init version for extract audio

synthmind/nas_audio_extract_v3.py

@@ -0,0 +1,171 @@
+#!/usr/bin/env python3
+"""
+NAS 视频音频批量提取 v3
+流程: ssh cat .mp4 → 本地文件 → FFmpeg → shell重定向上传 → 删除本地
+"""
+
+import subprocess
+import os
+import time
+
+NAS_BASE = "/volume2/work/Public Cloud Learning Sessions"
+MAC_MP4  = os.path.expanduser("~/.openclaw/temp/xingshu/nas_mp4")
+MAC_MP3  = os.path.expanduser("~/.openclaw/temp/xingshu/nas_mp3_out")
+MAC_LOG  = os.path.expanduser("~/.openclaw/temp/xingshu/logs/nas_audio_v3.log")
+PROGRESS = os.path.expanduser("~/.openclaw/temp/xingshu/nas_audio_v3.done")
+SSH_USER = "shenwei"
+NAS_HOST = "192.168.3.17"
+
+os.makedirs(MAC_MP4, exist_ok=True)
+os.makedirs(MAC_MP3, exist_ok=True)
+
+FFMPEG_BIN = "/opt/homebrew/bin/ffmpeg"
+FFMPEG_CMD = [FFMPEG_BIN, "-y", "-i", "pipe:0",
+              "-vn", "-acodec", "libmp3lame", "-ab", "64k", "-ar", "22050", "-ac", "1",
+              "-f", "mp3", "pipe:1"]
+
+def log(msg):
+    ts = time.strftime("%H:%M:%S")
+    line = f"[{ts}] {msg}"
+    print(line)
+    with open(MAC_LOG, "a") as f:
+        f.write(line + "\n")
+
+def ssh_download(nas_path, local_path):
+    """NAS 文件通过 ssh cat 落地到本地（1MB 分块）"""
+    cmd = ["ssh", f"{SSH_USER}@{NAS_HOST}", f"cat '{nas_path}'"]
+    with open(local_path, "wb") as fout:
+        proc = subprocess.Popen(cmd, stdout=subprocess.PIPE)
+        while True:
+            chunk = proc.stdout.read(1024 * 1024)
+            if not chunk:
+                break
+            fout.write(chunk)
+        proc.stdout.close()
+        proc.wait()
+    return proc.returncode == 0
+
+def ssh_upload(local_path, nas_path):
+    """本地文件通过 shell 重定向上传到 NAS（本地路径需加引号防空格）"""
+    cmd = f'ssh {SSH_USER}@{NAS_HOST} "cat > \'{nas_path}\'" < "{local_path}"'
+    return subprocess.run(cmd, shell=True, stdout=subprocess.DEVNULL,
+                          stderr=subprocess.DEVNULL).returncode == 0
+
+def get_nas_mp3s():
+    r = subprocess.run(["ssh", f"{SSH_USER}@{NAS_HOST}",
+                       f"ls '{NAS_BASE}'/*.mp3 2>/dev/null"],
+                      capture_output=True, text=True)
+    if r.returncode != 0:
+        return set()
+    return set(l.strip() for l in r.stdout.split("\n") if l.strip())
+
+def get_nas_mp4s():
+    r = subprocess.run(["ssh", f"{SSH_USER}@{NAS_HOST}",
+                       f"ls '{NAS_BASE}'/*.mp4 2>/dev/null"],
+                      capture_output=True, text=True)
+    if r.returncode != 0:
+        return []
+    return [l.strip() for l in r.stdout.split("\n") if l.strip()]
+
+def load_done():
+    if os.path.exists(PROGRESS):
+        with open(PROGRESS) as f:
+            return set(f.read().splitlines())
+    return set()
+
+def save_done(done_set):
+    with open(PROGRESS, "w") as f:
+        f.write("\n".join(done_set))
+
+def main():
+    log("=" * 60)
+    log("🚀 v3 开始批量提取")
+    
+    done = load_done()
+    nas_mp3s = get_nas_mp3s()
+    all_mp4s = get_nas_mp4s()
+    
+    pending = []
+    for v in all_mp4s:
+        name = os.path.basename(v)
+        mp3_name = name.replace(".mp4", ".mp3")
+        nas_mp3_path = f"{NAS_BASE}/{mp3_name}"
+        if name not in done and nas_mp3_path not in nas_mp3s:
+            pending.append(name)
+    
+    total = len(all_mp4s)
+    done_count = total - len(pending)
+    log(f"📊 总体: {done_count}/{total} 已完成，{len(pending)} 待处理")
+    
+    if not pending:
+        log("✅ 全部已完成")
+        return
+    
+    success, failed = 0, []
+    
+    for i, video in enumerate(pending, 1):
+        mp3_name = video.replace(".mp4", ".mp3")
+        nas_mp4 = f"{NAS_BASE}/{video}"
+        nas_mp3 = f"{NAS_BASE}/{mp3_name}"
+        local_mp4 = f"{MAC_MP4}/{video}"
+        local_mp3 = f"{MAC_MP3}/{mp3_name}"
+        
+        log(f"\n[{i}/{len(pending)}] ▶ {video}")
+        
+        try:
+            # Step 1: 下载 .mp4 → 本地
+            log(f"  📥 downloading...")
+            if not ssh_download(nas_mp4, local_mp4):
+                raise RuntimeError("download failed")
+            size_mp4 = os.path.getsize(local_mp4)
+            log(f"  ✅ downloaded {size_mp4//1024//1024}MB")
+            
+            # Step 2: FFmpeg 提取 .mp3
+            log(f"  🔊 extracting...")
+            with open(local_mp3, "wb") as fout:
+                proc = subprocess.Popen(["/bin/cat", local_mp4],
+                                       stdout=subprocess.PIPE, stderr=subprocess.DEVNULL)
+                ffmpeg = subprocess.Popen(FFMPEG_CMD,
+                                          stdin=proc.stdout, stdout=fout, stderr=subprocess.DEVNULL)
+                proc.stdout.close()
+                ret = ffmpeg.wait()
+                proc.wait()
+            
+            if ret != 0:
+                raise RuntimeError("ffmpeg failed")
+            
+            # 删除 .mp4 释放空间
+            os.remove(local_mp4)
+            
+            size_mp3 = os.path.getsize(local_mp3)
+            log(f"  ✅ extracted {size_mp3//1024//1024}MB ({size_mp3//1024}KB)")
+            
+            # Step 3: 上传 .mp3 → NAS
+            log(f"  📤 uploading...")
+            if not ssh_upload(local_mp3, nas_mp3):
+                raise RuntimeError("upload failed")
+            log(f"  ✅ uploaded to NAS")
+            
+            # 删除 .mp3
+            os.remove(local_mp3)
+            
+            done.add(video)
+            save_done(done)
+            success += 1
+            
+            log(f"  📊 进度: {done_count + success}/{total}")
+            
+        except Exception as e:
+            log(f"  ❌ {e}")
+            failed.append(video)
+            for p in [local_mp4, local_mp3]:
+                if os.path.exists(p):
+                    os.remove(p)
+    
+    log(f"\n{'='*60}")
+    log(f"🏁 完成: {success}/{len(pending)}，失败: {len(failed)}")
+    if failed:
+        log(f"失败列表: {failed}")
+
+if __name__ == "__main__":
+    main()