递归处理压缩文件，子目录中的文件

server/file_association.py

@@ -14,6 +14,8 @@ from typing import Optional, List, Dict, Tuple, Union
 from datetime import datetime
 import time
 import re
+import shutil
+import shutil
 
 
 def extract_all_zips(
@@ -238,6 +240,42 @@ def get_files_with_times(folder: Path) -> List[Tuple[Path, datetime]]:
     return files
 
 
+def extract_zip_recursive(zip_path: Path, extract_dir: Path) -> List[Path]:
+    """递归解压 zip 文件，如果解压后的文件还有 zip，继续解压"""
+    # 先清空 extract_dir 中的内容
+    for item in extract_dir.iterdir():
+        if item.is_file():
+            item.unlink()
+        elif item.is_dir():
+            shutil.rmtree(item)
+
+    # 解压当前层
+    with zipfile.ZipFile(zip_path, 'r') as zip_ref:
+        zip_ref.extractall(extract_dir)
+
+    # 查找解压后的所有 zip 文件，递归解压
+    new_zips = list(extract_dir.glob("*.zip"))
+    while new_zips:
+        for z in new_zips:
+            with zipfile.ZipFile(z, 'r') as zip_ref:
+                zip_ref.extractall(extract_dir)
+            z.unlink()  # 删除已解压的 zip 文件
+        new_zips = list(extract_dir.glob("*.zip"))
+
+    # 递归收集所有解压后的文件（包括子目录）
+    def collect_all_files(dir_path: Path) -> List[Path]:
+        files = []
+        for item in dir_path.iterdir():
+            if item.is_file():
+                files.append(item)
+            elif item.is_dir():
+                files.extend(collect_all_files(item))
+        return files
+
+    extracted_files = collect_all_files(extract_dir)
+    return extracted_files
+
+
 def build_file_associations(
     word_content: List[str],
     twole_folder: Path,
@@ -245,7 +283,7 @@ def build_file_associations(
 ) -> Dict:
     """构建文件关联关系"""
     result = []
-    
+
     twole_files = get_files_with_times(twole_folder)
     zxxk_files = get_files_with_times(zxxk_folder)
 
@@ -254,16 +292,49 @@ def build_file_associations(
         parts = content.split('\t')
         if len(parts) < 6:
             continue
-        
+
         # 提取两组数据：标题、网址、时间
         title1, url1, time1 = parts[0].strip(), parts[1].strip(), parts[2].strip()
         title2, url2, time2 = parts[3].strip(), parts[4].strip(), parts[5].strip()
-        
+
+        # 辅助函数：处理文件路径，如果是 zip 则递归解压
+        def process_file(file_path: Path) -> List[str]:
+            filenames = [file_path.name]
+            # 检查是否是压缩文件
+            if file_path.suffix.lower() in ('.zip', '.rar', '.7z'):
+                tmp_dir = Path(__file__).parent / "tmp"
+                tmp_dir.mkdir(exist_ok=True)
+                extract_target = tmp_dir / file_path.stem
+                # 清空 extract_target 目录
+                if extract_target.exists():
+                    for item in extract_target.iterdir():
+                        if item.is_file():
+                            item.unlink()
+                        elif item.is_dir():
+                            shutil.rmtree(item)
+                else:
+                    extract_target.mkdir(parents=True, exist_ok=True)
+
+                # 根据压缩格式选择解压方式
+                if file_path.suffix.lower() == '.zip':
+                    extracted = extract_zip_recursive(file_path, extract_target)
+                else:
+                    # 其他压缩格式使用 subprocess
+                    import subprocess
+                    subprocess.run(['unzip', '-o', str(file_path), '-d', str(extract_target)],
+                                   capture_output=True)
+                    extracted = list(extract_target.iterdir())
+
+                # 将解压后的文件名添加到列表
+                filenames.extend([f.name for f in extracted])
+                return filenames
+            return filenames
+
         # 第一组：根据网址匹配文件
         if 'www.21cnjy.com' in url1 and twole_files:
             file_path, ctime = twole_files.pop(0)
             result.append({
-                "filename": [file_path.name],
+                "filename": process_file(file_path),
                 "title": title1,
                 "url": url1,
                 "time": time1
@@ -271,17 +342,17 @@ def build_file_associations(
         elif 'www.zxxk.com' in url1 and zxxk_files:
             file_path, ctime = zxxk_files.pop(0)
             result.append({
-                "filename": [file_path.name],
+                "filename": process_file(file_path),
                 "title": title1,
                 "url": url1,
                 "time": time1
             })
-        
+
         # 第二组：根据网址匹配文件
         if 'www.21cnjy.com' in url2 and twole_files:
             file_path, ctime = twole_files.pop(0)
             result.append({
-                "filename": [file_path.name],
+                "filename": process_file(file_path),
                 "title": title2,
                 "url": url2,
                 "time": time2
@@ -289,12 +360,12 @@ def build_file_associations(
         elif 'www.zxxk.com' in url2 and zxxk_files:
             file_path, ctime = zxxk_files.pop(0)
             result.append({
-                "filename": [file_path.name],
+                "filename": process_file(file_path),
                 "title": title2,
                 "url": url2,
                 "time": time2
             })
-    
+
     return {"items": result}