Create app.py
Browse files
app.py
ADDED
|
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# app.py
|
| 2 |
+
import gradio as gr
|
| 3 |
+
from docx2pdf import convert
|
| 4 |
+
import os
|
| 5 |
+
import zipfile
|
| 6 |
+
import shutil
|
| 7 |
+
from pathlib import Path
|
| 8 |
+
|
| 9 |
+
# Set up temporary directories
|
| 10 |
+
TEMP_DIR = Path("./temp_files")
|
| 11 |
+
TEMP_INPUT_DIR = TEMP_DIR / "input"
|
| 12 |
+
TEMP_OUTPUT_DIR = TEMP_DIR / "output"
|
| 13 |
+
|
| 14 |
+
# Ensure directories exist
|
| 15 |
+
for d in [TEMP_INPUT_DIR, TEMP_OUTPUT_DIR]:
|
| 16 |
+
d.mkdir(parents=True, exist_ok=True)
|
| 17 |
+
|
| 18 |
+
def convert_docs_to_pdf(doc_files):
|
| 19 |
+
"""
|
| 20 |
+
Takes a list of uploaded docx files, converts them to PDF,
|
| 21 |
+
and zips the results for download.
|
| 22 |
+
"""
|
| 23 |
+
if not doc_files:
|
| 24 |
+
return None, "Please upload one or more .docx or .doc files."
|
| 25 |
+
|
| 26 |
+
# 1. Clean up and prepare directories for a new conversion run
|
| 27 |
+
try:
|
| 28 |
+
if TEMP_INPUT_DIR.exists(): shutil.rmtree(TEMP_INPUT_DIR)
|
| 29 |
+
if TEMP_OUTPUT_DIR.exists(): shutil.rmtree(TEMP_OUTPUT_DIR)
|
| 30 |
+
TEMP_INPUT_DIR.mkdir(parents=True)
|
| 31 |
+
TEMP_OUTPUT_DIR.mkdir(parents=True)
|
| 32 |
+
except Exception as e:
|
| 33 |
+
return None, f"Error preparing directories: {e}"
|
| 34 |
+
|
| 35 |
+
success_count = 0
|
| 36 |
+
|
| 37 |
+
# 2. Convert each file
|
| 38 |
+
for file_obj in doc_files:
|
| 39 |
+
original_filepath = file_obj.name
|
| 40 |
+
filename = Path(original_filepath).name
|
| 41 |
+
|
| 42 |
+
# Determine the target output path for the PDF
|
| 43 |
+
output_filename = filename.rsplit('.', 1)[0] + '.pdf'
|
| 44 |
+
output_filepath = TEMP_OUTPUT_DIR / output_filename
|
| 45 |
+
|
| 46 |
+
try:
|
| 47 |
+
# Copy file to a temp input dir, which can be useful if docx2pdf
|
| 48 |
+
# has issues with temporary Gradio paths on some systems.
|
| 49 |
+
input_file_copy = TEMP_INPUT_DIR / filename
|
| 50 |
+
shutil.copy(original_filepath, input_file_copy)
|
| 51 |
+
|
| 52 |
+
# Perform the conversion
|
| 53 |
+
# The 'output_file' parameter specifies the single output PDF path.
|
| 54 |
+
# When converting a single file, this works.
|
| 55 |
+
# Note: docx2pdf handles doc and docx automatically.
|
| 56 |
+
convert(input_file_copy, output_filepath)
|
| 57 |
+
success_count += 1
|
| 58 |
+
|
| 59 |
+
except Exception as e:
|
| 60 |
+
print(f"Error converting {filename}: {e}")
|
| 61 |
+
# Optionally, you could write a placeholder PDF to inform the user of the failure
|
| 62 |
+
|
| 63 |
+
if success_count == 0:
|
| 64 |
+
return None, "No files were converted successfully. Ensure they are valid .docx or .doc files."
|
| 65 |
+
|
| 66 |
+
# 3. Zip the results
|
| 67 |
+
zip_filename = TEMP_DIR / "converted_pdfs.zip"
|
| 68 |
+
|
| 69 |
+
# Check if the zip file already exists and remove it
|
| 70 |
+
if zip_filename.exists():
|
| 71 |
+
os.remove(zip_filename)
|
| 72 |
+
|
| 73 |
+
with zipfile.ZipFile(zip_filename, 'w') as zipf:
|
| 74 |
+
for file in TEMP_OUTPUT_DIR.iterdir():
|
| 75 |
+
# Add files from the output directory to the zip file
|
| 76 |
+
zipf.write(file, arcname=file.name)
|
| 77 |
+
|
| 78 |
+
# Return the path to the zip file for Gradio to offer as a download
|
| 79 |
+
return str(zip_filename), f"Successfully converted {success_count} files and zipped them."
|
| 80 |
+
|
| 81 |
+
# --- Gradio Interface Definition ---
|
| 82 |
+
# Use gr.Blocks for a more flexible layout
|
| 83 |
+
with gr.Blocks(title="Multi DOC/DOCX to PDF Converter") as demo:
|
| 84 |
+
gr.Markdown(
|
| 85 |
+
"""
|
| 86 |
+
# Multi DOC/DOCX to PDF Converter 📄➡️📜
|
| 87 |
+
Upload multiple Microsoft Word files (.doc or .docx) and get them all converted to PDF in a single downloadable ZIP file.
|
| 88 |
+
|
| 89 |
+
**Note:** This app relies on the `docx2pdf` library and LibreOffice on the backend for accurate formatting preservation.
|
| 90 |
+
"""
|
| 91 |
+
)
|
| 92 |
+
|
| 93 |
+
with gr.Row():
|
| 94 |
+
# Input component: File component set to accept multiple files
|
| 95 |
+
file_input = gr.File(
|
| 96 |
+
file_count="multiple",
|
| 97 |
+
label="Upload Word Files (.docx or .doc)",
|
| 98 |
+
file_types=[".doc", ".docx"]
|
| 99 |
+
)
|
| 100 |
+
|
| 101 |
+
# Output components
|
| 102 |
+
with gr.Column():
|
| 103 |
+
download_zip = gr.File(label="Download Converted PDFs (ZIP)", visible=False)
|
| 104 |
+
status_message = gr.Textbox(label="Status", value="Upload your files and click Convert.", interactive=False)
|
| 105 |
+
|
| 106 |
+
convert_button = gr.Button("Convert to PDF", variant="primary")
|
| 107 |
+
|
| 108 |
+
# Connect the button click to the conversion function
|
| 109 |
+
convert_button.click(
|
| 110 |
+
fn=convert_docs_to_pdf,
|
| 111 |
+
inputs=[file_input],
|
| 112 |
+
outputs=[download_zip, status_message],
|
| 113 |
+
# Show the download component only after successful conversion
|
| 114 |
+
postprocess=[lambda x: gr.update(visible=True)]
|
| 115 |
+
)
|
| 116 |
+
|
| 117 |
+
if __name__ == "__main__":
|
| 118 |
+
demo.launch()
|