extract_audio and transcribe_audio scripts

2026-08-23 22:12:51 +08:00
parent 86c0dd1c53
commit 02e655ddf4
4 changed files with 1568 additions and 171 deletions
--- a/synthmind/extract_audio.py
+++ b/synthmind/extract_audio.py
@@ -0,0 +1,384 @@
+#!/usr/bin/env python3
+"""
+extract_audio.py - 视频音频批量提取脚本
+功能:
+  - 扫描单个视频文件或遍历指定目录中的所有视频文件
+  - 维护 manifest.json 进度文件，支持断点续传
+  - 使用 FFmpeg 提取音频（MP3, 64k, 22050Hz, 单声道）
+  - 支持视频切分（处理超大文件）
+  - 支持含空格和中文的文件名
+
+用法:
+  python extract_audio.py <视频文件或目录> [选项]
+
+示例:
+  python extract_audio.py /path/to/videos/
+  python extract_audio.py /path/to/video.mp4
+  python extract_audio.py /path/to/videos/ --output /path/to/output/
+  python extract_audio.py /path/to/videos/ --split-size 600   # 切分为600秒片段
+  python extract_audio.py /path/to/videos/ --retry-failed     # 重新处理失败项
+  python extract_audio.py /path/to/videos/ --status           # 查看进度状态
+"""
+
+import argparse
+import json
+import os
+import subprocess
+import sys
+import time
+from pathlib import Path
+
+# ─── 常量 ──────────────────────────────────────────────────────────────────────
+
+MANIFEST_NAME = "manifest.json"
+VIDEO_EXTS = {".mp4", ".mkv", ".avi", ".mov", ".flv", ".wmv", ".webm", ".m4v"}
+
+# FFmpeg 音频提取参数（语音课程优化：体积小）
+FFMPEG_AUDIO_OPTS = [
+    "-vn",                  # 去除视频轨道
+    "-acodec", "libmp3lame",
+    "-ab", "64k",
+    "-ar", "22050",
+    "-ac", "1",             # 单声道
+    "-f", "mp3",
+]
+
+# 视频切分：默认超过此时长（秒）才切分
+DEFAULT_SPLIT_THRESHOLD_SECS = 3600   # 1小时
+DEFAULT_SPLIT_SIZE_SECS = 600         # 每片10分钟
+
+
+# ─── 日志 ──────────────────────────────────────────────────────────────────────
+
+def log(msg: str, level: str = "INFO"):
+    ts = time.strftime("%H:%M:%S")
+    prefix = {"INFO": "  ", "OK": "✅", "ERR": "❌", "WARN": "⚠️ ", "STEP": "▶ "}.get(level, "  ")
+    print(f"[{ts}] {prefix} {msg}", flush=True)
+
+
+# ─── Manifest 操作 ─────────────────────────────────────────────────────────────
+
+def load_manifest(manifest_path: Path) -> dict:
+    if manifest_path.exists():
+        with open(manifest_path, encoding="utf-8") as f:
+            return json.load(f)
+    return {"version": 1, "files": {}}
+
+
+def save_manifest(manifest_path: Path, manifest: dict):
+    manifest_path.parent.mkdir(parents=True, exist_ok=True)
+    with open(manifest_path, "w", encoding="utf-8") as f:
+        json.dump(manifest, f, ensure_ascii=False, indent=2)
+
+
+def get_file_entry(manifest: dict, video_path: str) -> dict:
+    """获取或初始化某个视频文件的 manifest 条目"""
+    if video_path not in manifest["files"]:
+        manifest["files"][video_path] = {
+            "audio_extracted": False,
+            "audio_path": None,
+            "split_segments": [],       # 切分后的片段列表（若有）
+            "error": None,
+            "updated_at": None,
+        }
+    return manifest["files"][video_path]
+
+
+def mark_done(manifest: dict, manifest_path: Path, video_path: str,
+              audio_path: str, segments: list = None):
+    entry = get_file_entry(manifest, video_path)
+    entry["audio_extracted"] = True
+    entry["audio_path"] = audio_path
+    entry["split_segments"] = segments or []
+    entry["error"] = None
+    entry["updated_at"] = time.strftime("%Y-%m-%dT%H:%M:%S")
+    save_manifest(manifest_path, manifest)
