A quick Python script to filter all URL, domain and domain suffixes from HAR file.

main.py

import json
from urllib.parse import urlparse
import tldextract


def extract_urls(har_file_path, url_file_path, domain_txt_file_path, suffix_txt_file_path):
    with open(har_file_path, 'r', encoding='utf-8') as f:
        har_data = json.load(f)

    urls = []
    domains = set()
    second_domains = set()
    for entry in har_data['log']['entries']:
        url = entry['request']['url']
        urls.append(url)
        domain = urlparse(url).netloc
        domains.add(domain)
        second_domain_extract = tldextract.extract(url)
        second_domain = '.'.join(part for part in second_domain_extract[1:] if part)
        second_domains.add(second_domain)

    with open(url_file_path, 'w', encoding='utf-8') as f:
        for url in urls:
            f.write(url + '\n')

    with open(domain_txt_file_path, 'w', encoding='utf-8') as f:
        for domain in domains:
            f.write(domain + '\n')

    with open(suffix_txt_file_path, 'w', encoding='utf-8') as f:
        for second_domain in second_domains:
            f.write(second_domain + '\n')


# replace the path/to/your/har/file.har with the path to your HAR file
extract_urls("path/to/your/har/file.har", "urls.txt", "domains.txt", "domain-suffixes.txt")