Mobile proxies for Google Ads

import csv
import time
from urllib.parse import urlparse

import requests

PROXY = "http://LOGIN:PASSWORD@HOST:PORT"
LANDINGS_FILE = "landings.txt"
REPORT_FILE = "landings_report.csv"
MAX_REDIRECTS = 3
MAX_SECONDS = 4.0
HEADERS = {
    "User-Agent": "Mozilla/5.0 (Linux; Android 14; Pixel 8) AppleWebKit/537.36 "
    "(KHTML, like Gecko) Chrome/126.0 Mobile Safari/537.36"
}

proxies = {"http": PROXY, "https": PROXY}


def site(url):
    host = urlparse(url).hostname or ""
    return host[4:] if host.startswith("www.") else host


def inspect(url):
    started = time.time()
    try:
        response = requests.get(url, headers=HEADERS, proxies=proxies, timeout=30)
    except requests.RequestException as error:
        return {"url": url, "status": "error", "final_url": "", "redirects": 0, "seconds": "", "issues": type(error).__name__}

    seconds = round(time.time() - started, 2)
    issues = []
    if response.status_code != 200:
        issues.append(f"status {response.status_code}")
    if len(response.history) > MAX_REDIRECTS:
        issues.append(f"{len(response.history)} redirects")
    if site(response.url) != site(url):
        issues.append("final domain differs from the ad URL")
    if seconds > MAX_SECONDS:
        issues.append(f"slow: {seconds} s")
    return {
        "url": url,
        "status": response.status_code,
        "final_url": response.url,
        "redirects": len(response.history),
        "seconds": seconds,
        "issues": "; ".join(issues),
    }


def main():
    with open(LANDINGS_FILE) as f:
        urls = [line.strip() for line in f if line.strip()]

    if not urls:
        raise SystemExit(f"{LANDINGS_FILE} is empty")
    rows = [inspect(url) for url in urls]
    with open(REPORT_FILE, "w", newline="") as f:
        writer = csv.DictWriter(f, fieldnames=list(rows[0].keys()))
        writer.writeheader()
        writer.writerows(rows)

    broken = [row for row in rows if row["issues"]]
    for row in broken:
        print(f"{row['url']}  ->  {row['issues']}")
    print(f"checked {len(rows)} landing pages, {len(broken)} need attention")
    raise SystemExit(1 if broken else 0)


if __name__ == "__main__":
    main()