From f69fe236e09bd3d34975335b091142804001b4ab Mon Sep 17 00:00:00 2001
From: Cody Hiar <cody@hiar.ca>
Date: Mon, 13 Mar 2023 10:44:49 -0600
Subject: Initial commit

---
 check_links.py | 41 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 41 insertions(+)
 create mode 100644 check_links.py

(limited to 'check_links.py')

diff --git a/check_links.py b/check_links.py
new file mode 100644
index 0000000..46feb0f
--- /dev/null
+++ b/check_links.py
@@ -0,0 +1,41 @@
+import asyncio
+
+import aiohttp
+import markdown
+from bs4 import BeautifulSoup
+
+with open("README.md") as f:
+    body_markdown = f.read()
+html_page = markdown.markdown(body_markdown)
+
+
+print("Gathering links...")
+urls = []
+soup = BeautifulSoup(html_page, features="lxml")
+for link in soup.findAll("a"):
+    urls.append(link.get("href"))
+
+
+async def get_url_response(session, url):
+    try:
+        async with session.get(url) as resp:
+            return (resp.status, url)
+    except Exception:
+        return (000, url)
+
+
+async def main():
+    timeout = aiohttp.ClientTimeout(total=20)
+    async with aiohttp.ClientSession(timeout=timeout) as session:
+        tasks = []
+        for url in urls:
+            tasks.append(asyncio.ensure_future(get_url_response(session, url)))
+
+        print("Checking links...")
+        responses = await asyncio.gather(*tasks)
+        for _, (resp, url) in enumerate(responses):
+            if resp != 200:
+                print(resp, url)
+
+loop = asyncio.get_event_loop()
+loop.run_until_complete(main())
-- 
cgit v1.2.3