python实现视频抽帧与添加背景音频和字幕朗读的脚本分享

from moviepy.editor import VideoFileClip, CompositeAudioClip, CompositeVideoClip, concatenate_videoclips
from cv2 import VideoCapture, VideoWriter, VideoWriter_fourcc, CAP_PROP_FRAME_COUNT

# 单个视频抽帧
def video_extract_frame(video_path, out_path):
  # 打开视频文件
  vc = VideoCapture(video_path)
  # 视频的总帧数
  total_frame = int(vc.get(CAP_PROP_FRAME_COUNT))
  video = VideoFileClip(video_path, audio=False)
  # # 创建一个视频写入对象。设置视频的宽度和高度、帧率、输出路径
  fourcc = VideoWriter_fourcc(*'mp4v')
  videoWriter = VideoWriter(out_path, fourcc, VIDEO_FPS, (video.w, video.h))
  if vc.isOpened():
      status, frame = vc.read()
  else:
      status = False
      print("视频没有打开成功！")
      vc.release()
      video.close()
      videoWriter.release()
      return False
  if status:
      for index in trange(total_frame, desc='抽帧进度'):
          # 读取视频帧并写入输出视频
          status, frame = vc.read()
          if index % VIDEO_FPS == 0:
              skip_frames = tool.get_unique_random_numbers(index, VIDEO_FPS)
          if index in skip_frames:
              continue
          videoWriter.write(frame)
  videoWriter.release()
  vc.release()
  video.close()

video_extract_frame('./test.mp4', 'result.mp4')

 for index, video_file in enumerate(['1.mp4', '2.mp4', '3.mp4']):
    //取出链接中的视频文件名称，例如1,2,3
    video_name = tool.get_file_name(video_file)
    //组装成新目录、新名字（根据自己需要）
    out_path = "{}{}.mp4".format(frame_path, video_name)
    videoTool.video_extract_frame(video_file, out_path)
    print("\n第{}条, 视频抽帧已完成: {}".format(index + 1, out_path))

# 字幕片段
def generate_textclip(text, width, params, start, duration) -> TextClip:
    return TextClip(
        text,
        font=params.get('font'),
        align=params.get('align'),
        fontsize=params.get('fontsize'),
        color=params.get('color', '#ffbd00'),
        size=(width, params.get('height')),
        stroke_color=params.get('stroke_color'),
        stroke_width=params.get('stroke_width')
    ).set_position((params['location']['x'], params['location']['y'])).set_duration(duration).set_start(start)
# 添加srt字幕
def add_srt(video_clip, params):
  if not (isfile(params["srt_path"]) and params["srt_path"].endswith('.srt')):
      print('字幕仅支持srt格式!')
      return []
  else:
      # 获取视频的宽度和高度
      v_width, v_height = video_clip.w, video_clip.h
      # 所有字幕剪辑
      txts = []
      content = tool.read_srt(params["srt_path"])
      sequences = tool.get_sequences(content)
      max_count = len(sequences)
      max_duration = video_clip.duration
      srt_text = params["srt_text"]
      for index, line in enumerate(sequences):
          print("字幕生成进度:{}/{}".format(index, max_count))
          if len(line) < 3:
              continue
          start = line[1].split(' --> ')[0]
          end = line[1].split(' --> ')[1]
          start = tool.str_float_time(start)
          end = tool.str_float_time(end)
          start, end = map(float, (start, end))
          if start >= max_duration:
              break
          if end >= max_duration:
              end = max_duration
          duration = end - start
          txt_srt = generate_textclip(line[2], (v_width - 20), srt_text, start, duration)
          txts.append(txt_srt)
      print("\n字幕转换已完成...")
      return txts

def read_srt(self, path):
    content = ""
    with open(path, 'r', encoding='UTF-8') as f:
        content = f.read()
        return content

# 字幕拆分
def get_sequences(self, content):
    sequences = content.split('\n\n')
    sequences = [sequence.split('\n') for sequence in sequences]
    # 去除每一句空值
    sequences = [list(filter(None, sequence)) for sequence in sequences]
    # 去除整体空值
    return list(filter(None, sequences))

# 字符串数字格式化成时间
def str_float_time(self, str):
    str_list = str.split(':')
    hour = int(str_list[0])
    minute = int(str_list[1])
    second = int(str_list[2].split(',')[0])
    minsecond = int(str_list[2].split(',')[1])
    allTime = hour * 60 * 60 + minute * 60 + second + minsecond / 1000
    return allTime

# frame_video_paths:是抽帧后的视频片段
def merge_videos_with_bgm(params, frame_video_paths, out_path):
    # 用VideoFileClip加载所有输入视频文件
    video_clips = [VideoFileClip(file) for file in frame_video_paths]
    final_clip = concatenate_videoclips(video_clips)
    bgm_music = audioTool.get_audio({
        "volume": params.get("bgm_volume", 0.1), #背景音频小声点
        "duration": final_clip.duration,
        "audio_path": params['bgm_path']
    })
    # 加载主音乐(朗读音频)
    main_music = audioTool.get_audio({
        "volume": params.get("audio_volume", 1.0),# 朗读音频大声点
        "duration": final_clip.duration,
        "audio_path": params['audio_path']
    })
    # 将音乐混合到最终视频切片
    final_clip = final_clip.set_audio(CompositeAudioClip([main_music, bgm_music]))
    video_srt = videoTextTool.add_srt(final_clip, params)
    final_clip.extend(video_srt)
    # 复合视频
    video = CompositeVideoClip(final_clip)
    output_path = path.join(out_path, "result.mp4")
    # 输出最终视频
    video.write_videofile(output_path)