+
+
+def mark_failed(manifest: dict, manifest_path: Path, video_path: str, error: str):
+    entry = get_file_entry(manifest, video_path)
+    entry["audio_extracted"] = False
+    entry["error"] = error
+    entry["updated_at"] = time.strftime("%Y-%m-%dT%H:%M:%S")
+    save_manifest(manifest_path, manifest)
+
+
+# ─── FFmpeg 工具函数 ────────────────────────────────────────────────────────────
+
+def check_ffmpeg():
+    try:
+        subprocess.run(["ffmpeg", "-version"], capture_output=True, check=True)
+        return True
+    except (subprocess.CalledProcessError, FileNotFoundError):
+        log("未找到 ffmpeg 命令，请确认已安装：sudo apt install ffmpeg", "ERR")
+        return False
+
+
+def get_video_duration(video_path: str) -> float:
+    """用 ffprobe 获取视频时长（秒），失败返回 0"""
+    try:
+        r = subprocess.run(
+            ["ffprobe", "-v", "error", "-show_entries", "format=duration",
+             "-of", "default=noprint_wrappers=1:nokey=1", video_path],
+            capture_output=True, text=True
+        )
+        return float(r.stdout.strip())
+    except Exception:
+        return 0.0
+
+
+def extract_audio_simple(video_path: str, mp3_path: str) -> bool:
+    """
+    从视频提取音频到 mp3 文件。
+    注意：MP4 的 moov atom 可能在文件尾部，需要 seek，因此不能用 pipe:0 输入。
+    直接用 -i <file> 让 ffmpeg 自行 seek，同时用 -f mp3 明确输出格式。
+    """
+    cmd = ["ffmpeg", "-y", "-i", video_path] + FFMPEG_AUDIO_OPTS + [mp3_path]
+    r = subprocess.run(cmd, capture_output=True)
+    if r.returncode != 0:
+        return False
+    return os.path.exists(mp3_path) and os.path.getsize(mp3_path) > 1024
+
+
+def split_video(video_path: str, output_dir: str, segment_secs: int) -> list:
+    """
+    将视频切分为多个片段。
+    返回切分后的 mp4 片段路径列表；若失败返回空列表。
+    """
+    stem = Path(video_path).stem
+    ext = Path(video_path).suffix
+    out_pattern = os.path.join(output_dir, f"{stem}_seg%03d{ext}")
+
+    cmd = [
+        "ffmpeg", "-y", "-i", video_path,
+        "-c", "copy",
+        "-segment_time", str(segment_secs),
+        "-f", "segment",
+        "-reset_timestamps", "1",
+        out_pattern
+    ]
+    r = subprocess.run(cmd, capture_output=True)
+    if r.returncode != 0:
+        return []
+
+    # 收集生成的片段文件（按名称排序）
+    parent = Path(output_dir)
+    segments = sorted(
+        str(p) for p in parent.glob(f"{stem}_seg*{ext}")
+    )
+    return segments
+
+
+def extract_audio_from_segments(segments: list, mp3_dir: str, stem: str) -> tuple:
+    """
+    对切分后的每个片段提取音频，返回 (segment_mp3s, all_ok)
+    """
+    segment_mp3s = []
+    all_ok = True
+    for seg in segments:
+        seg_stem = Path(seg).stem
+        seg_mp3 = os.path.join(mp3_dir, f"{seg_stem}.mp3")
+        ok = extract_audio_simple(seg, seg_mp3)
+        if ok:
+            segment_mp3s.append(seg_mp3)
+            log(f"    片段 {Path(seg).name} → {Path(seg_mp3).name}", "OK")
+        else:
+            log(f"    片段 {Path(seg).name} 提取失败", "ERR")
+            all_ok = False
+    return segment_mp3s, all_ok
+
+
+# ─── 文件扫描 ──────────────────────────────────────────────────────────────────
+
+def scan_videos(source: str) -> list:
+    """扫描单文件或目录，返回视频文件路径列表"""
+    p = Path(source)
+    if p.is_file():
+        if p.suffix.lower() in VIDEO_EXTS:
+            return [str(p.resolve())]
