XCDesktop/tools/tongyi/PptExtraction.py

#!/usr/bin/env python
#coding=utf-8

import os
import json
import requests
import datetime
from urllib.parse import urlparse


def read_a_txt():
    """
    读取并解析 a.txt 文件，提取 PptExtraction 链接
    """
    try:
        file_path = r'd:\Xuanchi\高斯泼溅\XCNote\tools\tongyi\a.txt'
        with open(file_path, 'r', encoding='utf-8') as f:
            # 读取文件内容，跳过开头的 "响应数据: " 字符串
            content = f.read().replace('响应数据: ', '')
            data = json.loads(content)
            
        ppt_extraction_url = data.get('Data', {}).get('Result', {}).get('PptExtraction')
        if ppt_extraction_url:
            print(f"成功提取 PptExtraction 链接: {ppt_extraction_url}")
            return ppt_extraction_url
        else:
            print("无法找到 PptExtraction 链接")
            return None
    except Exception as e:
        print(f"读取 a.txt 文件失败: {e}")
        import traceback
        traceback.print_exc()
        return None


def download_ppt_extraction(url):
    """
    下载并解析 PptExtraction 内容
    """
    try:
        print(f"开始下载 PptExtraction 内容: {url}")
        response = requests.get(url, timeout=30)
        response.raise_for_status()
        
        data = response.json()
        ppt_extraction_data = data.get('PptExtraction', {})
        key_frame_list = ppt_extraction_data.get('KeyFrameList', [])
        
        print(f"成功下载并解析 PptExtraction 内容，共 {len(key_frame_list)} 张图片")
        return key_frame_list
    except Exception as e:
        print(f"下载 PptExtraction 内容失败: {e}")
        import traceback
        traceback.print_exc()
        return []


def download_image(url, save_dir, timestamp, index):
    """
    下载图片并保存到指定目录
    """
    try:
        print(f"开始下载图片: {url}")
        response = requests.get(url, timeout=30)
        response.raise_for_status()
        
        # 生成图片文件名：年月日_时分秒_序号.png
        image_filename = f"{timestamp}_{str(index).zfill(3)}.png"
        image_path = os.path.join(save_dir, image_filename)
        
        # 保存图片
        with open(image_path, 'wb') as f:
            f.write(response.content)
        
        print(f"成功下载图片: {image_filename}")
        return image_filename
    except Exception as e:
        print(f"下载图片失败: {e}")
        import traceback
        traceback.print_exc()
        return None





def main():
    """
    主函数
    """
    print("===== 开始处理 PPT 提取结果 =====")
    
    # 1. 读取并解析 a.txt 文件
    ppt_extraction_url = read_a_txt()
    if not ppt_extraction_url:
        print("无法提取 PptExtraction 链接，程序退出")
        return
    
    # 2. 下载并解析 PptExtraction 内容
    key_frame_list = download_ppt_extraction(ppt_extraction_url)
    if not key_frame_list:
        print("无法获取 PPT 内容，程序退出")
        return
    
    # 3. 生成时间戳（年月日_时分秒）
    timestamp = datetime.datetime.now().strftime('%Y%m%d_%H%M%S')
    print(f"生成时间戳: {timestamp}")
    
    # 4. 创建保存目录
    save_dir = r'd:\Xuanchi\高斯泼溅\XCNote\tools\tongyi\ppt_output'
    if not os.path.exists(save_dir):
        os.makedirs(save_dir)
        print(f"创建保存目录: {save_dir}")
    
    # 5. 下载图片并整理结果
    result_dict = {}
    downloaded_count = 0
    
    for i, frame in enumerate(key_frame_list):
        image_url = frame.get('FileUrl')
        if image_url:
            # 下载图片
            image_filename = download_image(image_url, save_dir, timestamp, i+1)
            if image_filename:
                downloaded_count += 1
                # 整理结果到字典
                result_dict[i+1] = {
                    "Start": frame.get('Start'),
                    "End": frame.get('End'),
                    "ImageMd": f"![]({image_filename})"
                }
    
    if not downloaded_count:
        print("无法下载任何图片，程序退出")
        return
    
    # 6. 输出整理结果
    print(f"\n===== 处理完成 =====")
    print(f"保存目录: {save_dir}")
    print(f"下载的图片数量: {downloaded_count}")
    print(f"\n整理结果:")
    print(json.dumps(result_dict, indent=4, ensure_ascii=False))


if __name__ == "__main__":
    main()