From 04280d1b9bf6c7324ceb95cef4ac269268ebc880 Mon Sep 17 00:00:00 2001
From: yequari <yequari@32bit.cafe>
Date: Thu, 14 Sep 2023 22:17:57 -0700
Subject: [PATCH] add logging and cli arguments

---
 rss.py | 65 ++++++++++++++++++++++++++++++++++++++--------------------
 1 file changed, 43 insertions(+), 22 deletions(-)

diff --git a/rss.py b/rss.py
index 5d94819..e296648 100644
--- a/rss.py
+++ b/rss.py
@@ -1,11 +1,19 @@
 import os
+import argparse
+import logging
 import xml.etree.ElementTree as ET
 import requests
 from datetime import datetime, timezone
 
-FEED = 'https://discuss.32bit.cafe/all/new.atom'
-FILENAME = os.path.basename(FEED)
-WEBHOOK = 'https://discord.com/api/webhooks/1152044037017186417/igGNMxiVhLSW9y4kL8cs7y6m0AutxqXHxMTWSXWN0jbCUnsxLT_er8pqWQKoAjGpPywg'
+LOGGER = logging.getLogger(__name__)
+LOGGER.setLevel(logging.INFO)
+
+ch = logging.StreamHandler()
+ch.setLevel(logging.INFO)
+formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
+ch.setFormatter(formatter)
+
+LOGGER.addHandler(ch)
 
 
 def tag(tagname: str) -> str:
@@ -21,46 +29,45 @@ class Entry:
         self.date = datetime.fromisoformat(entry.find(tag('published')).text)
 
     def __str__(self):
-        return f'{self.title} by {self.author} at {self.date} \n {self.url}'
+        return f'New post by {self.author}: {self.title}\n{self.url}'
 
 
-def get_last_update_time():
+def get_last_update_time(file: str) -> datetime:
     try:
-        stat = os.stat(FILENAME)
+        stat = os.stat(file)
         return datetime.fromtimestamp(stat.st_mtime,
                                       datetime.now().astimezone().tzinfo)
     except FileNotFoundError:
         return datetime.now(timezone.utc)
 
 
-def update_rss_file():
-    r = requests.get(FEED, stream=True)
-    with open(FILENAME, 'w') as fd:
+def update_rss_file(file, feed):
+    r = requests.get(feed, stream=True)
+    with open(file, 'w') as fd:
         for chunk in r.iter_content(chunk_size=1024, decode_unicode=True):
             fd.write(chunk)
 
 
-def parse_rss_file():
-    tree = ET.parse(FILENAME)
+def parse_rss_file(file) -> ET.Element:
+    tree = ET.parse(file)
     return tree.getroot()
 
 
-def get_new_posts(time, root):
+def get_new_posts(time, root) -> list[Entry]:
     posts = []
     for entry in root.findall(tag('entry')):
         e = Entry(entry)
-        print(e.date)
         if e.date > time:
             posts.append(e)
     return posts
 
 
-def send_message(entry):
+def send_message(entry, url) -> int:
     obj = {
             'content': str(entry)
             }
-    r = requests.post(WEBHOOK, obj)
-    print(r.status_code)
+    r = requests.post(url, obj)
+    return r.status_code
 
 # Check last mod date of current rss file
 # Download new version of file
@@ -69,11 +76,25 @@ def send_message(entry):
 
 
 if __name__ == "__main__":
-    last_updated = get_last_update_time()
-    print(last_updated)
-    update_rss_file()
-    root = parse_rss_file()
+    parser = argparse.ArgumentParser(
+            prog='discussfeed',
+            description='Checks for new entries from an atom feed and sends them to a discord webhook')
+    parser.add_argument('-w', '--webhook')
+    parser.add_argument('feed_url')
+    args = parser.parse_args()
+
+    filename = os.path.basename(args.feed_url)
+    last_updated = get_last_update_time(filename)
+    LOGGER.info(f'last updated: {last_updated}')
+
+    update_rss_file(filename, args.feed_url)
+    root = parse_rss_file(filename)
     posts = get_new_posts(last_updated, root)
-    print(posts)
+    LOGGER.info(f'found {len(posts)} new posts')
+
     for post in posts:
-        send_message(post)
+        status = send_message(post, args.webhook)
+        if status >= 300:
+            LOGGER.error(f'Response code {status}')
+        else:
+            LOGGER.info(f'response code {status}')