Merge Docx Documents

• Upload multiple DOCX files.

• Sort filenames A → Z.

• Merge them into one document.

• Automatically insert a page break before every Heading 1 paragraph (except the very first Heading 1 in the merged document).

• Download the final document.

# Install package
!pip install python-docx -q

from google.colab import files
from docx import Document
from copy import deepcopy

# =====================================================
# Upload files
# =====================================================

print("Select DOCX files...")
uploaded = files.upload()

# =====================================================
# Sort files alphabetically
# =====================================================

docx_files = sorted(
    [f for f in uploaded.keys() if f.lower().endswith(".docx")]
)

print("\nFiles to merge:")
for f in docx_files:
    print(f)

# =====================================================
# Create merged document
# =====================================================

merged_doc = Document()

# Remove default empty paragraph
if merged_doc.paragraphs:
    p = merged_doc.paragraphs[0]._element
    p.getparent().remove(p)

first_heading1_found = False

# =====================================================
# Merge documents
# =====================================================

for filename in docx_files:

    print(f"Merging {filename}")

    src = Document(filename)

    for para in src.paragraphs:

        style_name = para.style.name if para.style else ""

        # Start every Heading 1 on a new page
        if style_name == "Heading 1":

            if first_heading1_found:
                merged_doc.add_page_break()
            else:
                first_heading1_found = True

        new_para = merged_doc.add_paragraph(style=para.style)

        # Copy text and formatting
        for run in para.runs:
            new_run = new_para.add_run(run.text)

            new_run.bold = run.bold
            new_run.italic = run.italic
            new_run.underline = run.underline

            if run.font:
                new_run.font.name = run.font.name
                new_run.font.size = run.font.size

# =====================================================
# Save output
# =====================================================

output_file = "Merged_Document.docx"
merged_doc.save(output_file)

print(f"\nSaved: {output_file}")

files.download(output_file)