Python 代码：检查并提取两个文件夹中的重复视频

下面是一个检查并提取两个文件夹内部所有重复视频的 Python 代码：

import os
import hashlib
import shutil

def get_file_hash(file_path):
    # 计算文件的哈希值
    with open(file_path, 'rb') as f:
        data = f.read()
        file_hash = hashlib.md5(data).hexdigest()
    return file_hash

def find_duplicate_videos(folder1, folder2):
    # 获取文件夹内所有视频文件的哈希值
    folder1_videos = {}
    for root, dirs, files in os.walk(folder1):
        for file in files:
            if file.lower().endswith(('.mp4', '.avi', '.mov', '.mkv')):
                file_path = os.path.join(root, file)
                file_hash = get_file_hash(file_path)
                folder1_videos[file_hash] = file_path

    # 检查第二个文件夹内的视频是否与第一个文件夹内的视频重复
    duplicate_videos = []
    for root, dirs, files in os.walk(folder2):
        for file in files:
            if file.lower().endswith(('.mp4', '.avi', '.mov', '.mkv')):
                file_path = os.path.join(root, file)
                file_hash = get_file_hash(file_path)
                if file_hash in folder1_videos:
                    duplicate_videos.append(file_path)

    return duplicate_videos

def extract_duplicate_videos(duplicate_videos, output_folder):
    # 将重复视频提取到单独的文件夹内
    if not os.path.exists(output_folder):
        os.makedirs(output_folder)

    for file_path in duplicate_videos:
        file_name = os.path.basename(file_path)
        output_path = os.path.join(output_folder, file_name)
        shutil.copy2(file_path, output_path)

# 示例用法
folder1 = 'path/to/folder1'
folder2 = 'path/to/folder2'
output_folder = 'path/to/output_folder'

duplicate_videos = find_duplicate_videos(folder1, folder2)
extract_duplicate_videos(duplicate_videos, output_folder)

请将 folder1 和 folder2 替换为你要检查的两个文件夹路径，将 output_folder 替换为提取重复视频的输出文件夹路径。