Document Processing (DOCX)

Create and manipulate Microsoft Word documents programmatically using Python.

Setup

Installation

pip install python-docx

Basic Usage

from docx import Document

# Create document
doc = Document()

# Add content
doc.add_heading('Document Title', 0)
doc.add_paragraph('Hello, World!')

# Save
doc.save('document.docx')

Document Structure

Sections and Headings

# Main heading
doc.add_heading('Main Title', 0)

# Section headings
doc.add_heading('Section 1', level=1)
doc.add_heading('Subsection 1.1', level=2)

# Paragraphs
doc.add_paragraph('This is a paragraph.')

Lists

# Bullet list
doc.add_paragraph('Item 1', style='List Bullet')
doc.add_paragraph('Item 2', style='List Bullet')

# Numbered list
doc.add_paragraph('First item', style='List Number')
doc.add_paragraph('Second item', style='List Number')

Tables

# Create table
table = doc.add_table(rows=3, cols=3)

# Add data
for i, row in enumerate(table.rows):
    for j, cell in enumerate(row.cells):
        cell.text = f'Row {i}, Col {j}'

# Style table
table.style = 'Table Grid'

Advanced Features

Formatting

from docx.shared import Inches, Pt
from docx.enum.text import WD_ALIGN_PARAGRAPH

# Paragraph formatting
paragraph = doc.add_paragraph()
paragraph.alignment = WD_ALIGN_PARAGRAPH.CENTER

# Run formatting
run = paragraph.add_run('Bold text')
run.bold = True

run = paragraph.add_run('Italic text')
run.italic = True

run = paragraph.add_run('Large text')
run.font.size = Pt(14)

Images

doc.add_picture('image.png', width=Inches(4))

# Add with alignment
from docx.enum.text import WD_ALIGN_PARAGRAPH
paragraph = doc.add_paragraph()
run = paragraph.add_run()
run.add_picture('image.png', width=Inches(4))
paragraph.alignment = WD_ALIGN_PARAGRAPH.CENTER

Headers and Footers

section = doc.sections[0]
header = section.header
header_para = header.paragraphs[0]
header_para.text = 'Document Header'

footer = section.footer
footer_para = footer.paragraphs[0]
footer_para.text = 'Page number: '

Template System

Using Templates

from docx import Document

# Load template
doc = Document('template.docx')

# Replace placeholders
for paragraph in doc.paragraphs:
    if '{{NAME}}' in paragraph.text:
        paragraph.text = paragraph.text.replace('{{NAME}}', 'John Doe')
    if '{{DATE}}' in paragraph.text:
        paragraph.text = paragraph.text.replace('{{DATE}}', '2024-01-15')

# Save with new name
doc.save('output.docx')

Dynamic Content

def create_report(data):
    doc = Document()
    doc.add_heading(f'Report: {data["title"]}', 0)
    
    # Add summary
    doc.add_heading('Summary', level=1)
    doc.add_paragraph(data['summary'])
    
    # Add data table
    doc.add_heading('Data', level=1)
    table = doc.add_table(rows=len(data['items']) + 1, cols=2)
    table.style = 'Table Grid'
    
    # Header row
    table.rows[0].cells[0].text = 'Item'
    table.rows[0].cells[1].text = 'Value'
    
    # Data rows
    for i, item in enumerate(data['items']):
        table.rows[i + 1].cells[0].text = item['name']
        table.rows[i + 1].cells[1].text = str(item['value'])
    
    return doc

Best Practices

• Use templates for consistent formatting
• Handle errors gracefully
• Validate input data
• Close documents properly
• Use context managers when possible
• Test with different Word versions
• Consider PDF conversion for distribution