requester: treat DDoS-Guard interstitials as challenges (FlareSolverr fallback); mock-origin test

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MUYdCh2nCVsQYgJAT7gwSi

src/util/requester.rs

@@ -222,6 +222,15 @@ impl Requester {
         body.contains("Just a moment...")
             || body.contains("cf-turnstile-response")
             || body.contains("Enable JavaScript and cookies to continue")
+            || Self::looks_like_ddos_guard_challenge(body)
+    }
+
+    /// DDoS-Guard interstitials (rule34video) are short JS-check pages, never real content.
+    fn looks_like_ddos_guard_challenge(body: &str) -> bool {
+        body.len() < 20_000
+            && (body.contains("/.well-known/ddos-guard/")
+                || body.contains("check.ddos-guard.net")
+                || body.contains("DDoS-Guard</title>"))
     }
 
     fn jina_mirror_url(url: &str) -> Option<String> {
@@ -1033,4 +1042,88 @@ mod tests {
 
         assert!(cookie_header.contains("shared_cookie=1"));
     }
+
+    async fn serve(listener: tokio::net::TcpListener, reply: impl Fn(&str) -> String + Send + 'static) {
+        use tokio::io::{AsyncReadExt, AsyncWriteExt};
+        loop {
+            let Ok((mut sock, _)) = listener.accept().await else { return };
+            let mut buf = vec![0u8; 16384];
+            let mut len = 0;
+            // read headers, then the declared body
+            loop {
+                let Ok(n) = sock.read(&mut buf[len..]).await else { break };
+                if n == 0 { break; }
+                len += n;
+                let text = String::from_utf8_lossy(&buf[..len]).to_string();
+                if let Some(head_end) = text.find("\r\n\r\n") {
+                    let want = text
+                        .lines()
+                        .find_map(|l| l.to_ascii_lowercase().strip_prefix("content-length:").map(|v| v.trim().parse::<usize>().unwrap_or(0)))
+                        .unwrap_or(0);
+                    if len >= head_end + 4 + want { break; }
+                }
+            }
+            let req = String::from_utf8_lossy(&buf[..len]).to_string();
+            let _ = sock.write_all(reply(&req).as_bytes()).await;
+            let _ = sock.shutdown().await;
+        }
+    }
+
+    fn http(status: &str, ctype: &str, extra: &str, body: &str) -> String {
+        format!(
+            "HTTP/1.1 {status}\r\ncontent-type: {ctype}\r\n{extra}content-length: {}\r\nconnection: close\r\n\r\n{body}",
+            body.len()
+        )
+    }
+
+    /// DDoS-Guard answers either a bare `403 Access denied.` (blocked fingerprint/IP) or a
+    /// short JS-check page. Both must end up at FlareSolverr and return the real listing.
+    #[tokio::test(flavor = "multi_thread")]
+    async fn ddos_guard_blocks_are_solved_through_flaresolverr() {
+        // distinct hosts: the cookie jar is process-wide, so a solved cookie would leak across passes
+        for (interstitial, host) in [(false, "127.0.0.1"), (true, "localhost")] {
+            let origin = tokio::net::TcpListener::bind("127.0.0.1:0").await.unwrap();
+            let flare = tokio::net::TcpListener::bind("127.0.0.1:0").await.unwrap();
+            let origin_port = origin.local_addr().unwrap().port();
+            let flare_port = flare.local_addr().unwrap().port();
+
+            tokio::spawn(serve(origin, move |req| {
+                if req.contains("ddg_ok=1") {
+                    http("200 OK", "text/html", "", "<div class=\"item thumb video_1\">real listing</div>")
+                } else if interstitial {
+                    http(
+                        "200 OK",
+                        "text/html",
+                        "server: ddos-guard\r\n",
+                        "<html><head><title>DDoS-Guard</title><script src=\"/.well-known/ddos-guard/check?context=free_splash\"></script></head></html>",
+                    )
+                } else {
+                    http("403 Forbidden", "text/plain", "server: ddos-guard\r\n", "Access denied.")
+                }
+            }));
+            tokio::spawn(serve(flare, move |req| {
+                let body = if req.contains("sessions.create") {
+                    r#"{"status":"ok","message":"","session":"mock"}"#.to_string()
+                } else if req.contains("sessions.destroy") {
+                    r#"{"status":"ok","message":""}"#.to_string()
+                } else {
+                    format!(
+                        r#"{{"status":"ok","message":"","startTimestamp":0,"endTimestamp":1,"version":"mock","solution":{{"url":"http://127.0.0.1:{origin_port}/","status":200,"response":"<div class=\"item thumb video_1\">real listing</div>","headers":{{}},"userAgent":"Mozilla/5.0 mock","cookies":[{{"name":"ddg_ok","value":"1","domain":"","path":"/"}}]}}}}"#
+                    )
+                };
+                http("200 OK", "application/json", "", &body)
+            }));
+
+            unsafe { std::env::set_var("FLARE_URL", format!("http://127.0.0.1:{flare_port}/v1")) };
+            let mut requester = Requester::new();
+            let body = requester
+                .get(&format!("http://{host}:{origin_port}/?mode=async"), None)
+                .await
+                .expect("requester should fall through to FlareSolverr");
+            assert!(
+                body.contains("real listing"),
+                "interstitial={interstitial}: got {body:?}"
+            );
+        }
+    }
 }