From 03bb1280050e6fcb09405c8848cb58ec7807f8d9 Mon Sep 17 00:00:00 2001
From: Andrew Kvalheim <Andrew@Kvalhe.im>
Date: Thu, 14 Jul 2022 09:41:33 -0700
Subject: [PATCH] Key entries by link if missing ID
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Resolves the problem of incorrectly duplicated entries in feeds that
update content but don’t explicitly provide entry IDs. Example feed:

  - https://www.to-rss.xyz/wikipedia/current_events/

Example entry:

    <item>
      <title>Current events: 2022-07-13</title>
      <link>https://en.wikipedia.org/wiki/Portal:Current_events/2022_July_13</link>
      <description>[VARIABLE CONTENT]</description>
      <pubDate>Wed, 13 Jul 2022 00:00:00 -0000</pubDate>
      </item>
    <item>

This behavior is suggested by the common practice of using an entry’s
link as its ID value, and is consistent with typical feed aggregators
such as Feedbin and Inoreader.
---
 rss/bot.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/rss/bot.py b/rss/bot.py
index 0352f4c..42ca897 100644
--- a/rss/bot.py
+++ b/rss/bot.py
@@ -279,12 +279,12 @@ class RSSBot(Plugin):
             feed_id=feed_id,
             id=(
                 getattr(entry, "id", None)
+                or getattr(entry, "link", None)
                 or hashlib.sha1(
                     " ".join(
                         [
                             getattr(entry, "title", ""),
                             getattr(entry, "description", ""),
-                            getattr(entry, "link", ""),
                         ]
                     ).encode("utf-8")
                 ).hexdigest()