diff --git a/docs/bean-reference.rst b/docs/bean-reference.rst
index 538ffa4b..666f71da 100644
--- a/docs/bean-reference.rst
+++ b/docs/bean-reference.rst
@@ -521,6 +521,24 @@ ScrollDownBehavior
 
 .. bean-doc:: org.archive.modules.behaviors.ScrollDownBehavior
 
+Miscellaneous Processors
+------------------------
+
+BotBlockDetector
+~~~~~~~~~~~~~~~~
+
+.. bean-doc:: org.archive.modules.processor.BotBlockDetector
+
+HashCrawlMapper
+~~~~~~~~~~~~~~~
+
+.. bean-doc:: org.archive.crawler.processor.HashCrawlMapper
+
+LexicalCrawlMapper
+~~~~~~~~~~~~~~~~~~
+
+.. bean-doc:: org.archive.crawler.processor.LexicalCrawlMapper
+
 Post-Processors
 ---------------
 
diff --git a/modules/src/main/java/org/archive/modules/processor/BotBlockDetector.java b/modules/src/main/java/org/archive/modules/processor/BotBlockDetector.java
new file mode 100644
index 00000000..d8ccc45f
--- /dev/null
+++ b/modules/src/main/java/org/archive/modules/processor/BotBlockDetector.java
@@ -0,0 +1,152 @@
+/*
+ *  This file is part of the Heritrix web crawler (crawler.archive.org).
+ *
+ *  Licensed to the Internet Archive (IA) by one or more individual
+ *  contributors.
+ *
+ *  The IA licenses this file to You under the Apache License, Version 2.0
+ *  (the "License"); you may not use this file except in compliance with
+ *  the License.  You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ *  Unless required by applicable law or agreed to in writing, software
+ *  distributed under the License is distributed on an "AS IS" BASIS,
+ *  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ *  See the License for the specific language governing permissions and
+ *  limitations under the License.
+ */
+package org.archive.modules.processor;
+
+import java.util.Map;
+import java.util.TreeMap;
+import java.util.concurrent.ConcurrentHashMap;
+import java.util.concurrent.ConcurrentMap;
+import java.util.concurrent.atomic.AtomicLong;
+
+import org.archive.modules.CrawlURI;
+import org.archive.modules.Processor;
+import org.archive.util.JSONUtils;
+import org.json.JSONException;
+import org.json.JSONObject;
+
+/**
+ * Detects responses produced by bot-blocking services and adds a "botblock:service" annotation.
+ * <p>
+ * Normally added to the fetch chain before the extractors.
+ */
+public class BotBlockDetector extends Processor {
+    protected final ConcurrentMap<String, AtomicLong> counts = new ConcurrentHashMap<>();
+
+    public Map<String, AtomicLong> getCounts() {
+        return counts;
+    }
+
+    @Override
+    protected boolean shouldProcess(CrawlURI curi) {
+        return curi.isHttpTransaction() &&
+               curi.getFetchStatus() > 0;
+    }
+
+    @Override
+    protected void innerProcess(CrawlURI curi) throws InterruptedException {
+        String detected = detect(curi);
+        if (detected != null &&
+            curi.getAnnotations().add("botblock:" + detected)) {
+            counts.computeIfAbsent(detected, ignored -> new AtomicLong()).incrementAndGet();
+        }
+    }
+
+    @Override
+    protected JSONObject toCheckpointJson() throws JSONException {
+        JSONObject json = super.toCheckpointJson();
+        json.put("counts", counts);
+        return json;
+    }
+
+    @Override
+    protected void fromCheckpointJson(JSONObject json) throws JSONException {
+        super.fromCheckpointJson(json);
+        counts.clear();
+        JSONObject counts = json.optJSONObject("counts");
+        if (counts != null) JSONUtils.putAllAtomicLongs(this.counts, counts);
+    }
+
+    @Override
+    public String report() {
+        return super.report() + "  Blocked requests by service: " +
+               new TreeMap<>(counts) + "\n";
+    }
+
+    protected static String detect(CrawlURI curi) {
+        if (detectAkamai(curi)) return "akamai";
+        if (detectAnubis(curi)) return "anubis";
+        if (detectCloudflare(curi)) return "cloudflare";
