Check a URL using Selenium

selenium_check_url.py

#! /usr/bin/env python3
# Check a URL using headless Selenium
# Copyright (c) 2025 Sebastian Pipping <[email protected]>
#
# Licensed under GNU Affero General Public License v3.0 or later
# SPDX-License-Identifier: AGPL-3.0-or-later

import argparse
import json
import sys
from enum import Enum

from selenium import webdriver


# Tip: https://www.whatsmybrowser.org/
_DEFAULT_USER_AGENT = "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/134.0.0.0 Safari/537.36"


class PageLoadStrategy(Enum):
    EAGER = "eager"
    NONE = "none"
    NORMAL = "normal"


def run(config) -> int:
    service = webdriver.ChromeService(executable_path=config.chromedriver)

    options = webdriver.ChromeOptions()
    options.add_argument("--headless")
    options.add_argument(f"--user-agent={config.user_agent}")
    options.capabilities["goog:loggingPrefs"] = {"performance": "ALL"}
    options.page_load_strategy = config.page_load_strategy

    browser = webdriver.Chrome(options=options, service=service)

    browser.get(config.url)

    logs = browser.get_log("performance")

    responses = []
    for log in logs:
        message = json.loads(log["message"])["message"]
        if message["method"] == "Network.responseReceived":
            status_code = int(message["params"]["response"]["status"])
            url = message["params"]["response"]["url"]
            responses.append((url, status_code))

    browser.close()

    success = False

    if responses:
        if config.page_load_strategy == PageLoadStrategy.NONE.value:
            url, status_code = responses[0]
            print(f"{status_code} {url}")
        else:
            for i, (url, status_code) in enumerate(responses):
                print(f"{i + 1}. {status_code} {url}")

        success = 200 <= responses[0][1] < 300

    exit_code = 0 if success else 1

    return exit_code


if __name__ == "__main__":
    parser = argparse.ArgumentParser(
        description="Check a URL using headless Selenium",
    )
    parser.add_argument(
        "--page-load-strategy",
        choices={v.value for v in PageLoadStrategy},
        default=PageLoadStrategy.NONE.value,
        help='Selenium page load strategy (default: "%(default)s")',
    )
    parser.add_argument(
        "--chromedriver",
        metavar="PATH",
        default="/usr/bin/chromedriver",
        help='Path to chromedriver executable (default: "%(default)s")',
    )
    parser.add_argument(
        "--user-agent",
        metavar="STRING",
        default=_DEFAULT_USER_AGENT,
        help='User agent header value to use (default: "%(default)s")',
    )
    parser.add_argument("--version", action="version", version="%(prog)s 1.3.1")
    parser.add_argument("url", metavar="URL", help="URL to check")

    config = parser.parse_args()

    sys.exit(run(config))