Python script to check URLs for 404 errors with CSV export

check_urls_status.py

import requests
import csv
import time
from collections import Counter

# Settings
input_file = 'urls.txt'
output_file = 'result.csv'
timeout = 10  # Request timeout in seconds
delay = 0.5   # Delay between requests to avoid overloading servers

# Load URLs from file
with open(input_file, 'r', encoding='utf-8') as file:
    urls = [line.strip() for line in file if line.strip()]

print(f'Found {len(urls)} URLs to check.')

# URL checking
results = []
status_list = []

for index, url in enumerate(urls, start=1):
    try:
        response = requests.head(url, timeout=timeout, allow_redirects=True)
        status_code = response.status_code
        print(f'{index}. {url} - {status_code}')
    except requests.exceptions.RequestException as e:
        status_code = 'Error'
        print(f'{index}. {url} - Error: {e}')
    results.append((index, url, status_code))
    status_list.append(status_code)
    time.sleep(delay)

# Save results to CSV (tab-separated)
with open(output_file, 'w', newline='', encoding='utf-8') as csvfile:
    writer = csv.writer(csvfile, delimiter='\t')
    writer.writerow(['No', 'URL', 'Status'])
    writer.writerows(results)

# Calculate statistics
counter = Counter(status_list)

print('\n===== SUMMARY =====')
print(f'Total checked: {len(urls)}')
for status, count in counter.items():
    print(f'Status {status}: {count}')
print(f'Results saved to {output_file}')