From dca4d276a45cc85f97db326636b4b671a3263225 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?No=C3=A9mi=20V=C3=A1nyi?= <sitbackandwait@gmail.com>
Date: Sun, 30 Oct 2016 01:01:22 +0200
Subject: [PATCH 1/2] add sample config of filtron

---
 docs/admin/filtron.rst | 114 +++++++++++++++++++++++++++++++++++++++++
 docs/index.rst         |   1 +
 2 files changed, 115 insertions(+)
 create mode 100644 docs/admin/filtron.rst

diff --git a/docs/admin/filtron.rst b/docs/admin/filtron.rst
new file mode 100644
index 000000000..c422cb0a8
--- /dev/null
+++ b/docs/admin/filtron.rst
@@ -0,0 +1,114 @@
+How to protect an instance
+==========================
+
+Searx depens on external search services. To avoid the abuse of these services it is advised to limit the number of requests processed by searx.
+
+An application firewall, ``filtron`` solves exactly this problem. Information on how to install it can be found at the `project page of filtron <https://github.com/asciimoo/filtron>`__.
+
+Sample configuration of filtron
+-------------------------------
+
+An example configuration can be find below. This configuration limits the access of
+
+ * scripts or applications (roboagent limit)
+
+ * webcrawlers (botlimit)
+
+ * IPs which send too many requests (IP limit)
+
+ * too many json, csv, etc. requests (rss/json limit)
+
+ * the same UserAgent of if too many requests (useragent limit)
+
+
+.. code:: json
+
+    [
+        {
+            "name": "search request",
+            "filters": ["Param:q", "Path=^(/|/search)$"],
+            "interval": <time-interval-in-sec>,
+            "limit": <max-request-number-in-interval>,
+            "subrules": [
+                {
+                    "name": "roboagent limit",
+                    "interval": <time-interval-in-sec>,
+                    "limit": <max-request-number-in-interval>,
+                    "filters": ["Header:User-Agent=(curl|cURL|Wget|python-requests|Scrapy|FeedFetcher|Go-http-client)"],
+                    "actions": [
+                        {"name": "block",
+                         "params": {"message": "Rate limit exceeded"}}
+                    ]
+                },
+                {
+                    "name": "botlimit",
+                    "limit": 0,
+                    "stop": true,
+                    "filters": ["Header:User-Agent=(Googlebot|bingbot|Baiduspider|yacybot|YandexMobileBot|YandexBot|Yahoo! Slurp|MJ12bot|AhrefsBot|archive.org_bot|msnbot|MJ12bot|SeznamBot|linkdexbot|Netvibes|SMTBot|zgrab|James BOT)"],
+                    "actions": [
+                        {"name": "block",
+                         "params": {"message": "Rate limit exceeded"}}
+                    ]
+                },
+                {
+                    "name": "IP limit",
+                    "interval": <time-interval-in-sec>,
+                    "limit": <max-request-number-in-interval>,
+                    "stop": true,
+                    "aggregations": ["Header:X-Forwarded-For"],
+                    "actions": [
+                        {"name": "block",
+                         "params": {"message": "Rate limit exceeded"}}
+                    ]
+                },
+                {
+                    "name": "rss/json limit",
+                    "interval": <time-interval-in-sec>,
+                    "limit": <max-request-number-in-interval>,
+                    "stop": true,
+                    "filters": ["Param:format=(csv|json|rss)"],
+                    "actions": [
+                        {"name": "block",
+                         "params": {"message": "Rate limit exceeded"}}
+                    ]
+                },
+                {
+                    "name": "useragent limit",
+                    "interval": <time-interval-in-sec>,
+                    "limit": <max-request-number-in-interval>,
+                    "aggregations": ["Header:User-Agent"],
+                    "actions": [
+                        {"name": "block",
+                         "params": {"message": "Rate limit exceeded"}}
+                    ]
+                }
+            ]
+        }
+    ]
+
+
+
+Route request through filtron
+-----------------------------
+
+Filtron can be started using the following command:
+
+.. code:: bash
+
+    $ filtron -rules rules.json
+
+It listens on 127.0.0.1:4004 and forwards filtered requests to 127.0.0.1:8888 by default.
+
+Use it along with ``nginx`` with the following example configuration.
+
+.. code:: bash
+
+    location / {
+        proxy_set_header        Host    $http_host;
+        proxy_set_header        X-Real-IP $remote_addr;
+        proxy_set_header        X-Forwarded-For $proxy_add_x_forwarded_for;
+        proxy_set_header        X-Scheme $scheme;
+        proxy_pass http://127.0.0.1:4004/;
+    }
+
+Requests are coming from port 4004 going through filtron and then forwarded to port 8888 where a searx is being run.
diff --git a/docs/index.rst b/docs/index.rst
index 46960c0fc..18e4b6d07 100644
--- a/docs/index.rst
+++ b/docs/index.rst
@@ -38,6 +38,7 @@ Administrator documentation
 
    dev/install/installation
    admin/api
+   admin/filtron
 
 Developer documentation
 -----------------------