main

main.py

@@ -0,0 +1,64 @@
+import os
+import glob
+import re
+import pandas as pd, numpy as np
+import comtypes.client
+import docx
+from docx.document import Document
+from docx.oxml.table import CT_Tbl
+from docx.oxml.text.paragraph import CT_P
+from docx.table import _Cell, Table
+from docx.text.paragraph import Paragraph
+from flask import Flask, request, send_file
+from werkzeug.utils import secure_filename
+import zipfile
+import io
+
+app = Flask(__name__)
+
+UPLOAD_FOLDER = 'uploads/'
+if not os.path.exists(UPLOAD_FOLDER):
+    os.makedirs(UPLOAD_FOLDER)
+
+@app.route('/convert', methods=['POST'])
+def convert_pdfs():
+    if 'pdf_files' not in request.files:
+        return 'No file part', 400
+
+    pdf_files = request.files.getlist('pdf_files')
+    if not pdf_files:
+        return 'No selected file', 400
+
+    for pdf_file in pdf_files:
+        filename = secure_filename(pdf_file.filename)
+        pdf_file.save(os.path.join(UPLOAD_FOLDER, filename))
+
+    path_pdf = UPLOAD_FOLDER
+    path_docx = UPLOAD_FOLDER
+
+    word = comtypes.client.CreateObject('Word.Application')
+    word.visible = 0
+
+    for i, doc in enumerate(glob.iglob(path_pdf + '*.pdf')):
+        filename = doc.split('\\')[-1]
+        in_file = os.path.abspath(doc)
+        wdoc = word.Documents.Open(in_file)
+        out_file = os.path.abspath(path_docx + filename[:-4] + '.docx')
+        wdoc.SaveAs2(out_file, FileFormat=16)
+        wdoc.Close()
+
+    word.Quit()
+
+    memory_file = io.BytesIO()
+    with zipfile.ZipFile(memory_file, 'w', zipfile.ZIP_DEFLATED) as zf:
+        for root, _, filenames in os.walk(UPLOAD_FOLDER):
+            for filename in filenames:
+                if filename.endswith('.docx'):
+                    filepath = os.path.join(root, filename)
+                    zf.write(filepath, filename)
+
+    memory_file.seek(0)
+    return send_file(memory_file, attachment_filename='converted_docx.zip', as_attachment=True)
+
+if __name__ == '__main__':
+    app.run(host='0.0.0.0', port=5000)