Python Utility Scripts for Data Cleaning, Translation, File Sync, Cloud Backup, and More

CSV File Data Cleaning Tool

import csv

def clean_csv(input_file, output_file):
    with open(input_file, mode='r', newline='', encoding='utf-8') as infile, \
         open(output_file, mode='w', newline='', encoding='utf-8') as outfile:
        reader = csv.reader(infile)
        writer = csv.writer(outfile)
        for row in reader:
            # Clean data, e.g., strip whitespace
            cleaned_row = [cell.strip() for cell in row]
            writer.writerow(cleaned_row)

input_file = '/path/to/input.csv'
output_file = '/path/to/cleaned_output.csv'
clean_csv(input_file, output_file)

Text File Translation Tool

from deep_translator import GoogleTranslator

def translate_text(input_file, output_file, target_language):
    with open(input_file, 'r', encoding='utf-8') as file:
        text = file.read()
    translated_text = GoogleTranslator(source='auto', target=target_language).translate(text)
    with open(output_file, 'w', encoding='utf-8') as file:
        file.write(translated_text)

input_file = '/path/to/your/text.txt'
output_file = '/path/to/translated_text.txt'
target_language = 'es'  # Spanish
translate_text(input_file, output_file, target_language)

Folder Synchronization Tool

import shutil
import os

def sync_folders(src_folder, dst_folder):
    for item in os.listdir(src_folder):
        s = os.path.join(src_folder, item)
        d = os.path.join(dst_folder, item)
        if os.path.isdir(s):
            shutil.copytree(s, d, dirs_exist_ok=True)
        else:
            shutil.copy2(s, d)

src_folder = '/path/to/source/folder'
dst_folder = '/path/to/destination/folder'
sync_folders(src_folder, dst_folder)

Data Backup to Cloud Storage Service (AWS S3)

import boto3

def upload_to_s3(bucket_name, local_file_path, remote_file_path):
    s3 = boto3.client('s3')
    s3.upload_file(local_file_path, bucket_name, remote_file_path)

bucket_name = 'your-bucket-name'
local_file_path = '/path/to/your/local/file'
remote_file_path = 'path/to/remote/file'
upload_to_s3(bucket_name, local_file_path, remote_file_path)

Folder Content Statistics Tool

import os

def count_files_and_dirs(directory):
    total_files = 0
    total_dirs = 0
    for root, dirs, files in os.walk(directory):
        total_files += len(files)
        total_dirs += len(dirs)
    return total_files, total_dirs

directory = '/path/to/your/directory'
files, dirs = count_files_and_dirs(directory)
print(f"Total files: {files}, Total directories: {dirs}")

File Type Classification Tool

import os

def classify_files_by_type(directory):
    file_types = {}
    for filename in os.listdir(directory):
        if os.path.isfile(os.path.join(directory, filename)):
            extension = os.path.splitext(filename)[1]
            if extension in file_types:
                file_types[extension] += 1
            else:
                file_types[extension] = 1
    return file_types

directory = '/path/to/your/directory'
file_types = classify_files_by_type(directory)
for ext, count in file_types.items():
    print(f"Files with extension '{ext}': {count}")

Image Recognition Tag Generation (OCR)

from PIL import Image
from pytesseract import pytesseract

def image_to_text(image_path):
    img = Image.open(image_path)
    text = pytesseract.image_to_string(img)
    return text

image_path = '/path/to/your/image.png'
text = image_to_text(image_path)
print(f"Text from image: {text}")

Video to Audio Conversion Tool

from moviepy.editor import VideoFileClip

def convert_video_to_audio(video_path, audio_path):
    clip = VideoFileClip(video_path)
    clip.audio.write_audiofile(audio_path)

video_path = '/path/to/your/video.mp4'
audio_path = '/path/to/converted/audio.mp3'
convert_video_to_audio(video_path, audio_path)

Extract Images from Webpage

import requests
from bs4 import BeautifulSoup
import os

def extract_images_from_webpage(url, output_dir):
    response = requests.get(url)
    soup = BeautifulSoup(response.text, 'html.parser')
    images = soup.find_all('img')
    os.makedirs(output_dir, exist_ok=True)
    for image in images:
        src = image.get('src')
        if src and src.startswith('http'):
            image_data = requests.get(src).content
            filename = os.path.join(output_dir, os.path.basename(src))
            with open(filename, 'wb') as f:
                f.write(image_data)

url = 'https://example.com'
output_dir = '/path/to/output/images'
extract_images_from_webpage(url, output_dir)

Text Summarization Tool

from transformers import pipeline

def generate_summary(text):
    summarizer = pipeline("summarization")
    summary = summarizer(text, max_length=130, min_length=30, do_sample=False)
    return summary[0]['summary_text']

text = """Lorem ipsum dolor sit amet, consectetur adipiscing elit. 
Sed non risus. Suspendisse lectus tortor, dignissim sit amet, adipiscing nec, ultricies sed, dolor."""
summary = generate_summary(text)
print(f"Summary: {summary}")