Hit all URLs in a sitemap and report any non-200 responses

sitemaperrors.py

import requests, re

# PUT YOUR SITEMAP URL RIGHT HERE PLEASE
SITEMAP_URL = "https://www.example.com/sitemap.xml"
# REPORT BACK EVERY X URLS DOWNLOADED
REPORT_EVERY = 100

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:100.0) Gecko/20100101 Firefox/100.0",
}

print("Getting %s" % (SITEMAP_URL))
sitemap_text = requests.get(SITEMAP_URL, headers=headers).text
urls = re.findall("<loc>(.*?)</loc>", sitemap_text)
number_of_urls = len(urls)
print("Checking URLs...")

url_number = 0
for url in urls: 
    request = requests.get(url, headers=headers)
    if request.status_code != 200:
        print("ERROR %s %s" % (str(request.status_code), url))
    if url_number % REPORT_EVERY == 0:
        print("Checked %s of %s URLs" % (url_number, number_of_urls))
    url_number += 1