Python实现生成指定大小文件的示例详解

import os
import time
import csv
from PIL import Image
import random
import numpy as np
import imageio
import cv2
# pip install opencv-python
# pip install Pillow
def generate_txt(file_size):
    file_size_bytes = 1024 * 1024 * file_size
    file_path = './data/txt' + time.strftime('%Y%m%d') + '_' + str(file_size) + 'M.txt'
    text = "Women only affect the speed at which I type Pythong code."  # 要重复的文本
    text_size_bytes = len(text.encode('utf-8'))  # 每个重复的文本的大小（以字节为单位）
    repetitions = file_size_bytes // text_size_bytes  # 需要重复的次数
    remainder = file_size_bytes % text_size_bytes  # 剩余的字节数
    with open(file_path, 'w') as file:
        for _ in range(repetitions):
            file.write(text)
        if remainder > 0:
            file.write(text[:remainder])
    print("生成完成")
def generate_video(target_filesize_mb,  frame_width=1920, frame_height=1080, frame_rate=30):
    temp_filename = './data/image' + time.strftime('%Y%m%d') + '_' + str(target_filesize_mb) + 'M.mp4'
    fourcc = cv2.VideoWriter_fourcc(*"mp4v")
    out = cv2.VideoWriter(temp_filename, fourcc, frame_rate, (frame_width, frame_height))
    while True:
        frame = np.random.randint(0, 256, (frame_height, frame_width, 3), dtype=np.uint8)
        out.write(frame)
        current_filesize = (len(open(temp_filename, "rb").read())) / (1024 * 1024)  # in MB
        if current_filesize >= target_filesize_mb:
            break
    out.release()
def generate_image(memory_size, filename):
    """
    :param memory_size: 生成图片的大小，单位是m
    :param filename: 生成图片的文件格式
    :return:
    """
    filename = './data/image'+ time.strftime('%Y%m%d') +'_'+ str(memory_size) + 'M' '.'+filename
    # 计算所需的像素数量
    num_pixels = (memory_size * 1024 * 1024) // 3  # 每个像素占用 3 个字节（RGB模式）
    # 根据像素数量计算图片的长和宽
    img_width = int(np.sqrt(num_pixels))
    img_height = int(num_pixels / img_width)
    # 创建一个随机颜色的数组
    pixels = np.random.randint(0, 256, (img_height, img_width, 3), dtype=np.uint8)
    # 根据数组创建图片对象
    image = Image.fromarray(pixels, 'RGB')
    image.save(filename)
def generate_csv(target_memory_mb):
    file_name = './data/csv_utf8 ' + time.strftime('%Y%m%d') +"_"+ str(target_memory_mb) + 'M.csv'
    row_data = "Data" * 100  # Adjust length to control memory usage per row
    with open(file_name, 'w', newline='', encoding='utf-8') as csv_file:
        writer = csv.writer(csv_file)
        while os.path.getsize(file_name) / (1024 * 1024) < target_memory_mb:
            writer.writerow([row_data])
if __name__ == '__main__':
    # 生成一个大小为2MB的TXT文件
    generate_txt(2)
    # 生成15M视频
    generate_video(target_filesize_mb=15)
    # 生成一个10M 的png的图片
    generate_image(10, "png")
    # 以utf-8的格式，生成一个10M的csv文件  CSV 文件的大小通常由数据量和内容决定，而不是像 Excel 那样可以直接控制行高和列宽。CSV 文件的大小可能会受到编码和分隔符的影响
    generate_csv(target_memory_mb=10)  # Change target memory size as needed

import os
#创建一个1GB大小的文件
file_name = "test.txt"
with open(file_name, 'w') as f:
    f.write(" " * 1024)  # 写入1KB的空数据
    f.seek(1024 * 1024 * 1024)  # 定位到文件末尾
    f.write("EOF")
    f.truncate()  # 设置文件大小

import subprocess
# 创建一个1GB大小的文件
file_name = "test.txt"
subprocess.run(['fallocate', '-l', '1G', file_name])

import subprocess
#创建一个1GB大小的文件
file_name = "test.txt"
subprocess.run(['dd', 'if=/dev/zero', 'of=' + file_name, 'bs=1M', 'count=1024'])