Merge pull request #748 from Gluejar/disallow-search

Disallow search

frontend/templates/robots.txt

@@ -4,6 +4,7 @@ User-agent: *
 Disallow: /accounts/
 Disallow: /feedback/
 Disallow: /socialauth/
+Disallow: /search/
 Disallow: /googlebooks/
 {% else %}
 User-agent: *

frontend/templates/worksummary.html

@@ -0,0 +1,45 @@
+{% extends 'base.html' %}
+
+{% load humanize %}
+{% block title %}— 
+    {% if work.is_free %}
+        {{ work.title }} is a Free eBook. {% for fmt in  work.formats %}[{{ fmt }}]{% endfor %}
+    {% else %}
+        Help us make  {{ work.title }} a Free eBook!
+    {% endif %}{% if action == 'editions' %} – All Editions{% endif %}
+{% endblock %}
+{% block extra_meta %}
+<meta property="og:title" content="{{ work.title }}" />
+<meta property="og:type" content="book" />
+<meta property="og:url" content="https://unglue.it{% url 'work' work.id %}" />
+<meta property="og:image" content="{{ work.cover_image_thumbnail }}" />
+<meta property="og:site_name" content="Unglue.it" />
+{% for author in work.relators %}<meta property="book:author" content="{{ author.name }}" />{% endfor %}
+{% if work.first_isbn_13 %}<meta property="book:isbn" content="{{ work.first_isbn_13 }}" />{% endif %}
+{% endblock %}
+
+
+{% block topsection %}
+    <div class="book-detail-info">
+        <div class="layout">
+            <h2 class="book-name" itemprop="name">{{ work.title }}</h2>
+        <div>
+                <div class="pubinfo">
+                    <h3 class="book-author">
+                    <span  itemprop="author"><a href="{% url 'search' %}?q={{ work.relators.0.author.name|urlencode }}&amp;ty=au" >{{ work.relators.0.name }}</a></span>{% if work.authors.count == 2 %}
+                        and <span  itemprop="author"><a href="{% url 'search' %}?q={{ work.relators.1.author.name|urlencode }}&amp;ty=au" >{{ work.relators.1.name }}</a></span>
+                    {% endif %}{% if work.relators.count > 2 %}{% for author in work.relators %}{% if not forloop.first %}, <span  itemprop="author"><a href="{% url 'search' %}?q={{ author.author.name|urlencode }}&amp;ty=au" >{{ author.name }}</a></span>{% endif %}{% endfor %}
+                    {% endif %}
+                    </h3>
+                    <h3 class="book-year"> 
+                        {% if work.last_campaign.publisher %}
+                        <span itemprop="publisher"><a href="{% url 'bypubname_list' work.last_campaign.publisher.name.id %}">{{ work.last_campaign.publisher }}</a></span>
+                        {% endif %}
+                        <span itemprop="datePublished">{{ work.publication_date }}</span>
+                        <meta itemprop="inLanguage" content="work.language" />
+                        <meta itemprop="typicalAgeRange" content="work.age_range" />
+                    </h3>
+                </div>
+            </div>
+    </div>
+{% endblock %}

frontend/tests.py

@@ -63,6 +63,7 @@ class RhPageTests(TestCase):
     def test_anonymous(self):
         anon_client = Client()
         r = anon_client.get("/work/{}/".format(self.work.id))
+        r = anon_client.head("/work/{}/".format(self.work.id))
         self.assertEqual(r.status_code, 200)
         csrfmatch =  re.search("name='csrfmiddlewaretoken' value='([^']*)'", r.content)
         self.assertFalse(csrfmatch)

frontend/views/__init__.py

@@ -300,7 +300,8 @@ def acks(request, work):
 def work(request, work_id, action='display'):
     work = safe_get_work(work_id)
     alert = ''
-
+    if request.method == "HEAD":
+        return render(request, 'worksummary.html', {'work': work,})
     formset = None
     if action == "acks":
         return acks(request, work)
@@ -524,11 +525,20 @@ def manage_ebooks(request, edition_id, by=None):
         })
 
 
+BAD_ROBOTS = [u'memoryBot']
+def is_bad_robot(request):
+    user_agent = request.META.get('HTTP_USER_AGENT', '')
+    for robot in BAD_ROBOTS:
+        if robot in user_agent:
+            return True
+    return False        
 
 def googlebooks(request, googlebooks_id):
     try:
         edition = models.Identifier.objects.get(type='goog', value=googlebooks_id).edition
     except models.Identifier.DoesNotExist:
+        if is_bad_robot(request):
+            return HttpResponseNotFound("failed looking up googlebooks id %s" % googlebooks_id)
         try:
             edition = bookloader.add_by_googlebooks_id(googlebooks_id)
             if edition.new:
@@ -1916,12 +1926,18 @@ def search(request):
             results = models.Work.objects.none()
             break
         else:
-            results = gluejar_search(q, user_ip=request.META['REMOTE_ADDR'], page=1)
-            gbo = 'y'
+            if is_bad_robot(request):
+                results = models.Work.objects.none()
+            else:
+                results = gluejar_search(q, user_ip=request.META['REMOTE_ADDR'], page=1)
+                gbo = 'y'
     else:
         if gbo == 'n':
             page = page-1 # because page=1 is the unglue.it results
-        results = gluejar_search(q, user_ip=request.META['REMOTE_ADDR'], page=page)
+        if is_bad_robot(request):
+            results = models.Work.objects.none()
+        else:
+            results = gluejar_search(q, user_ip=request.META['REMOTE_ADDR'], page=page)
         campaign_works = None
 
     # flag search result as on wishlist as appropriate