convert.py

from pdfminer.high_level import extract_text
import os
import glob
import sys

pdf_folder = "documents"
text_folder = "text_files"

if not os.path.exists(text_folder):
    os.makedirs(text_folder)

success_count = 0
fail_count = 0
failed_files = []

for pdf_path in glob.glob(f"{pdf_folder}/*.pdf"):
    try:
        text = extract_text(pdf_path)
        filename = os.path.basename(pdf_path).replace(".pdf", ".txt")
        output_path = f"{text_folder}/{filename}"
        with open(output_path, "w", encoding="utf-8") as f:
            f.write(text)
        print(f"[SUCCESS] Converted: {filename}")
        success_count += 1
    except Exception as e:
        print(f"[FAIL] Could not convert {pdf_path}: {e}", file=sys.stderr)
        fail_count += 1
        failed_files.append(pdf_path)

print("\nConversion Summary:")
print(f"  Successful conversions: {success_count}")
print(f"  Failed conversions: {fail_count}")
if failed_files:
    print("  Failed files:")
    for f in failed_files:
        print(f"    - {f}")