+        if (detectDataDome(curi)) return "datadome";
+        if (detectIncapsula(curi)) return "incapsula";
+        return null;
+    }
+
+    private static boolean detectAkamai(CrawlURI curi) {
+        return curi.getFetchStatus() == 403 &&
+               "AkamaiGHost".equals(curi.getHttpResponseHeader("server"));
+    }
+
+    private static boolean detectAnubis(CrawlURI curi) {
+        if (curi.getFetchStatus() == 307) {
+            String location = curi.getHttpResponseHeader("location");
+            return location != null && location.contains("/.within.website/?redir=");
+        } else if (curi.getFetchStatus() == 200) {
+            String setCookie = curi.getHttpResponseHeader("set-cookie");
+            return setCookie != null && setCookie.startsWith("techaro.lol-anubis-") &&
+                   bodyContainsHtml(curi, "<script id=\"anubis_challenge\"");
+        }
+        return false;
+    }
+
+    private static boolean detectCloudflare(CrawlURI curi) {
+        // challenge page
+        if ("challenge".equalsIgnoreCase(curi.getHttpResponseHeader("cf-mitigated"))) {
+            return true;
+        }
+        // block page
+        return curi.getFetchStatus() == 403 &&
+               "cloudflare".equalsIgnoreCase(curi.getHttpResponseHeader("server")) &&
+               bodyContainsHtml(curi, "<h1 data-translate=\"block_headline\">Sorry, you have been blocked</h1>");
+    }
+
+    private static boolean detectDataDome(CrawlURI curi) {
+        return curi.getHttpResponseHeader("x-dd-b") != null &&
+               "protected".equalsIgnoreCase(curi.getHttpResponseHeader("x-datadome"));
+    }
+
+    private static boolean detectIncapsula(CrawlURI curi) {
+        return curi.getFetchStatus() == 404 &&
+               curi.getHttpResponseHeader("x-iinfo") != null &&
+               bodyContainsHtml(curi, "Incapsula incident ID:");
+    }
+
+    private static boolean bodyContainsHtml(CrawlURI curi, String string) {
+        return hasHtmlContentType(curi) &&
+               curi.getRecorder() != null &&
+               curi.getRecorder().getContentReplayPrefixString(8000).contains(string);
+    }
+
+    private static boolean hasHtmlContentType(CrawlURI curi) {
+        String type = curi.getContentType();
+        return type == null ||
+               matchesMediaType(type, "text/html") ||
+               matchesMediaType(type, "application/xhtml+xml");
+    }
+
+    private static boolean matchesMediaType(String value, String expected) {
+        if (!value.regionMatches(true, 0, expected, 0, expected.length())) {
+            return false;
+        }
+        int i = expected.length();
+        while (i < value.length() && Character.isWhitespace(value.charAt(i))) {
+            i++;
+        }
+        return i == value.length() || value.charAt(i) == ';';
+    }
+}
\ No newline at end of file
diff --git a/modules/src/test/java/org/archive/modules/processor/BotBlockDetectorTest.java b/modules/src/test/java/org/archive/modules/processor/BotBlockDetectorTest.java
new file mode 100644
index 00000000..9982b156
--- /dev/null
+++ b/modules/src/test/java/org/archive/modules/processor/BotBlockDetectorTest.java
@@ -0,0 +1,173 @@
+/*
+ *  This file is part of the Heritrix web crawler (crawler.archive.org).
+ *
+ *  Licensed to the Internet Archive (IA) by one or more individual
+ *  contributors.
+ *
+ *  The IA licenses this file to You under the Apache License, Version 2.0
+ *  (the "License"); you may not use this file except in compliance with
+ *  the License.  You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ *  Unless required by applicable law or agreed to in writing, software
+ *  distributed under the License is distributed on an "AS IS" BASIS,
+ *  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ *  See the License for the specific language governing permissions and
+ *  limitations under the License.
