel.Level2
titleStyle2.CharacterFormat.Bold = True
titleStyle2.CharacterFormat.FontName = "Microsoft YaHei"
titleStyle2.CharacterFormat.FontSize = 16
titleStyle2.ParagraphFormat.HorizontalAlignment = HorizontalAlignment.Left
doc.Styles.Add(titleStyle2)

# Define Outline Level 3
titleStyle3 = ParagraphStyle(doc)
titleStyle3.Name = "T3S"
titleStyle3.ParagraphFormat.OutlineLevel = OutlineLevel.Level3
titleStyle3.CharacterFormat.Bold = True
titleStyle3.CharacterFormat.FontName = "Microsoft YaHei"
titleStyle3.CharacterFormat.FontSize = 14
titleStyle3.ParagraphFormat.HorizontalAlignment = HorizontalAlignment.Left
doc.Styles.Add(titleStyle3)

# Add a paragraph
TOCparagraph = section.AddParagraph()
toc = TOCparagraph.AppendTOC(1, 3)
toc.UseHeadingStyles = False
toc.UseHyperlinks = True
toc.UseTableEntryFields = False
toc.RightAlignPageNumbers = True
toc.SetTOCLevelStyle(1, titleStyle1.Name)
toc.SetTOCLevelStyle(2, titleStyle2.Name)
toc.SetTOCLevelStyle(3, titleStyle3.Name)

# Define character format
characterFormat = CharacterFormat(doc)
characterFormat.FontName = "Microsoft YaHei"
characterFormat.FontSize = 12

# Add a paragraph and apply outline level style 1
paragraph = section.Body.AddParagraph()
paragraph.ApplyStyle(titleStyle1.Name)
paragraph.AppendText("Overview")

# Add a paragraph and set the text content
paragraph = section.Body.AddParagraph()
textRange = paragraph.AppendText("Spire.Doc for Python is a professional Word Python API specifically designed for developers to create, read, write, convert, and compare Word documents with fast and high-quality performance.")
textRange.ApplyCharacterFormat(characterFormat)

# Add a paragraph and apply outline level style 1
paragraph = section.Body.AddParagraph()
paragraph.ApplyStyle(titleStyle1.Name)
paragraph.AppendText("Main Functions")

# Add a paragraph and apply outline level style 2
paragraph = section.Body.AddParagraph()
paragraph.ApplyStyle(titleStyle2.Name)
paragraph.AppendText("Only Spire.Doc, No Microsoft Office Automation")

# Add a paragraph and set the text content
paragraph = section.Body.AddParagraph()
textRange = paragraph.AppendText("Spire.Doc for Python is a totally independent Python Word class library which doesn't require Microsoft Office installed on system. Microsoft Office Automation is proved to be unstable, slow and not scalable to produce MS Word documents. Spire.Doc for Python is many times faster than Microsoft Word Automation and with much better stability and scalability.")
textRange.ApplyCharacterFormat(characterFormat)

# Add a paragraph and apply outline level style 3
paragraph = section.Body.AddParagraph()
paragraph.ApplyStyle(titleStyle3.Name)
paragraph.AppendText("Word Versions")

# Add a paragraph and set the text content
paragraph = section.Body.AddParagraph()
textRange = paragraph.AppendText("Word97-03  Word2007  Word2010  Word2013  Word2016  Word2019")
textRange.ApplyCharacterFormat(characterFormat)

# Add a paragraph and apply outline level style 2
paragraph = section.Body.AddParagraph()
paragraph.ApplyStyle(titleStyle2.Name)
paragraph.AppendText("Convert File Documents with High Quality")

# Add a paragraph and set the text content
paragraph = section.Body.AddParagraph()
textRange = paragraph.AppendText("By using Spire.Doc for Python, users can save Word Doc/Docx to stream, save as web response and convert Word Doc/Docx to XML, RTF, EMF, TXT, XPS, EPUB, HTML, SVG, ODT and vice versa. Spire.Doc for Python also supports to convert Word Doc/Docx to PDF and HTML to image.")
textRange.ApplyCharacterFormat(characterFormat)

# Add a paragraph and apply outline level style 2
paragraph = section.Body.AddParagraph()
paragraph.ApplyStyle(titleStyle2.Name)
paragraph.AppendText("Other Technical Features")

