opencode/process_any_pdf.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Универсальное распознавание PDF в указанную папку.
Использование:
    python process_any_pdf.py <pdf_file> <output_folder_name>
"""

import sys
import json
import fitz
from pathlib import Path
from rapidocr_onnxruntime import RapidOCR

# ------------------------------------------------------------------
# Параметры
# ------------------------------------------------------------------
DPI = 300
BATCH_SIZE = 5

engine = RapidOCR()

# ------------------------------------------------------------------
def process_pdf(pdf_path: Path, out_dir: Path):
    out_dir.mkdir(parents=True, exist_ok=True)
    doc = fitz.open(pdf_path)
    total = len(doc)
    print(f"=== PDF: {pdf_path.name} | Страниц: {total} -> {out_dir} ===\n")
    
    all_pages = []
    for i in range(total):
        print(f"[{i+1}/{total}] Рендер + OCR ...", end=" ")
        page = doc.load_page(i)
        raw_text = page.get_text("text").strip()
        
        mat = fitz.Matrix(DPI / 72, DPI / 72)
        pix = page.get_pixmap(matrix=mat)
        img_path = out_dir / f"page_{i+1:03d}.png"
        pix.save(img_path)
        
        res = engine(img_path)
        ocr_lines = []
        if res and res[0] is not None:
            for item in res[0]:
                box, txt, score = item
                ocr_lines.append({
                    "text": txt,
                    "confidence": float(score),
                    "bbox": box
                })
        
        all_pages.append({
            "page_number": i + 1,
            "image": str(img_path.name),
            "pdf_text_layer": raw_text,
            "ocr_lines": ocr_lines,
            "ocr_line_count": len(ocr_lines)
        })
        print(f"OCR строк: {len(ocr_lines)}")
        
        if (i + 1) % BATCH_SIZE == 0 or i == total - 1:
            with open(out_dir / "full_ocr_results.json", "w", encoding="utf-8") as f:
                json.dump({"pages": all_pages}, f, ensure_ascii=False, indent=2)
            print(f"  -> промежуточное сохранение ({i+1} страниц)")
    
    doc.close()
    print(f"\n=== Готово. Результат в {out_dir} ===")

# ------------------------------------------------------------------
def main():
    if len(sys.argv) < 2:
        pdf_file = "123.pdf"
        out_name = "output_123"
    else:
        pdf_file = sys.argv[1]
        out_name = sys.argv[2] if len(sys.argv) > 2 else f"output_{Path(pdf_file).stem}"
    
    pdf_path = Path(pdf_file) if Path(pdf_file).exists() else Path(".") / pdf_file
    out_dir = Path(out_name)
    
    if not pdf_path.exists():
        print(f"[ERR] Файл не найден: {pdf_path}")
        sys.exit(1)
    
    process_pdf(pdf_path, out_dir)

if __name__ == "__main__":
    main()