+ */
+package org.archive.modules.processor;
+
+import java.io.ByteArrayInputStream;
+import java.nio.charset.StandardCharsets;
+import java.nio.file.Path;
+import java.util.Set;
+
+import org.archive.modules.CrawlURI;
+import org.archive.net.UURIFactory;
+import org.archive.util.Recorder;
+import org.junit.jupiter.api.Test;
+import org.junit.jupiter.api.io.TempDir;
+
+import static org.junit.jupiter.api.Assertions.*;
+
+class BotBlockDetectorTest {
+
+    @TempDir
+    Path tempDir;
+
+    @Test
+    void detectsAkamaiBlock() throws Exception {
+        assertBlocked(akamaiBlock(), "akamai");
+    }
+
+    @Test
+    void detectsAnubisRedirectChallenge() throws Exception {
+        CrawlURI curi = curi(307);
+        curi.putHttpResponseHeader("Location",
+                "/.within.website/?redir=https%3A%2F%2Fexample.com%2F");
+
+        assertBlocked(curi, "anubis");
+    }
+
+    @Test
+    void detectsAnubisCookieChallenge() throws Exception {
+        CrawlURI curi = curi(200);
+        curi.putHttpResponseHeader("Set-Cookie",
+                "techaro.lol-anubis-auth=token; Path=/");
+        recordResponse(curi, "<script id=\"anubis_challenge\"></script>");
+
+        assertBlocked(curi, "anubis");
+    }
+
+    @Test
+    void ordinaryResponseDoesNotMatch() throws Exception {
+        CrawlURI curi = curi(200);
+
+        assertNotBlocked(curi);
+    }
+
+    @Test
+    void detectsCloudflareChallenge() throws Exception {
+        CrawlURI curi = curi(403);
+        curi.putHttpResponseHeader("Server", "cloudflare");
+        curi.putHttpResponseHeader("CF-Mitigated", "challenge");
+
+        assertBlocked(curi, "cloudflare");
+    }
+
+    @Test
+    void detectsCloudflareBlock() throws Exception {
+        assertBlocked(cloudflareBlock(), "cloudflare");
+    }
+
+    @Test
+    void detectsDatadomeBlock() throws Exception {
+        CrawlURI curi = curi(403);
+        // some sites use both Cloudflare and DataDome
+        curi.putHttpResponseHeader("server", "cloudflare");
+        curi.putHttpResponseHeader("cf-ray", "1111111111111111-SJC");
+        curi.putHttpResponseHeader("x-datadome", "protected");
+        curi.putHttpResponseHeader("x-dd-b", "2");
+        curi.putHttpResponseHeader("x-datadome-cid", "AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA==");
+        assertBlocked(curi, "datadome");
+    }
+
+    @Test
+    void detectsIncapsulaChallenge() throws Exception {
+        CrawlURI curi = curi(404);
+        curi.putHttpResponseHeader("x-iinfo", "foo");
+        recordResponse(curi,
+                "Request unsuccessful. Incapsula incident ID: 123456");
+
+        assertBlocked(curi, "incapsula");
+    }
+
+    @Test
+    void unrelated403ResponseDoesNotMatch() throws Exception {
+        CrawlURI curi = curi(403);
+        curi.putHttpResponseHeader("Server", "example");
+
+        assertNotBlocked(curi);
+    }
+
+    @Test
+    void checkpointRoundTripPreservesBlockedRequestCounts() throws Exception {
+        BotBlockDetector detector = new BotBlockDetector();
+        detector.process(akamaiBlock());
+        detector.process(cloudflareBlock());
+
+        BotBlockDetector restored = new BotBlockDetector();
+        restored.fromCheckpointJson(detector.toCheckpointJson());
+
+        assertEquals(1, restored.getCounts().get("akamai").get());
+        assertEquals(1, restored.getCounts().get("cloudflare").get());
+        assertEquals(2, restored.getURICount());
+    }
+
+    private static void assertBlocked(CrawlURI curi, String service)
+            throws InterruptedException {
+        new BotBlockDetector().process(curi);
+        assertEquals(Set.of("botblock:" + service), curi.getAnnotations());
+    }
+
+    private static void assertNotBlocked(CrawlURI curi)
+            throws InterruptedException {
+        new BotBlockDetector().process(curi);
+        assertTrue(curi.getAnnotations().isEmpty());
+    }
+
+    private static CrawlURI akamaiBlock() throws Exception {
+        CrawlURI curi = curi(403);
+        curi.putHttpResponseHeader("Server", "AkamaiGHost");
+        return curi;
+    }
+
+    private CrawlURI cloudflareBlock() throws Exception {
+        CrawlURI curi = curi(403);
+        curi.putHttpResponseHeader("Server", "cloudflare");
+        recordResponse(curi, "<h1 data-translate=\"block_headline\">Sorry, you have been blocked</h1>");
+        return curi;
+    }
+
+    private static CrawlURI curi(int status) throws Exception {
+        CrawlURI curi = new CrawlURI(UURIFactory.getInstance("https://example.com/"));
+        curi.setFetchStatus(status);
+        curi.setFetchType(CrawlURI.FetchType.HTTP_GET);
+        curi.setContentType("text/html");
+        return curi;
+    }
+
+    private void recordResponse(CrawlURI curi, String body) throws Exception {
+        byte[] response = ("HTTP/1.1 " + curi.getFetchStatus() + " Test\r\n"
+                + "Content-Type: text/html\r\n"
+                + "Content-Length: " + body.getBytes(StandardCharsets.UTF_8).length + "\r\n"
+                + "\r\n"
+                + body).getBytes(StandardCharsets.UTF_8);
+        Recorder recorder = new Recorder(tempDir.toFile(), "bot-block-detector");
+        curi.setRecorder(recorder);
+        recorder.inputWrap(new ByteArrayInputStream(response));
+        recorder.getRecordedInput().readFully();
+        recorder.close();
+    }
+}