web: extract readable html content

2026-05-31 05:49:20 +09:00
parent dc5ce2ba72
commit 7906ca5326
4 changed files with 427 additions and 39 deletions
@@ -13,6 +13,7 @@ grep-searcher = "0.1.16"
 ignore = "0.4.25"
 llm-worker = { workspace = true }
 manifest = { workspace = true }
+readability = { package = "readability-rs", version = "0.5.0" }
 reqwest = { version = "0.13", default-features = false, features = ["json", "native-tls"] }
 schemars = { workspace = true }
 serde = { workspace = true, features = ["derive"] }