Python 3 视频文件信息分析代码优化

以下是对python3代码的优化建议：/n/n1. 使用列表推导式简化获取视频文件列表的代码：/npython/nvideo_files = [os.path.join(root, file) for root, dirs, files in os.walk(video_folder) for file in files if any(file.endswith(format) for format in supported_formats)]/n/n2. 将获取文件大小并进行单位换算的代码封装成一个函数，简化代码可读性：/npython/ndef format_size(size):/n if size < 1024:/n return f'{size} B'/n elif size < 1024 * 1024:/n return f'{size / 1024:.2f} KiB'/n elif size < 1024 * 1024 * 1024:/n return f'{size / 1024 / 1024:.2f} MiB'/n else:/n return f'{size / 1024 / 1024 / 1024:.2f} GiB'/n/n3. 使用Popen替代run函数，以便在处理大文件时可以逐行读取数据，而不必等待整个输出完成：/npython/nvideo_process = subprocess.Popen(['mediainfo', '--Inform=Video;%Format%|%Width%x%Height%|%BitRate/String%|%FrameRate%|%Duration/String3%', video_file], stdout=subprocess.PIPE)/naudio_process = subprocess.Popen(['mediainfo', '--Inform=Audio;%BitRate/String%|%SamplingRate/String%|%Language/String%', video_file], stdout=subprocess.PIPE)/nvideo_output, _ = video_process.communicate()/naudio_output, _ = audio_process.communicate()/nvideo_output = video_output.decode().strip()/naudio_output = audio_output.decode().strip()/n/n4. 将解析输出结果的代码封装成一个函数，简化代码可读性：/npython/ndef parse_output(output):/n return output.split('|')/n/n5. 将处理多音轨情况的代码封装成一个函数，简化代码可读性：/npython/ndef parse_audio_info(audio_info):/n audio_bitrate = []/n audio_sampling_rate = []/n audio_lang = []/n for i in range(len(audio_info) // 3):/n audio_bitrate.append(audio_info[i * 3])/n audio_sampling_rate.append(audio_info[i * 3 + 1])/n audio_lang.append(audio_info[i * 3 + 2])/n return audio_bitrate, audio_sampling_rate, audio_lang/n/n6. 将获取帧率的代码封装成一个函数，简化代码可读性：/npython/ndef get_framerate(video_info):/n try:/n return float(video_info[3])/n except ValueError:/n return None/n/n7. 将打印文件信息的代码封装成一个函数，简化代码可读性：/npython/ndef print_file_info(file_name, size_str, duration, video_info, audio_lang, ratio):/n bitrate = re.sub(pattern, r'/1/2', video_info[2])/n framerate = get_framerate(video_info)/n print(f'{file_name}, {size_str}, {duration}, {video_info[1]}, {bitrate}, {framerate}, {' / '.join(audio_lang)}, {ratio}')/n/n8. 将整个文件的处理逻辑封装成一个函数，提高代码的可复用性和可读性：/npython/ndef process_video_files(video_folder):/n # 获取视频文件列表（包括子目录）/n video_files = [os.path.join(root, file) for root, dirs, files in os.walk(video_folder) for file in files if any(file.endswith(format) for format in supported_formats)]/n # 遍历所有视频文件/n for video_file in video_files:/n # 获取文件名/n file_name = os.path.basename(video_file)/n/n # 获取文件大小并进行单位换算/n size = os.path.getsize(video_file)/n size_str = format_size(size)/n/n # 使用mediainfo获取视频信息 / 音频信息/n video_process = subprocess.Popen(['mediainfo', '--Inform=Video;%Format%|%Width%x%Height%|%BitRate/String%|%FrameRate%|%Duration/String3%', video_file], stdout=subprocess.PIPE)/n audio_process = subprocess.Popen(['mediainfo', '--Inform=Audio;%BitRate/String%|%SamplingRate/String%|%Language/String%', video_file], stdout=subprocess.PIPE)/n video_output, _ = video_process.communicate()/n audio_output, _ = audio_process.communicate()/n video_output = video_output.decode().strip()/n audio_output = audio_output.decode().strip()/n/n # 解析输出结果/n video_info = parse_output(video_output)/n audio_info = parse_output(audio_output)/n/n # 处理多音轨情况/n audio_bitrate, audio_sampling_rate, audio_lang = parse_audio_info(audio_info)/n/n # 时长取整/n duration = video_info[4].split('.')