results = [] for image in Path(input_folder).glob("*.jpg"): print(f"Processing: image.name") # OCR text = fr.get_recognized_text(str(image)) # Save text txt_path = Path(output_folder) / f"image.stem.txt" txt_path.write_text(text, encoding='utf-8') # Save metadata results.append( "file": image.name, "text_length": len(text), "timestamp": datetime.now().isoformat() )

def _parse_amount(self, raw): match = re.search(r'\$\s*[\d,]+\.?\d0,2', raw) if match: amount = match.group(0).replace('$', '').replace(',', '') return float(amount) return 0.0

return result.returncode fine_read_cli("scan.jpg", "output/result", "docx") Batch Processing with CLI from concurrent.futures import ThreadPoolExecutor from tqdm import tqdm def batch_ocr_cli(input_folder, output_folder, max_workers=4): """Process all images in a folder.""" input_folder = Path(input_folder) output_folder = Path(output_folder) output_folder.mkdir(exist_ok=True)

def get_recognized_text(self, input_path): """Return recognized text as string without saving to file.""" doc = self.app.CreateDocument() doc.AddImageFile(input_path, 0) doc.AnalyzeLayout() doc.Recognize("English") # Extract text from all pages full_text = [] for i in range(doc.Pages.Count): full_text.append(doc.Pages[i].Text) doc.Close() return "\n\n".join(full_text)

file_hash = hashlib.md5(Path(input_path).read_bytes()).hexdigest() cache_file = cache_dir / f"file_hash.pkl"

return result import logging from functools import wraps logging.basicConfig(level=logging.INFO) logger = logging.getLogger( name )

image_files = list(input_folder.glob("*.png,jpg,jpeg,tiff,bmp"))

return output_pdf_path FineReader Server provides a REST API for distributed OCR. REST API Client import requests import base64 import json from pathlib import Path class FineReaderServerClient: def init (self, base_url, username, password): self.base_url = base_url.rstrip('/') self.session = requests.Session() self.session.auth = (username, password)