Do not auto-download enclosures that are not audio or video

Blog feeds put each article's header image in an <enclosure>, so a text
feed read as a podcast full of episodes: 149 images, 74 MB across 11
feeds. media_types defaults to audio and video, with a per-feed override.

Such enclosures stay listed and stay downloadable by hand; the row names
what it is rather than saying "skipped". An unknown type is allowed, since
the real type is only known after downloading, and a torrent is allowed as
a container judged once unpacked.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AdXho5tTkjFLeUXKbEjKBh

src/config.rs

@@ -38,6 +38,10 @@ pub struct General {
     /// Unlimited by default was a trap: subscribing to an OPML of 80 feeds then pulled
     /// every back-catalogue episode at once. 0 means unlimited, deliberately chosen.
     pub max_new_per_check: usize,
+    /// Top-level media types worth downloading. Blog feeds put each article's header
+    /// image in an <enclosure>, so taking everything filled the disk with artwork and
+    /// counted it as episodes. Empty means take anything.
+    pub media_types: Vec<String>,
 }
 
 #[derive(Debug, Clone, Copy, PartialEq, Eq, Deserialize, Serialize)]
@@ -108,6 +112,9 @@ pub struct Feed {
     /// Overrides the global schedule for this feed. Same forms: "every 6h", "2d".
     #[serde(default, skip_serializing_if = "Option::is_none")]
     pub schedule: Option<String>,
+    /// Media types for this feed. None follows `[general]`; an empty list takes anything.
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub media_types: Option<Vec<String>>,
     /// Cap on new downloads per scan for this feed. None follows `[general]`.
     #[serde(default, skip_serializing_if = "Option::is_none")]
     pub max_new_per_check: Option<usize>,
@@ -135,6 +142,7 @@ impl Default for General {
             max_total_gb: 0.0,
             max_age_days: 0,
             max_new_per_check: 3,
+            media_types: vec!["audio".into(), "video".into()],
         }
     }
 }
@@ -276,6 +284,25 @@ fn default_socket() -> PathBuf {
     }
 }
 
+/// Whether an enclosure's type is one we want.
+///
+/// An unknown type is allowed: the real type is only known after downloading, and
+/// refusing everything untyped would drop feeds that simply omit the attribute.
+pub fn wanted_media(mime: Option<&str>, wanted: &[String]) -> bool {
+    if wanted.is_empty() {
+        return true;
+    }
+    let Some(mime) = mime.map(str::trim).filter(|m| !m.is_empty()) else {
+        return true;
+    };
+    let top = mime.split('/').next().unwrap_or(mime).to_ascii_lowercase();
+    // A .torrent is a container for media, not media itself; judge it once unpacked.
+    if mime.to_ascii_lowercase().contains("torrent") {
+        return true;
+    }
+    wanted.iter().any(|w| w.trim().eq_ignore_ascii_case(&top) || w.trim().eq_ignore_ascii_case(mime))
+}
+
 /// Feed ids are the TOML table key, so they must be readable and punctuation-free.
 pub fn slug(text: &str) -> String {
     let mut out = String::new();
@@ -391,6 +418,26 @@ mod tests {
         assert_eq!(t.ports(), (6881, 6889), "reversed range is not a range");
     }
 
+    #[test]
+    fn media_types_keep_article_artwork_out() {
+        let want = vec!["audio".to_string(), "video".to_string()];
+        assert!(wanted_media(Some("audio/mpeg"), &want));
+        assert!(wanted_media(Some("audio/mp4"), &want));
+        assert!(wanted_media(Some("video/quicktime"), &want));
+        assert!(!wanted_media(Some("image/jpeg"), &want), "a blog header image is not an episode");
+        assert!(!wanted_media(Some("text/html"), &want));
+
+        // A torrent is a container; what is inside is judged after unpacking.
+        assert!(wanted_media(Some("application/x-bittorrent"), &want));
+        // Unknown type: only discoverable by downloading, so do not refuse it outright.
+        assert!(wanted_media(None, &want));
+        assert!(wanted_media(Some(""), &want));
+        // An empty list means take anything, which is how it behaved before.
+        assert!(wanted_media(Some("image/jpeg"), &[]));
+        // A full type can be named exactly.
+        assert!(wanted_media(Some("image/jpeg"), &["image/jpeg".to_string()]));
+    }
+
     #[test]
     fn slugs_are_readable_and_unique() {
         assert_eq!(slug("Accidental Tech Podcast"), "accidental-tech-podcast");
@@ -402,7 +449,7 @@ mod tests {
 
         let mut taken = BTreeMap::new();
         taken.insert("the-daily".to_string(), Feed {
-            url: "u".into(), folder: None, group: None, schedule: None, keywords: vec![], allow_explicit: false,
+            url: "u".into(), folder: None, group: None, media_types: None, schedule: None, keywords: vec![], allow_explicit: false,
             auto_download: true, max_new_per_check: None, username: None,
             password: None, password_env: None,
         });
@@ -415,6 +462,7 @@ mod tests {
             url: "https://x/y".into(),
             folder: None,
             group: None,
+            media_types: None,
             schedule: None,
             keywords: vec![],
             allow_explicit: false,