# encoding:UTF-*
import os
import cv2
from PIL import Image
import easyocr

def extract_frames(input_folder, output_folder):
    # 检查输出文件夹是否存在，如果不存在则创建
    if not os.path.exists(output_folder):
        os.makedirs(output_folder)

    # 遍历指定文件夹内的所有文件
    for filename in os.listdir(input_folder):
        if filename.endswith(".mp4"):
            video_path = os.path.join(input_folder, filename)

            # 使用OpenCV打开视频文件
            cap = cv2.VideoCapture(video_path)
            count = 0

            while cap.isOpened():
                # 读取视频的帧
                ret, frame = cap.read()

                # 每十帧保存一次截图
                if count % 40 == 0:
                    # 获取视频当前的时间（以秒为单位）
                    current_time = cap.get(cv2.CAP_PROP_POS_MSEC) / 1000

                    # 将时间转换为字符串，并替换文件名中的非法字符
                    time_str = str(current_time).replace(".", "_")

                    output_filename = f"{filename}_{time_str}.jpg"
                    output_path = os.path.join(output_folder, output_filename)
                    cv2.imwrite(output_path, frame)

                count += 1

                if not ret:
                    break

            cap.release()

def screenshot_images(folder_path, save_path, left, top, right, bottom):
    # 遍历指定文件夹内的所有文件
    for filename in os.listdir(folder_path):
        file_path = os.path.join(folder_path, filename)

        # 判断文件是否为图片文件
        if os.path.isfile(file_path) and filename.lower().endswith(('.png', '.jpg', '.jpeg')):
            # 打开图片文件
            image = Image.open(file_path)

            # 裁剪图片
            cropped_image = image.crop((left, top, right, bottom))

            # 保存截图到指定文件夹
            save_file_path = os.path.join(save_path, filename)
            cropped_image.save(save_file_path)

            print(f"已保存截图: {save_file_path}")

def extract_text_from_images(folder_path, save_path):
    reader = easyocr.Reader(['ch_sim', 'en'])  # 创建OCR阅读器，指定识别语言为简体中文和英文

    texts = []  # 存储提取的文字内容

    for filename in os.listdir(folder_path):
        file_path = os.path.join(folder_path, filename)

        if os.path.isfile(file_path) and filename.lower().endswith(('.png', '.jpg', '.jpeg')):
            try:
                result = reader.readtext(file_path)  # 进行OCR识别
                text = ' '.join([res[1] for res in result])  # 提取识别结果中的文字内容
                texts.append(text)
                print(f"已提取文字: {text}")
            except Exception as e:
                print(f"提取文字失败: {e}")

    try:
        with open(save_path, "w", encoding="utf-8") as file:
            file.write("\n".join(texts) + "\n")
        print(f"文字内容已保存到文件: {save_path}")
    except Exception as e:
        print(f"保存文字内容失败: {e}")

if __name__ == '__main__':
    # 指定输入文件夹和输出文件夹的路径
    input_folder = "" #视频输入路径
    output_folder = "" #前置截图输出路径

    # 调用函数进行截图
    extract_frames(input_folder, output_folder)

    folder_path = output_folder #前置截图输入路径
    OCRout_path = "C:/Users/suzumiya/Downloads/Video/pic/cut" #目标截图输出路径
    # 指定截图的矩形范围 (left, top, right, bottom)
    left = 0
    top = 547
    right = 1280
    bottom = 640
    # 调用函数进行截图
    screenshot_images(folder_path, OCRout_path, left, top, right, bottom)

    OCRout_path = "" #OCR信息输入路径
    save_path = ""#OCR信息输出路径
    extract_text_from_images(OCRout_path, save_path)