# Add a paragraph and set the text content
paragraph = section.Body.AddParagraph()
textRange = paragraph.AppendText("By using Spire.Doc for Python, developers can build any type of a 64-bit Python application to create and handle Word documents.")
textRange.ApplyCharacterFormat(characterFormat)

# Update the table of contents
doc.UpdateTableOfContents()

# Save the document
doc.SaveToFile("CreateTOCUsingOutlineStyles.docx", FileFormat.Docx2016)

# Release resources
doc.Dispose()

from spire.doc import *
from spire.doc.common import *

# Create a new document object
doc = Document()

# Add a section to the document
section = doc.AddSection()

# Create a table of content object for images
tocForImage = TableOfContent(doc, " \\h \\z \\c \"Picture\"")

# Add a paragraph to the section
tocParagraph = section.Body.AddParagraph()

# Add the TOC object to the paragraph
tocParagraph.Items.Add(tocForImage)

# Add a field separator
tocParagraph.AppendFieldMark(FieldMarkType.FieldSeparator)

# Add text content
tocParagraph.AppendText("TOC")

# Add a field end mark
tocParagraph.AppendFieldMark(FieldMarkType.FieldEnd)

# Add a blank paragraph to the section
section.Body.AddParagraph()

# Add a paragraph to the section
paragraph = section.Body.AddParagraph()

# Add an image
docPicture = paragraph.AppendPicture("images/DOC-Python.png")
docPicture.Width = 100
docPicture.Height = 100

# Add a caption paragraph for the image
obj = docPicture.AddCaption("Picture",CaptionNumberingFormat.Number,CaptionPosition.BelowItem)

paragraph = (Paragraph)(obj)
paragraph.AppendText("  Spire.Doc for Python product")
paragraph.Format.AfterSpacing = 20

# Continue adding paragraphs to the section
paragraph = section.Body.AddParagraph()
docPicture = paragraph.AppendPicture("images/PDF-Python.png")
docPicture.Width = 100
docPicture.Height = 100
obj = docPicture.AddCaption("Picture",CaptionNumberingFormat.Number,CaptionPosition.BelowItem)
paragraph = (Paragraph)(obj)
paragraph.AppendText("  Spire.PDF for Python product")
paragraph.Format.AfterSpacing = 20

paragraph = section.Body.AddParagraph()
docPicture = paragraph.AppendPicture("images/XLS-Python.png")
docPicture.Width = 100
docPicture.Height = 100
obj = docPicture.AddCaption("Picture",CaptionNumberingFormat.Number,CaptionPosition.BelowItem)
paragraph = (Paragraph)(obj)
paragraph.AppendText("  Spire.XLS for Python product")
paragraph.Format.AfterSpacing = 20

paragraph = section.Body.AddParagraph()
docPicture = paragraph.AppendPicture("images/PPT-Python.png")
docPicture.Width = 100
docPicture.Height = 100
obj = docPicture.AddCaption("Picture",CaptionNumberingFormat.Number,CaptionPosition.BelowItem)
paragraph = (Paragraph)(obj)
paragraph.AppendText("  Spire.Presentation for Python product")
paragraph.Format.AfterSpacing = 20

# Update the table of contents
doc.UpdateTableOfContents(tocForImage)

# Save the document to a file
doc.SaveToFile("CreateTOCWithImageCaptions.docx", FileFormat.Docx2016)

# Dispose of the document object
doc.Dispose()

from spire.doc import *
from spire.doc.common import *

# Create a new document
doc = Document()

# Add a section to the document
section = doc.AddSection()

# Create a TableOfContent object
tocForTable = TableOfContent(doc,  " \\h \\z \\c \"Table\"")

# Add a paragraph in the section to place the TableOfContent object
tocParagraph = section.Body.AddParagraph()
tocParagraph.Items.Add(tocForTable)
tocParagraph.AppendFieldMark(FieldMarkType.FieldSeparator)
tocParagraph.AppendText("TOC")
tocParagraph.AppendFieldMark(FieldMarkType.FieldEnd)

