disable crawling for catalogue pages with multiple tags

diff --git a/src/catalogue/views.py b/src/catalogue/views.py
index bba773d..5273ab4 100644 (file)
--- a/src/catalogue/views.py
+++ b/src/catalogue/views.py
@@ -6,6 +6,7 @@ from collections import OrderedDict
 import random
 
 from django.conf import settings
+from django.http.response import HttpResponseForbidden
 from django.template import RequestContext
 from django.template.loader import render_to_string
 from django.shortcuts import render_to_response, get_object_or_404, render, redirect
@@ -27,6 +28,7 @@ from catalogue.helpers import get_top_level_related_tags
 from catalogue.models import Book, Collection, Tag, Fragment
 from catalogue.utils import split_tags
 from catalogue.models.tag import prefetch_relations
+from wolnelektury.utils import is_crawler
 
 staff_required = user_passes_test(lambda user: user.is_staff)
 
@@ -222,6 +224,9 @@ def tagged_object_list(request, tags, list_type):
     except ResponseInstead as e:
         return e.response
 
+    if is_crawler(request) and len(tags) > 1:
+        return HttpResponseForbidden('address removed from crawling. check robots.txt')
+
     if list_type == 'gallery' and any(tag.category == 'set' for tag in tags):
         raise Http404
 

diff --git a/src/wolnelektury/utils.py b/src/wolnelektury/utils.py
index d20039c..2657a55 100644 (file)
--- a/src/wolnelektury/utils.py
+++ b/src/wolnelektury/utils.py
@@ -155,3 +155,14 @@ class UnicodeCSVWriter(object):
 # the original re.escape messes with unicode
 def re_escape(s):
     return re.sub(r"[(){}\[\].*?|^$\\+-]", r"\\\g<0>", s)
+
+
+BOT_BITS = ['bot', 'slurp', 'spider', 'facebook', 'crawler', 'parser', 'http']
+
+
+def is_crawler(request):
+    user_agent = request.META.get('HTTP_USER_AGENT')
+    if not user_agent:
+        return True
+    user_agent = user_agent.lower()
+    return any(bot_bit in user_agent for bot_bit in BOT_BITS)