Last active
May 23, 2023 19:41
-
-
Save joaovarelas/42fc3f134cce986cc40825ef79e64425 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from faker import Faker | |
import random | |
import string | |
import concurrent.futures | |
extensions = { | |
'pdf': b'\x25\x50\x44\x46\x2D\x31\x2E', | |
'jpg': b'\xFF\xD8\xFF\xE0\x00\x10\x4A\x46\x49\x46\x00\x01', | |
'png': b'\x89PNG\r\n\x1a\n\x00\x00\x00\rIHDR\x00\x00\x00\x01\x00\x00\x00\x01\x08', | |
'zip': b'\x50\x4B\x03\x04', | |
#'tar': b'\x75\x73\x74\x61\x72\x00\x30\x30', | |
'tar': b'\x1F\x8B', | |
'doc': b'\xD0\xCF\x11\xE0\xA1\xB1\x1A\xE1', | |
'docx': b'\x50\x4B\x03\x04\x14\x00\x06\x00', | |
} | |
fake = Faker() | |
def generate_fake_filename(ext): | |
filename = fake.file_name(extension=ext) # Adjust category as needed | |
return f'{filename}' | |
def generate_random_content(extension): | |
min_size = 5 * 1024 # 5 KB | |
max_size = int(1.2 * 1024 * 1024) # 1.2 MB | |
content_size = random.randint(min_size, max_size) | |
signature = extensions[extension] | |
remaining_size = content_size - len(signature) | |
#content = signature + bytes(random.randint(0, 255) for _ in range(remaining_size)) | |
content = signature + bytes(random.getrandbits(8) for _ in range(remaining_size)) | |
return content | |
def generate(): | |
print("Starting generate() worker...") | |
# Generate and write files with random content | |
extension = random.choice(list(extensions.keys())) | |
filename = generate_fake_filename(extension) | |
content = generate_random_content(extension) | |
with open(filename, 'wb') as file: | |
file.write(content) | |
# Generate 100 files with random bytes (magic bytes should match extension) | |
with concurrent.futures.ThreadPoolExecutor(max_workers=64) as executor: | |
n_files = 100 | |
futures = [executor.submit(generate, ) for _ in range(n_files)] | |
# Wait for all tasks to complete | |
for future in concurrent.futures.as_completed(futures): | |
result = future.result() | |
#print(f"Result: {result}") | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment