#!/usr/bin/env python3 """ 重新生成带空白音的静态视频并合并 确保所有静态视频都带有500ms空白音 """ import os import subprocess import tempfile import re # 导入编码处理模块 from console_helper import ( safe_print, print_header, print_step, print_info, print_success, print_fail, print_done ) def get_audio_duration(audio_path): """获取音频时长""" args = [ 'ffprobe', '-v', 'quiet', '-print_format', 'json', '-show_format', audio_path ] try: result = subprocess.run(args, check=True, capture_output=True, text=True) import json data = json.loads(result.stdout) return float(data['format']['duration']) except Exception as e: safe_print(f" 获取音频时长失败: {e}") return 0 def create_silent_audio(duration, output_path, ffmpeg_path="ffmpeg"): """创建静音音频""" args = [ ffmpeg_path, '-y', '-f', 'lavfi', '-i', 'anullsrc=r=44100:cl=mono', '-c:a', 'aac', '-ar', '44100', '-ac', '1', '-t', str(duration), output_path ] try: subprocess.run(args, check=True, capture_output=True) return True except subprocess.CalledProcessError as e: safe_print(f" 创建静音音频失败: {e}") return False def concatenate_audio_files(audio_files, output_path, ffmpeg_path="ffmpeg"): """使用filter_complex拼接多个音频文件""" inputs = [] filters = [] for i, audio_file in enumerate(audio_files): inputs.extend(['-i', audio_file]) filters.append(f"[{i}:a]") filters.append(f"concat=n={len(audio_files)}:v=0:a=1[out]") args = [ ffmpeg_path, '-y', ] + inputs + [ '-filter_complex', ''.join(filters), '-map', '[out]', '-c:a', 'aac', '-ar', '44100', '-ac', '1', output_path ] try: subprocess.run(args, check=True, capture_output=True) return True except subprocess.CalledProcessError as e: safe_print(f" 拼接音频失败: {e}") return False def create_static_video(image_path, audio_path, output_path, silence_duration=0.5, ffmpeg_path="ffmpeg"): """使用图片和音频生成静态视频，音频前加空白音""" temp_dir = tempfile.gettempdir() original_duration = get_audio_duration(audio_path) if original_duration == 0: safe_print(f" 无法获取音频时长") return False # 创建静音音频 silent_audio = os.path.join(temp_dir, f"silent_{os.path.basename(audio_path)}.aac") if not create_silent_audio(silence_duration, silent_audio): return False # 拼接静音音频和原始音频 combined_audio = os.path.join(temp_dir, f"combined_{os.path.basename(audio_path)}.aac") if not concatenate_audio_files([silent_audio, audio_path], combined_audio): try: os.remove(silent_audio) except: pass return False total_duration = silence_duration + original_duration # 生成视频 args = [ ffmpeg_path, '-y', '-loop', '1', '-i', image_path, '-i', combined_audio, '-c:v', 'libx264', '-c:a', 'aac', '-ar', '44100', '-ac', '1', '-t', str(total_duration), '-pix_fmt', 'yuv420p', '-shortest', output_path ] try: subprocess.run(args, check=True, capture_output=True) try: os.remove(silent_audio) os.remove(combined_audio) except: pass return True except subprocess.CalledProcessError as e: safe_print(f" 生成视频失败: {e}") try: os.remove(silent_audio) os.remove(combined_audio) except: pass return False def concatenate_videos(video_list, output_path, ffmpeg_path="ffmpeg"): """拼接多个视频""" list_file = 'concat_list.txt' with open(list_file, 'w', encoding='utf-8') as f: for video in video_list: escaped_path = video.replace('\\', '/') f.write(f"file '{escaped_path}'\n") args = [ ffmpeg_path, '-y', '-f', 'concat', '-safe', '0', '-i', list_file, '-c:v', 'libx264', '-c:a', 'aac', '-ar', '44100', '-ac', '1', '-pix_fmt', 'yuv420p', output_path ] try: subprocess.run(args, check=True, capture_output=True) os.remove(list_file) return True except subprocess.CalledProcessError as e: safe_print(f" 拼接视频失败: {e}") try: os.remove(list_file) except: pass return False def main(): # 配置 segments_dir = "all_segments" frames_with_subtitle_dir = "all_frames_with_subtitle" audio_dir = "tts_audio_all" static_videos_dir = "all_static_videos_with_silence" output_video = "final_video_with_silence.mp4" silence_duration = 0.5 # 500毫秒空白音 print_header("重新处理带空白音的静态视频") safe_print("") # 检查目录 if not os.path.exists(segments_dir): safe_print(f"错误: 片段目录 {segments_dir} 不存在") return if not os.path.exists(frames_with_subtitle_dir): safe_print(f"错误: 带字幕的帧目录 {frames_with_subtitle_dir} 不存在") return if not os.path.exists(audio_dir): safe_print(f"错误: 音频目录 {audio_dir} 不存在") return # 创建输出目录 if not os.path.exists(static_videos_dir): os.makedirs(static_videos_dir) # 1. 生成带空白音的静态视频 print_step(1, 2, "生成带空白音的静态视频...") static_video_files = [] # 遍历所有带字幕的帧 frame_files = sorted([f for f in os.listdir(frames_with_subtitle_dir) if f.endswith('.jpg')]) for frame_file in frame_files: # 提取序号 match = re.match(r'frame_(\d+)_with_subtitle\.jpg', frame_file) if match: line_number = int(match.group(1)) image_path = os.path.join(frames_with_subtitle_dir, frame_file) audio_path = os.path.join(audio_dir, f"tts_line_{line_number}.wav") output_path = os.path.join(static_videos_dir, f"static_video_{line_number:03d}.mp4") if not os.path.exists(audio_path): safe_print(f" 警告: 音频文件 {audio_path} 不存在，跳过第{line_number}句") continue safe_print(f" 生成第{line_number}句静态视频...") if create_static_video(image_path, audio_path, output_path, silence_duration): static_video_files.append(output_path) else: safe_print(f" 生成第{line_number}句静态视频失败") print_info("成功生成", f"{len(static_video_files)}/{len(frame_files)} 个静态视频") safe_print("") # 2. 拼接视频 print_step(2, 2, "拼接视频...") video_list = [] # 遍历所有序号 max_number = 68 # 已知最大序号 for i in range(1, max_number + 1): # 原始片段 segment = os.path.join(segments_dir, f"segment_{i:03d}.mp4") if os.path.exists(segment): video_list.append(segment) # 静态视频 static_video = os.path.join(static_videos_dir, f"static_video_{i:03d}.mp4") if os.path.exists(static_video): video_list.append(static_video) # 检查第69段 segment_69 = os.path.join(segments_dir, "segment_069.mp4") if os.path.exists(segment_69): video_list.append(segment_69) if not video_list: safe_print("错误: 没有找到任何视频文件") return print_info("总视频数", str(len(video_list))) safe_print("开始拼接...") if concatenate_videos(video_list, output_video): print_info("成功生成", output_video) else: safe_print("拼接视频失败") return print_done() if __name__ == '__main__': main()