图片批量识别文字

import pytesseract
from PIL import Image
import os

def batch_ocr(image_folder, output_folder):
    if not os.path.exists(output_folder):
        os.makedirs(output_folder)
    
    for filename in os.listdir(image_folder):
        if filename.endswith(('.png', '.jpg', '.jpeg')):
            img_path = os.path.join(image_folder, filename)
            img = Image.open(img_path)
            text = pytesseract.image_to_string(img)
            
            output_file = os.path.join(output_folder, f"{os.path.splitext(filename)[0]}.txt")
            with open(output_file, 'w', encoding='utf-8') as f:
                f.write(text)

# 使用示例
image_folder = 'path_to_image_folder'
output_folder = 'path_to_output_folder'
batch_ocr(image_folder, output_folder)