[0]/n h, m, s = duration.split(':')/n duration = f'{h}:{m}:{str(s).zfill(2)}'/n/n # 以分钟计算的时长/n duration_minutes = int(h) * 60 + int(m) + math.ceil(float(s)) / 60/n/n # 计算压缩比率/n ratio = round(duration_minutes / size * 1000000000, 2)/n/n # 打印文件信息/n print_file_info(file_name, size_str, duration, video_info, audio_lang, ratio)/n/n最终的优化代码如下：/npython/nimport os/nimport re/nimport subprocess/nimport math/n/n# 视频格式/nsupported_formats = ['.mp4', '.avi', '.mkv', '.wmv', '.mov', '.flv', '.m2ts', '.ts', '.rm', '.rmvb',/n '.vob', '.3gp', '.webm', '.hdmov', '.mp4v', '.mpv4', '.divx', '.xvid', '.f4v',/n '.mpeg', '.asf', '.asx', '.m2t']/n# 正则表达式匹配码率数据中的空格/npattern = re.compile(r'(/d+)/s+(/d+)')/n/ndef format_size(size):/n if size < 1024:/n return f'{size} B'/n elif size < 1024 * 1024:/n return f'{size / 1024:.2f} KiB'/n elif size < 1024 * 1024 * 1024:/n return f'{size / 1024 / 1024:.2f} MiB'/n else:/n return f'{size / 1024 / 1024 / 1024:.2f} GiB'/n/ndef parse_output(output):/n return output.split('|')/n/ndef parse_audio_info(audio_info):/n audio_bitrate = []/n audio_sampling_rate = []/n audio_lang = []/n for i in range(len(audio_info) // 3):/n audio_bitrate.append(audio_info[i * 3])/n audio_sampling_rate.append(audio_info[i * 3 + 1])/n audio_lang.append(audio_info[i * 3 + 2])/n return audio_bitrate, audio_sampling_rate, audio_lang/n/ndef get_framerate(video_info):/n try:/n return float(video_info[3])/n except ValueError:/n return None/n/ndef print_file_info(file_name, size_str, duration, video_info, audio_lang, ratio):/n bitrate = re.sub(pattern, r'/1/2', video_info[2])/n framerate = get_framerate(video_info)/n print(f'{file_name}, {size_str}, {duration}, {video_info[1]}, {bitrate}, {framerate}, {' / '.join(audio_lang)}, {ratio}')/n/ndef process_video_files(video_folder):/n # 获取视频文件列表（包括子目录）/n video_files = [os.path.join(root, file) for root, dirs, files in os.walk(video_folder) for file in files if any(file.endswith(format) for format in supported_formats)]/n # 遍历所有视频文件/n for video_file in video_files:/n # 获取文件名/n file_name = os.path.basename(video_file)/n/n # 获取文件大小并进行单位换算/n size = os.path.getsize(video_file)/n size_str = format_size(size)/n/n # 使用mediainfo获取视频信息 / 音频信息/n video_process = subprocess.Popen(['mediainfo', '--Inform=Video;%Format%|%Width%x%Height%|%BitRate/String%|%FrameRate%|%Duration/String3%', video_file], stdout=subprocess.PIPE)/n audio_process = subprocess.Popen(['mediainfo', '--Inform=Audio;%BitRate/String%|%SamplingRate/String%|%Language/String%', video_file], stdout=subprocess.PIPE)/n video_output, _ = video_process.communicate()/n audio_output, _ = audio_process.communicate()/n video_output = video_output.decode().strip()/n audio_output = audio_output.decode().strip()/n/n # 解析输出结果/n video_info = parse_output(video_output)/n audio_info = parse_output(audio_output)/n/n # 处理多音轨情况/n audio_bitrate, audio_sampling_rate, audio_lang = parse_audio_info(audio_info)/n/n # 时长取整/n duration = video_info[4].split('.')[0]/n h, m, s = duration.split(':')/n duration = f'{h}:{m}:{str(s).zfill(2)}'/n/n # 以分钟计算的时长/n duration_minutes = int(h) * 60 + int(m) + math.ceil(float(s)) / 60/n/n # 计算压缩比率/n ratio = round(duration_minutes / size * 1000000000, 2)/n/n # 打印文件信息/n print_file_info(file_name, size_str, duration, video_info, audio_lang, ratio)/n/nprocess_video_files('/home/115/up')/n