Initial commit

tools/tongyi/PptExtraction.py

@@ -0,0 +1,146 @@
+#!/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()