☰

如何查找和删除重复的视频（.mp4）文件？

tag-icon • tag-icon linux files find video file-comparison
如何查找和删除重复的视频（.mp4）文件？

我有 16,000 多个短视频剪辑，其中有很多与人眼完全相同，但如果您仔细检查，您会发现其中一个或另一个可能有额外的 1 秒（或更短）的持续时间开始或结束。

我已经尝试了几种方法，但查找重复项的成功率为零。您可能会认为比较确切的字节大小就足够了，因为字节是如此之小。但不是！之所以不这样做是因为视频剪辑的开头或结尾可能会有轻微的额外（或非额外）几毫秒。这导致它们不同且不相同，导致任何使用“逐字节比较”的重复查找器结果都不会出现重复结果。

尽管大部分视频剪辑与其他几个视频剪辑完全相同，但我没有使用任何方法来查找任何重复项，因为比较的 .mp4 文件的开头或结尾处存在几毫秒的差异。

有谁知道我如何成功找到这些短视频剪辑 .mp4 文件的重复项？平均而言，每个时间大约为 30 秒，但与其他时间相比，只有几毫秒的差异。对于人眼来说，这将是完全相同的，因此我看到了重复的内容，但我不想自己观看和比较 16,000 多个视频剪辑。

有什么建议么？

我找到了一个很好的答案来回答我的问题，你能允许我回答吗？

……好像搁置后我不能……

答案1

我也遇到了同样的问题，所以我写了一个程序。

问题是我有各种格式和分辨率的视频，因此我需要对每个视频帧进行哈希并进行比较。

您只需更改顶部的目录即可。

from os import path, walk, makedirs, rename
from time import clock
from imagehash import average_hash
from PIL import Image
from cv2 import VideoCapture, CAP_PROP_FRAME_COUNT, CAP_PROP_FRAME_WIDTH, CAP_PROP_FRAME_HEIGHT, CAP_PROP_FPS
from json import dump, load
from multiprocessing import Pool, cpu_count

input_vid_dir = r'C:\Users\gokul\Documents\data\\'
json_dir = r'C:\Users\gokul\Documents\db\\'
analyzed_dir = r'C:\Users\gokul\Documents\analyzed\\'
duplicate_dir = r'C:\Users\gokul\Documents\duplicate\\'

if not path.exists(json_dir):
    makedirs(json_dir)

if not path.exists(analyzed_dir):
    makedirs(analyzed_dir)

if not path.exists(duplicate_dir):
    makedirs(duplicate_dir)


def write_to_json(filename, data):
    file_full_path = json_dir + filename + ".json"
    with open(file_full_path, 'w') as file_pointer:
        dump(data, file_pointer)
    return


def video_to_json(filename):
    file_full_path = input_vid_dir + filename
    start = clock()
    size = round(path.getsize(file_full_path) / 1024 / 1024, 2)
    video_pointer = VideoCapture(file_full_path)
    frame_count = int(VideoCapture.get(video_pointer, int(CAP_PROP_FRAME_COUNT)))
    width = int(VideoCapture.get(video_pointer, int(CAP_PROP_FRAME_WIDTH)))
    height = int(VideoCapture.get(video_pointer, int(CAP_PROP_FRAME_HEIGHT)))
    fps = int(VideoCapture.get(video_pointer, int(CAP_PROP_FPS)))
    success, image = video_pointer.read()
    video_hash = {}
    while success:
        frame_hash = average_hash(Image.fromarray(image))
        video_hash[str(frame_hash)] = filename
        success, image = video_pointer.read()
    stop = clock()
    time_taken = stop - start
    print("Time taken for ", file_full_path, " is : ", time_taken)
    data_dict = dict()
    data_dict['size'] = size
    data_dict['time_taken'] = time_taken
    data_dict['fps'] = fps
    data_dict['height'] = height
    data_dict['width'] = width
    data_dict['frame_count'] = frame_count
    data_dict['filename'] = filename
    data_dict['video_hash'] = video_hash
    write_to_json(filename, data_dict)
    return


def multiprocess_video_to_json():
    files = next(walk(input_vid_dir))[2]
    processes = cpu_count()
    print(processes)
    pool = Pool(processes)
    start = clock()
    pool.starmap_async(video_to_json, zip(files))
    pool.close()
    pool.join()
    stop = clock()
    print("Time Taken : ", stop - start)


def key_with_max_val(d):
    max_value = 0
    required_key = ""
    for k in d:
        if d[k] > max_value:
            max_value = d[k]
            required_key = k
    return required_key


def duplicate_analyzer():
    files = next(walk(json_dir))[2]
    data_dict = {}
    for file in files:
        filename = json_dir + file
        with open(filename) as f:
            data = load(f)
        video_hash = data['video_hash']
        count = 0
        duplicate_file_dict = dict()
        for key in video_hash:
            count += 1
            if key in data_dict:
                if data_dict[key] in duplicate_file_dict:
                    duplicate_file_dict[data_dict[key]] = duplicate_file_dict[data_dict[key]] + 1
                else:
                    duplicate_file_dict[data_dict[key]] = 1
            else:
                data_dict[key] = video_hash[key]
        if duplicate_file_dict:
            duplicate_file = key_with_max_val(duplicate_file_dict)
            duplicate_percentage = ((duplicate_file_dict[duplicate_file] / count) * 100)
            if duplicate_percentage > 50:
                file = file[:-5]
                print(file, " is dup of ", duplicate_file)
                src = analyzed_dir + file
                tgt = duplicate_dir + file
                if path.exists(src):
                    rename(src, tgt)
                # else:
                #     print("File already moved")


def mv_analyzed_file():
    files = next(walk(json_dir))[2]
    for filename in files:
        filename = filename[:-5]
        src = input_vid_dir + filename
        tgt = analyzed_dir + filename
        if path.exists(src):
            rename(src, tgt)
        # else:
        #     print("File already moved")


if __name__ == '__main__':
    mv_analyzed_file()
    multiprocess_video_to_json()
    mv_analyzed_file()
    duplicate_analyzer()

相关内容