AWS Lambda function to check RSS feed validity using W3C's API

serverless_rss_validity.py

import json
import requests
import os
import sys
from xml.dom.minidom import parse, parseString

hostnames = ["react.statuscode.com", "javascriptweekly.com", "nodeweekly.com"]

def checkValidity(url):
    response = requests.get(url)
    dom = parseString(response.text)
    el = dom.getElementsByTagName("m:validity")[0]
    valid = el.firstChild.data
    return valid == 'true'

def postSlackMessage(message, channel='#experiments'):
    slack_data = {'text': message, 'channel': channel}
    response = requests.post(
        os.environ['SLACK_URL'], data=json.dumps(slack_data),
        headers={'Content-Type': 'application/json'}
    )

def lambda_handler(event, context):
    for hostname in hostnames:
        url = f"https://validator.w3.org/feed/check.cgi?url=https%3A%2F%2F{hostname}%2Frss&output=soap12"
        if checkValidity(url):
            postSlackMessage(f":white_check_mark: {hostname} has valid RSS")
        else:
            postSlackMessage(f":x: {hostname} has INVALID RSS", "#editorial")

# Run lambda function locally for test purposes
if len(sys.argv) > 1 and sys.argv[1] == 'test':
    lambda_handler(None, None)

If you want to use this code, you'd need to make a few minor changes, but it should be pretty straight forward. Perhaps change the "hostnames" array to be raw URLs. Also note the SLACK_URL env variable.

Worked out that running this every 5 minutes would cost about $0.08 a month in AWS Lambda fees and bandwidth.

ES6 version for comparison at https://gist.github.com/peterc/a7d63960ca6dcf165477b310d0d08afb