# Add two empty paragraphs in the section
section.Body.AddParagraph()
section.Body.AddParagraph()

# Add a table in the section
table = section.Body.AddTable(True)
table.ResetCells(1, 3)

# Add a caption paragraph for the table
obj = table.AddCaption("Table", CaptionNumberingFormat.Number, CaptionPosition.BelowItem)
paragraph = (Paragraph)(obj)
paragraph.AppendText(" One row three columns")
paragraph.Format.AfterSpacing = 20

# Add a new table in the section
table = section.Body.AddTable(True)
table.ResetCells(3, 3)

# Add a caption paragraph for the second table
obj = table.AddCaption("Table", CaptionNumberingFormat.Number, CaptionPosition.BelowItem)
paragraph = (Paragraph)(obj)
paragraph.AppendText(" Three rows three columns")
paragraph.Format.AfterSpacing = 20

# Add another new table in the section
table = section.Body.AddTable(True)
table.ResetCells(5, 3)

# Add a caption paragraph for the third table
obj = table.AddCaption("Table", CaptionNumberingFormat.Number, CaptionPosition.BelowItem)
paragraph = (Paragraph)(obj)
paragraph.AppendText(" Five rows three columns")
paragraph.Format.AfterSpacing = 20

# Update the table of contents
doc.UpdateTableOfContents(tocForTable)

# Save the document to a specified file
doc.SaveToFile("CreateTOCUsingTableCaptions.docx", FileFormat.Docx2016)

# Dispose resources
doc.Dispose()

pip install Spire.Doc

from spire.doc import *
from spire.doc.common import *

# Create an instance of Document
doc = Document()

# Load a Word document
doc.LoadFromFile("Sample.docx")

# Loop through the sections
for s in range(doc.Sections.Count):
    # Get a section
    section = doc.Sections.get_Item(s)
    # Get the tables in the section
    tables = section.Tables
    # Loop through the tables
    for i in range(0, tables.Count):
        # Get a table
        table = tables.get_Item(i)
        # Initialize a string to store the table data
        tableData = ''
        # Loop through the rows of the table
        for j in range(0, table.Rows.Count):
            # Loop through the cells of the row
            for k in range(0, table.Rows.get_Item(j).Cells.Count):
                # Get a cell
                cell = table.Rows.get_Item(j).Cells.get_Item(k)
                # Get the text in the cell
                cellText = ''
                for para in range(cell.Paragraphs.Count):
                    paragraphText = cell.Paragraphs.get_Item(para).Text
                    cellText += (paragraphText + ' ')
                # Add the text to the string
                tableData += cellText
                if k < table.Rows.get_Item(j).Cells.Count - 1:
                    tableData += '\t'
            # Add a new line
            tableData += '\n'
    
        # Save the table data to a text file
        with open(f'output/Tables/WordTable_{s+1}_{i+1}.txt', 'w', encoding='utf-8') as f:
            f.write(tableData)
doc.Close()

pip install Spire.XLS

from spire.doc import *
from spire.doc.common import *
from spire.xls import *
from spire.xls.common import *

# Create an instance of Document
doc = Document()

# Load a Word document
doc.LoadFromFile('Sample.docx')

# Create an instance of Workbook
wb = Workbook()
wb.Worksheets.Clear()

# Loop through sections in the document
for i in range(doc.Sections.Count):
    # Get a section
    section = doc.Sections.get_Item(i)
    # Loop through tables in the section
    for j in range(section.Tables.Count):
        # Get a table
        table = section.Tables.get_Item(j)
        # Create a worksheet
        ws = wb.Worksheets.Add(f'Table_{i+1}_{j+1}')
        # Write the table to the worksheet
        for row in range(table.Rows.Count):
            # Get a row
            tableRow = table.Rows.get_Item(row)
            # Loop through cells in the row
            for cell in range(tableRow.Cells.Count):
                # Get a cell
                tableCell = tableRow.Cells.get_Item(cell)
                # Get the text in the cell
                cellText = ''
                for paragraph in range(tableCell.Paragraphs.Count):
                    paragraph = tableCell.Paragraphs.get_Item(paragraph)
                    cellText = cellText + (paragraph.Text + ' ')
                # Write the cell text to the worksheet
                ws.SetCellValue(row + 1, cell + 1, cellText)

# Save the workbook
wb.SaveToFile('output/Tables/WordTableToExcel.xlsx', FileFormat.Version2016)
doc.Close()
wb.Dispose()