+        else:
+            log(f"不支持的文件格式: {p.suffix}", "ERR")
+            return []
+    elif p.is_dir():
+        files = []
+        for f in sorted(p.rglob("*")):
+            if f.suffix.lower() in VIDEO_EXTS:
+                files.append(str(f.resolve()))
+        return files
+    else:
+        log(f"路径不存在: {source}", "ERR")
+        return []
+
+
+def mp3_exists(mp3_path: str) -> bool:
+    return os.path.exists(mp3_path) and os.path.getsize(mp3_path) > 0
+
+
+# ─── 状态展示 ──────────────────────────────────────────────────────────────────
+
+def show_status(manifest: dict, all_videos: list):
+    print("\n" + "=" * 60)
+    print("📊 提取音频进度状态")
+    print("=" * 60)
+    done = sum(1 for v in all_videos
+               if manifest["files"].get(v, {}).get("audio_extracted"))
+    failed = sum(1 for v in all_videos
+                 if manifest["files"].get(v, {}).get("error"))
+    pending = len(all_videos) - done
+    print(f"  总文件数  : {len(all_videos)}")
+    print(f"  已完成    : {done}")
+    print(f"  失败      : {failed}")
+    print(f"  待处理    : {pending}")
+    print("=" * 60)
+    for v in all_videos:
+        entry = manifest["files"].get(v, {})
+        if entry.get("audio_extracted"):
+            status = "✅ 完成"
+        elif entry.get("error"):
+            status = f"❌ 失败: {entry['error']}"
+        else:
+            status = "⏳ 待处理"
+        print(f"  {status}  {Path(v).name}")
+    print()
+
+
+# ─── 主流程 ────────────────────────────────────────────────────────────────────
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="视频音频批量提取工具",
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        epilog=__doc__
+    )
+    parser.add_argument("source", help="视频文件路径或包含视频的目录")
+    parser.add_argument("--output", "-o", default=None,
+                        help="MP3 输出目录（默认与视频文件同目录）")
+    parser.add_argument("--manifest", "-m", default=None,
+                        help="manifest.json 路径（默认在 source 目录下）")
+    parser.add_argument("--split-size", type=int, default=None,
+                        help=f"切分阈值（秒）：超过此时长的视频会被切分（默认不切分）")
+    parser.add_argument("--split-segment", type=int, default=DEFAULT_SPLIT_SIZE_SECS,
+                        help=f"每个切分片段的时长（秒，默认 {DEFAULT_SPLIT_SIZE_SECS}）")
+    parser.add_argument("--retry-failed", action="store_true",
+                        help="重新处理上次失败的文件")
+    parser.add_argument("--status", action="store_true",
+                        help="仅查看进度状态，不执行提取")
+    args = parser.parse_args()
+
+    if not check_ffmpeg():
+        sys.exit(1)
+
+    # 确定 manifest 路径
+    source_path = Path(args.source).resolve()
+    base_dir = source_path if source_path.is_dir() else source_path.parent
+    manifest_path = Path(args.manifest) if args.manifest else base_dir / MANIFEST_NAME
+
+    manifest = load_manifest(manifest_path)
+
+    # 扫描视频文件
+    all_videos = scan_videos(args.source)
+    if not all_videos:
+        log("未找到任何视频文件", "WARN")
+        sys.exit(0)
+
+    log(f"扫描到 {len(all_videos)} 个视频文件", "INFO")
+
+    # 仅查看状态
+    if args.status:
+        show_status(manifest, all_videos)
+        return
+
+    # 确定待处理列表
+    pending = []
+    for v in all_videos:
+        entry = get_file_entry(manifest, v)
