Switch from fastfeedparser to feedparser

Sadly fastfeedparser doesn't collect an id for each entry, and since an entry's link is optional, we don't always have enough info to create a new entry, since we need the entry id to create a valid Atom feed.

Author: kevinrenskers

example/uv.lock

@@ -1,6 +1,6 @@
 [project]
 name = "django-rss-filter"
-version = "0.1.0"
+version = "0.2.0"
 description = "Filter public RSS feeds, remove articles that contain certain keywords or categories."
 authors = [
     {name = "Kevin Renskers", email = "[email protected]"},
@@ -12,8 +12,8 @@ keywords = ["rss", "atom", "feed", "filter", "mute", "django"]
 requires-python = ">=3.9"
 dependencies = [
     "django>=3.2.0",
-    "fastfeedparser>=0.3.7",
     "feedgen>=1.0.0",
+    "feedparser>=6.0.11",
     "httpx>=0.28.1",
 ]
 
@@ -26,7 +26,7 @@ dev = [
 ]
 
 [project.urls]
-Homepage = "https://github.com/loopwerk/django-rss-filter/issues"
+Homepage = "https://github.com/loopwerk/django-rss-filter/"
 Repository = "https://github.com/loopwerk/django-rss-filter.git"
 Issues = "https://github.com/loopwerk/django-rss-filter/issues"
 

pyproject.toml

@@ -1,20 +1,20 @@
-import fastfeedparser
+import feedparser
 from feedgen.feed import FeedGenerator
 
 
 def validate_feed(feed_url: str) -> bool:
     try:
-        fastfeedparser.parse(feed_url)
+        feedparser.parse(feed_url)
         return True
     except ValueError:
         return False
 
 
 def filter_feed(feed_body: str, filtered_words: str, filtered_categories: str) -> str:
-    feed = fastfeedparser.parse(feed_body)
+    feed = feedparser.parse(feed_body)
 
     fg = FeedGenerator()
-    fg.id(feed.feed.link)
+    fg.id(feed.feed.get("id", feed.feed.link))
     fg.title(feed.feed.title)
     fg.link(href=feed.feed.link)
     fg.description(feed.feed.get("description", "Filtered feed"))
@@ -32,12 +32,12 @@ def filter_feed(feed_body: str, filtered_words: str, filtered_categories: str) -
 
         # Check if the categories/terms contain filtered categories
         if len(filtered_categories_list) and hasattr(entry, "tags"):
-            terms = [tag["term"].lower() for tag in entry.tags]
+            terms = [tag.term.lower() for tag in entry.tags]
             if any(filtered_category in term for term in terms for filtered_category in filtered_categories_list):
                 continue
 
         fe = fg.add_entry()
-        fe.id(entry.link)
+        fe.id(entry.get("id", entry.link))
         fe.title(entry.title)
         fe.link(href=entry.link)
         fe.description(entry.get("description", ""))

rssfilter/utils.py

@@ -1,4 +1,4 @@
-import fastfeedparser
+import feedparser
 from django.test import TestCase
 
 from rssfilter.utils import filter_feed
@@ -37,40 +37,40 @@
 class UtilsTest(TestCase):
     def test_filter_words(self):
         filtered_feed_body = filter_feed(body, filtered_words="One", filtered_categories="")
-        filtered_feed = fastfeedparser.parse(filtered_feed_body)
+        filtered_feed = feedparser.parse(filtered_feed_body)
 
         self.assertEqual(len(filtered_feed.entries), 1)
         self.assertEqual(filtered_feed.entries[0].title, "Article Two")
 
     def test_filter_words_case_insenstive(self):
         filtered_feed_body = filter_feed(body, filtered_words="ONE", filtered_categories="")
-        filtered_feed = fastfeedparser.parse(filtered_feed_body)
+        filtered_feed = feedparser.parse(filtered_feed_body)
 
         self.assertEqual(len(filtered_feed.entries), 1)
         self.assertEqual(filtered_feed.entries[0].title, "Article Two")
 
     def test_filter_words_empty(self):
         filtered_feed_body = filter_feed(body, filtered_words="", filtered_categories="")
-        filtered_feed = fastfeedparser.parse(filtered_feed_body)
+        filtered_feed = feedparser.parse(filtered_feed_body)
 
         self.assertEqual(len(filtered_feed.entries), 2)
 
     def test_filter_words_not_found(self):
         filtered_feed_body = filter_feed(body, filtered_words="Foo", filtered_categories="")
-        filtered_feed = fastfeedparser.parse(filtered_feed_body)
+        filtered_feed = feedparser.parse(filtered_feed_body)
 
         self.assertEqual(len(filtered_feed.entries), 2)
 
     def test_filter_words_comma_seperated(self):
         filtered_feed_body = filter_feed(body, filtered_words="Foo, Bar, One", filtered_categories="")
-        filtered_feed = fastfeedparser.parse(filtered_feed_body)
+        filtered_feed = feedparser.parse(filtered_feed_body)
 
         self.assertEqual(len(filtered_feed.entries), 1)
         self.assertEqual(filtered_feed.entries[0].title, "Article Two")
 
     def test_filter_categories(self):
         filtered_feed_body = filter_feed(body, filtered_words="", filtered_categories="Category Four")
-        filtered_feed = fastfeedparser.parse(filtered_feed_body)
+        filtered_feed = feedparser.parse(filtered_feed_body)
 
         self.assertEqual(len(filtered_feed.entries), 1)
         self.assertEqual(filtered_feed.entries[0].title, "Article One")