#!/usr/bin/env python3 import os import sys from pathlib import Path import mutagen from mutagen.id3 import ID3 from mutagen.flac import FLAC from mutagen.mp4 import MP4 from mutagen.wave import WAVE def extract_raw_lyrics(file_path): """从音乐文件中直接提取原始歌词，不做任何修改""" try: file_ext = Path(file_path).suffix.lower() if file_ext in ['.mp3']: return extract_id3_lyrics_raw(file_path) elif file_ext in ['.flac']: return extract_flac_lyrics_raw(file_path) elif file_ext in ['.m4a', '.mp4']: return extract_mp4_lyrics_raw(file_path) elif file_ext in ['.wav', '.wave']: return extract_wav_lyrics_raw(file_path) else: return None except Exception as e: print(f" 警告: 提取歌词时出错 - {e}") return None def extract_id3_lyrics_raw(file_path): """从 MP3 文件提取原始 ID3 歌词""" try: audio = ID3(file_path) # 查找 USLT 帧（歌词） for key in audio.keys(): if key.startswith('USLT'): lyrics_text = str(audio[key]) # 检查是否是有效的歌词（不是空字符串或只有空格） if lyrics_text and lyrics_text.strip(): return lyrics_text return None except Exception as e: return None def extract_flac_lyrics_raw(file_path): """从 FLAC 文件提取原始歌词""" try: audio = FLAC(file_path) # 查找 lyrics 标签 if 'lyrics' in audio: lyrics_text = '\n'.join(audio['lyrics']) if lyrics_text and lyrics_text.strip(): return lyrics_text return None except: return None def extract_mp4_lyrics_raw(file_path): """从 MP4/M4A 文件提取原始歌词""" try: audio = MP4(file_path) if '©lyr' in audio: lyrics_text = audio['©lyr'][0] if lyrics_text and lyrics_text.strip(): return lyrics_text return None except: return None def extract_wav_lyrics_raw(file_path): """从 WAV 文件提取原始歌词""" try: audio = WAVE(file_path) # 检查是否有标签 if not audio.tags: return None # WAV 文件可能使用 ID3v2 标签存储歌词 # 查找 USLT（非同步歌词文本）帧 for tag in audio.tags.keys(): if tag.startswith('USLT'): lyrics_text = str(audio.tags[tag]) if lyrics_text and lyrics_text.strip(): return lyrics_text # 如果没有找到 USLT，尝试查找其他可能的歌词标签 lyrics_keys = ['lyrics', 'LYRICS', 'Lyrics', 'UNSYNCED LYRICS'] for key in lyrics_keys: if key in audio.tags: lyrics_text = audio.tags[key][0] if lyrics_text and lyrics_text.strip(): return lyrics_text return None except Exception as e: # WAV 文件可能没有标签或标签格式不支持 return None def format_file_size(size_bytes): """格式化文件大小显示""" if size_bytes >= 1024 * 1024: return f"{size_bytes / (1024 * 1024):.1f} MB" elif size_bytes >= 1024: return f"{size_bytes / 1024:.1f} KB" else: return f"{size_bytes} B" def main(): music_dir = Path.home() / 'Music' lyrics_base_dir = Path.home() / '.lyrics' # 创建基础歌词目录 lyrics_base_dir.mkdir(exist_ok=True) # 支持的文件格式 supported_formats = [ '.mp3', '.MP3', '.flac', '.FLAC', '.m4a', '.M4A', '.mp4', '.MP4', '.wav', '.WAV', '.wave', '.WAVE' ] total_files = 0 extracted_lyrics = 0 skipped_files = 0 format_stats = {} print(f"🎵 原始歌词提取工具") print(f"📁 扫描目录: {music_dir}") print(f"💾 保存格式: .lrc (与源文件同名同目录，内容完全一致)") print("=" * 60) # 遍历音乐文件 for format in supported_formats: format_count = 0 format_lyrics = 0 for file_path in music_dir.rglob(f'*{format}'): total_files += 1 format_count += 1 file_size = file_path.stat().st_size print(f"\n🎼 处理: {file_path.relative_to(music_dir)} ({format_file_size(file_size)})") print(f" 📊 格式: {format.upper()}") # 直接提取原始歌词，不做任何修改 raw_lyrics = extract_raw_lyrics(file_path) if raw_lyrics and raw_lyrics.strip(): # 创建与源文件相同的目录结构和文件名（仅后缀改为 .lrc） relative_path = file_path.relative_to(music_dir) lrc_filename = file_path.with_suffix('.lrc').name lrc_output_path = lyrics_base_dir / relative_path.parent / lrc_filename # 确保目标目录存在 lrc_output_path.parent.mkdir(parents=True, exist_ok=True) try: # 直接写入原始歌词内容，不做任何修改 with open(lrc_output_path, 'w', encoding='utf-8') as f: f.write(raw_lyrics) extracted_lyrics += 1 format_lyrics += 1 print(f" ✅ 保存原始歌词: {lrc_output_path.relative_to(lyrics_base_dir)}") print(f" 📖 原始内容长度: {len(raw_lyrics)} 字符") print(f" 📍 保存位置: {lrc_output_path}") # 显示前几行内容预览 lines = raw_lyrics.split('\n') preview_lines = [line for line in lines if line.strip()][:3] if preview_lines: print(f" 👀 内容预览: {preview_lines[0][:50]}{'...' if len(preview_lines[0]) > 50 else ''}") if len(preview_lines) > 1: for line in preview_lines[1:]: print(f" {line[:50]}{'...' if len(line) > 50 else ''}") except Exception as e: print(f" ❌ 保存失败: {e}") skipped_files += 1 else: print(" ❌ 未找到歌词") skipped_files += 1 print(" " + "-" * 50) # 记录格式统计 if format_count > 0: format_stats[format] = {'total': format_count, 'lyrics': format_lyrics} print("=" * 60) print("🎉 扫描完成!") print(f"📈 总体统计:") print(f" • 总共处理文件: {total_files}") print(f" • 成功提取歌词: {extracted_lyrics}") print(f" • 跳过/失败: {skipped_files}") print(f" • 保存位置: {lyrics_base_dir} (镜像 Music 目录结构)") # 显示格式统计 if format_stats: print(f"\n📊 格式统计:") for format, stats in format_stats.items(): success_rate = (stats['lyrics'] / stats['total']) * 100 if stats['total'] > 0 else 0 print(f" • {format.upper():6} : {stats['total']:3} 文件, {stats['lyrics']:2} 歌词 ({success_rate:.1f}%)") # 显示提取的文件结构 if extracted_lyrics > 0: print(f"\n📁 歌词文件结构:") lrc_files = list(lyrics_base_dir.rglob('*.lrc')) for lrc_file in sorted(lrc_files, key=os.path.getmtime, reverse=True)[:6]: file_size = lrc_file.stat().st_size relative_path = lrc_file.relative_to(lyrics_base_dir) print(f" • {relative_path} ({format_file_size(file_size)})") # 显示文件大小统计 total_size = sum(f.stat().st_size for f in lrc_files) print(f"\n💾 LRC 文件总大小: {format_file_size(total_size)}") # 显示目录统计 unique_dirs = len(set(f.parent for f in lrc_files)) print(f"📂 涉及目录: {unique_dirs} 个") # 提示信息 if total_files == 0: print(f"\n⚠️ 警告: 在 {music_dir} 中没有找到支持的音乐文件") print(f" 支持格式: {', '.join([f.upper() for f in supported_formats])}") if __name__ == "__main__": main()