Finereader Python: Abbyy

def get_task_status(self, task_id): """Check task status.""" response = self.session.get(f"self.base_url/api/v1/tasks/task_id") return response.json()

cmd = [ fine_cmd, input_path, f"/out:output_path", f"/fmt:output_format", "/lang:English", # Use multiple: "/lang:English,French,German" "/recognize", "/auto", # Automatic document analysis "/close" ]

def zonal_ocr(self, input_path, zones, language="English"): """ OCR only specific zones (regions) on the page. Args: zones: list of (x1, y1, x2, y2) tuples in pixels """ doc = self.app.CreateDocument() page = doc.AddImageFile(input_path, 0) # Clear auto-detected regions page.Regions.Clear() # Add custom zones for (x1, y1, x2, y2) in zones: region = page.Regions.Add(x1, y1, x2, y2) region.Type = 1 # 1 = Text region # Recognize only these zones doc.Recognize(language) results = [] for region in page.Regions: results.append(region.Text) doc.Close() return results abbyy finereader python

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

def _clean_invoice_number(self, raw): match = re.search(r'INV[-_]?\d5,10', raw) return match.group(0) if match else raw def get_task_status(self, task_id): """Check task status

def process_invoice(self, image_path): """Extract structured data from invoice image.""" # Extract text from zones extracted = {} for field, zone in self.zones.items(): text = self.fr.zonal_ocr(image_path, [zone])[0] extracted[field] = text.strip() # Parse line items from full text full_text = self.fr.get_recognized_text(image_path) line_items = self._extract_line_items(full_text) # Parse and clean invoice = 'number': self._clean_invoice_number(extracted['invoice_number']), 'date': self._parse_date(extracted['invoice_date']), 'due_date': self._parse_date(extracted['due_date']), 'total': self._parse_amount(extracted['total_amount']), 'vendor': extracted['vendor_name'], 'vendor_address': extracted['vendor_address'], 'line_items': line_items, 'processed_at': datetime.now().isoformat() return invoice

result = fine_read_cli(input_path, "temp", "txt") # Your OCR call with open(cache_file, 'wb') as f: pickle.dump(result, f) # Use multiple: "/lang:English

# Configure PDF export settings export_params = "PDFExportMode": 1, # 1 = Text and pictures (searchable) "PDFAComplianceMode": 1, # PDF/A-1b "PreserveOriginalPageSize": True

Args: input_path: Path to image or PDF output_path: Output file path (without extension) output_format: pdf, docx, xlsx, txt, html """ fine_cmd = r"C:\Program Files (x86)\ABBYY FineReader\FineReaderCmd.exe"