Last active
August 31, 2020 23:22
-
-
Save zstix/cb29c4ac16a7c2b5e3bb85c76a019294 to your computer and use it in GitHub Desktop.
A quick script to ping all of the site on a sitemap and check status codes
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
defmodule Crawl do | |
def process_resp({:ok, %{body: xml}}) do | |
XmlToMap.naive_map(xml) | |
end | |
def get_urls(xml) do | |
xml | |
|> Map.get("urlset") | |
|> Map.get("url") | |
|> Enum.map(&Map.get(&1, "loc")) | |
end | |
def update_url(url) do | |
url | |
|> String.replace("https://developer.newrelic.com", "localhost:8000") | |
|> Kernel.<>("/") | |
end | |
def get_page_status(url) do | |
url | |
|> HTTPoison.get() | |
|> case do | |
{:ok, %{status_code: code}} -> {code, url} | |
_ -> {:error, url} | |
end | |
end | |
def run do | |
"http://localhost:8000/sitemap.xml" | |
|> HTTPoison.get() | |
|> process_resp() | |
|> get_urls() | |
|> Enum.map(&update_url/1) | |
|> Enum.take(5) # For testing, just try the first 5 | |
|> Task.async_stream(&get_page_status/1, max_concurrency: 5) | |
|> Enum.map(fn {:ok, result} -> result end) | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment