Copied from arcadia

This commit is contained in:
2025-01-31 15:40:58 +03:00
commit 9428bf741d
5 changed files with 407 additions and 0 deletions

View File

@@ -0,0 +1,54 @@
import os
import requests
# Список URL для загрузки
file_urls = [
"https://example.com/file1.txt",
"https://example.com/file2.txt",
]
# Папка для сохранения файлов
download_folder = "downloads"
os.makedirs(download_folder, exist_ok=True)
# Функция для удаления строки 'payload:' и удаления дубликатов
def process_file(file_path):
with open(file_path, "r") as f:
lines = f.readlines()
# Удалить строки с "payload:" и убрать дубликаты
unique_lines = []
seen_lines = set()
for line in lines:
if "payload:" in line:
continue
if line not in seen_lines:
unique_lines.append(line)
seen_lines.add(line)
else:
unique_lines.append(f"# {line.strip()}\n") # Комментировать дубликат
# Записать обратно в файл
with open(file_path, "w") as f:
f.writelines(unique_lines)
# Скачивание файлов и обработка
for url in file_urls:
file_name = os.path.basename(url)
file_path = os.path.join(download_folder, file_name)
# Скачивание файла
print(f"Downloading {url}...")
response = requests.get(url)
if response.status_code == 200:
with open(file_path, "wb") as f:
f.write(response.content)
print(f"Saved to {file_path}")
# Обработка файла
print(f"Processing {file_path}...")
process_file(file_path)
else:
print(f"Failed to download {url} (Status Code: {response.status_code})")
print("All files processed.")