+        already_done = entry.get("audio_extracted") and entry.get("audio_path") and \
+                       mp3_exists(entry["audio_path"])
+        is_failed = bool(entry.get("error"))
+
+        if already_done:
+            continue
+        if is_failed and not args.retry_failed:
+            log(f"跳过（上次失败，用 --retry-failed 重试）: {Path(v).name}", "WARN")
+            continue
+        pending.append(v)
+
+    done_count = len(all_videos) - len(pending)
+    log(f"📊 总体: {done_count}/{len(all_videos)} 已完成，{len(pending)} 待处理")
+
+    if not pending:
+        log("全部已完成 ✅", "OK")
+        return
+
+    success, failed_list = 0, []
+
+    for i, video in enumerate(pending, 1):
+        video_name = Path(video).name
+        stem = Path(video).stem
+        video_dir = Path(video).parent
+
+        # 确定输出目录
+        out_dir = Path(args.output).resolve() if args.output else video_dir
+        out_dir.mkdir(parents=True, exist_ok=True)
+
+        mp3_path = str(out_dir / f"{stem}.mp3")
+
+        log(f"\n[{i}/{len(pending)}] {video_name}", "STEP")
+
+        try:
+            # 判断是否需要切分
+            duration = get_video_duration(video)
+            need_split = args.split_size and duration > 0 and duration > args.split_size
+
+            if need_split:
+                log(f"  视频时长 {duration:.0f}s > {args.split_size}s，启动切分模式")
+                seg_dir = out_dir / f"{stem}_segments"
+                seg_dir.mkdir(exist_ok=True)
+
+                segments = split_video(video, str(seg_dir), args.split_segment)
+                if not segments:
+                    raise RuntimeError("视频切分失败")
+                log(f"  切分为 {len(segments)} 个片段")
+
+                seg_mp3s, all_ok = extract_audio_from_segments(
+                    segments, str(out_dir), stem
+                )
+                if not all_ok:
+                    raise RuntimeError("部分片段音频提取失败")
+
+                # 记录切分片段到 manifest（主 mp3_path 设为第一个片段）
+                mark_done(manifest, manifest_path, video, seg_mp3s[0] if seg_mp3s else mp3_path,
+                          segments=seg_mp3s)
+            else:
+                # 普通提取
+                log(f"  📥 提取音频中...")
+                if not extract_audio_simple(video, mp3_path):
+                    raise RuntimeError("FFmpeg 音频提取失败")
+
+                size = os.path.getsize(mp3_path)
+                log(f"  输出: {Path(mp3_path).name}  ({size // 1024} KB)", "OK")
+                mark_done(manifest, manifest_path, video, mp3_path)
+
+            success += 1
+            log(f"  进度: {done_count + success}/{len(all_videos)}", "OK")
+
+        except Exception as e:
+            err_msg = str(e)
+            log(f"  {err_msg}", "ERR")
+            mark_failed(manifest, manifest_path, video, err_msg)
+            failed_list.append(video_name)
+            # 清理可能残留的不完整 mp3
+            if os.path.exists(mp3_path) and os.path.getsize(mp3_path) == 0:
+                os.remove(mp3_path)
+
+    print(f"\n{'='*60}")
+    log(f"🏁 完成: {success}/{len(pending)}  失败: {len(failed_list)}", "INFO")
+    if failed_list:
+        log(f"失败文件列表:", "ERR")
+        for f in failed_list:
+            print(f"    - {f}")
+        print("  运行时加 --retry-failed 可重新处理失败项")
+
+
+if __name__ == "__main__":
+    main()