Bulk PDF Processor
This utility scans a directory for PDF files and processes them (e.g., extracts text) using a progress bar to track status.
Modules Used:
- argparse: To handle input/output directories.
- pathlib: To find files recursively.
- pypdf: To read the PDF content.
- tqdm: To show a progress bar.
The Code
Save this as pdf_tool.py.
import argparse
from pathlib import Path
from pypdf import PdfReader
from tqdm import tqdm
def process_pdfs(input_dir, keyword):
# 1. Find all PDF files
path = Path(input_dir)
files = list(path.rglob("*.pdf"))
print(f"Found {len(files)} PDF files in {input_dir}")
results = []
# 2. Iterate with Progress Bar
for pdf_file in tqdm(files, desc="Processing PDFs", unit="file"):
try:
reader = PdfReader(pdf_file)
# Check first page for keyword
if len(reader.pages) > 0:
text = reader.pages[0].extract_text()
if keyword.lower() in text.lower():
results.append(pdf_file.name)
except Exception as e:
# Don't crash the loop on a bad file, just print error
tqdm.write(f"Error reading {pdf_file.name}: {e}")
# 3. Report Results
print("\n" + "="*30)
print(f"Files containing '{keyword}':")
for res in results:
print(f"- {res}")
if __name__ == "__main__":
parser = argparse.ArgumentParser(description="Bulk PDF Scanner")
parser.add_argument("directory", help="Directory to scan")
parser.add_argument("--search", required=True, help="Keyword to search for in first page")
args = parser.parse_args()
process_pdfs(args.directory, args.search)Usage
python pdf_tool.py ./documents --search "Invoice"