Add robots.txt support

README.md

@@ -20,10 +20,15 @@ round
 --sock <address> | Bind to the given socket. Defaults to 0.0.0.0:3000.
 ```
 
-Deploy it in a docker environment. It's probably safe, but no reason to take chances.
+Babble will search for a `robots.txt` file in the working directory to use. If it does not find one, it will use a
+default one that denies everything.
 
-If you want to be nice to crawlers that *actually abide by `robots.txt`*, perhaps add an entry to warn search engines
-away from it.
+Babble will periodically emit statistics into `stats.txt`, showing information about the worst-offending requesting
+IPs.
+
+## Warning
+
+Deploy it in a docker environment. It's probably safe, but no reason to take chances.
 
 ## Usage terms
 

src/main.rs

@@ -56,6 +56,7 @@ fn create_rng(seed_bytes: impl IntoIterator<Item = u8>) -> Rng {
 
 const COUNT_FILE: &str = "count.txt";
 const STATS_FILE: &str = "stats.txt";
+const ROBOTS_TXT: &str = "robots.txt";
 
 const SLOW_CHUNK_SIZE: usize = 100;
 const SLOW_DURATION: Duration = Duration::from_millis(100);
@@ -119,10 +120,16 @@ async fn main() {
 
     let (stats_tx, stats_rx) = flume::unbounded();
 
+    let robots_txt = std::fs::read_to_string(ROBOTS_TXT)
+        .ok()
+        .unwrap_or_else(|| include_str!("robots.txt").to_string());
+
     let app = {
         let counter = counter.clone();
         let stats_tx = stats_tx.clone();
-        Router::new().route(
+        Router::new()
+            .route("/robots.txt", get(|| async move { robots_txt.clone() }))
+            .route(
                 "/{id}",
                 get(
                     |Path(id): Path<String>,
@@ -146,7 +153,9 @@ async fn main() {
                         let mut session_rng = create_rng(count.to_le_bytes());
 
                         // Artificially slow down connections as rudimentary DDoS protection, and to use up client resources
-                    tokio::time::sleep(Duration::from_millis(session_rng.random_range(200..1000)))
+                        tokio::time::sleep(Duration::from_millis(
+                            session_rng.random_range(200..1000),
+                        ))
                         .await;
 
                         // Choose a bullshit generator from our collection for this page
@@ -221,6 +230,7 @@ async fn main() {
                     .rev()
                     .enumerate()
                     .map(|(i, (ip, n))| format!("{:<4} | {:<4} | {}\n", i + 1, n, ip))
+                    .take(30)
                     .collect::<String>();
                 let _ = std::fs::write(STATS_FILE, &stats);
             }

src/robots.txt

@@ -0,0 +1,2 @@
+User-agent: *
+Disallow: