Add automated spam filter for questions with logging according to weights

.env.example

@@ -6,4 +6,5 @@ SPOKEN_DB='13thJune'
 SECRET_KEY=''
 VIDEO_PATH=''
 DEBUG=True
-TEMPLATE_DEBUG=True
+TEMPLATE_DEBUG=True
+SPAM_LOG_FILE=''

forums/settings.py

@@ -17,6 +17,7 @@
 # Build paths inside the project like this: os.path.join(BASE_DIR, ...)
 BASE_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
 
+SPAM_LOG_FILE = os.getenv("SPAM_LOG_FILE")
 
 # Quick-start development settings - unsuitable for production
 # See https://docs.djangoproject.com/en/1.11/howto/deployment/checklist/
@@ -267,29 +268,54 @@
 except ImportError:
     pass
 
-
 LOGGING = {
     'version': 1,
     'disable_existing_loggers': False,
+
     'filters': {
         'require_debug_false': {
             '()': 'django.utils.log.RequireDebugFalse'
         }
     },
+
+    'formatters': {
+        'verbose': {
+            'format': '[{asctime}] {levelname} {name}: {message}',
+            'style': '{',
+        },
+    },
+
     'handlers': {
         'mail_admins': {
             'level': 'ERROR',
             'filters': ['require_debug_false'],
             'class': 'django.utils.log.AdminEmailHandler'
-        }
+        },
+
+        # New handler for spam detection
+        'spam_file': {
+            'level': 'INFO',
+            'class': 'logging.handlers.RotatingFileHandler',
+            'filename': SPAM_LOG_FILE,  # create logs/ dir
+            'maxBytes': 1024 * 1024 * 5,   # 5 MB
+            'backupCount': 5,              # keep 5 old logs
+            'formatter': 'verbose',
+        },
     },
+
     'loggers': {
         'django.request': {
             'handlers': ['mail_admins'],
             'level': 'ERROR',
             'propagate': True,
         },
+
+        #  New dedicated logger
+        'spam_detection': {
+            'handlers': ['spam_file'],
+            'level': 'INFO',
+            'propagate': False,
+        },
     }
 }
-
 VIDEO_PATH = os.getenv("VIDEO_PATH")

seed_spam_rules.py

@@ -0,0 +1,116 @@
+# Script to seed the database with predefined spam rules
+import os
+import django
+
+os.environ.setdefault("DJANGO_SETTINGS_MODULE", "forums.settings")
+django.setup()
+
+from django.db.models import Q
+from website.models import SpamRule
+
+
+
+def seed_spam_rules():
+    rules = {
+        # Certification/Exam dump patterns
+        "Certification/Exam Spam": {
+            "score": 30,
+            "type": SpamRule.KEYWORD,
+            "patterns": [
+                r"exam\s+dumps?", r"braindumps?", r"practice\s+test",
+                r"certification\s+exam", r"test\s+preparation",
+                r"exam\s+questions?", r"study\s+guides?",
+                r"pdf\s+\+\s+testing\s+engine", r"testing\s+engine",
+                r"exam\s+prep", r"mock\s+exam", r"real\s+exam",
+                r"dumps\s+pdf", r"braindump"
+            ],
+        },
+
+        # Promotional spam
+        "Promotional Spam": {
+            "score": 25,
+            "type": SpamRule.KEYWORD,
+            "patterns": [
+                r"click\s+here", r"join\s+now", r"limited\s+time",
+                r"discount", r"coupon\s+code", r"20%\s+off",
+                r"free\s+download", r"get\s+certified",
+                r"unlock\s+your\s+career", r"master\s+the",
+                r"boost\s+your\s+career", r"cert20",
+                r"at\s+checkout", r"special\s+offer",
+            ],
+        },
+
+        # Suspicious domains
+        "Suspicious Domain": {
+            "score": 35,
+            "type": SpamRule.DOMAIN,
+            "patterns": [
+                r"dumpscafe\.com", r"certsout\.com", r"mycertshub\.com",
+                r"vmexam\.com", r"kissnutra\.com", r"dumps.*\.com",
+                r"cert.*\.com", r"exam.*\.com",
+            ],
+        },
+
+        # Generic business language
+        "Business/Career Spam": {
+            "score": 15,
+            "type": SpamRule.KEYWORD,
+            "patterns": [
+                r"attests\s+to\s+your\s+proficiency",
+                r"esteemed\s+(?:accreditation|certification|credential)",
+                r"valuable\s+asset\s+to\s+companies",
+                r"demonstrates\s+your\s+ability",
+                r"comprehensive\s+study\s+(?:tools|materials)",
+                r"interactive\s+practice\s+tests",
+                r"real\s+exam\s+questions",
+                r"actual\s+exam\s+questions",
+                r"validated\s+by\s+.*certification",
+                r"urgently\s+need\s+experts",
+            ],
+        },
+
+        # Gaming content
+        "Gaming Spam": {
+            "score": 20,
+            "type": SpamRule.KEYWORD,
+            "patterns": [
+                r"spacebar\s+clicker", r"clicker\s+game",
+                r"addictive\s+game", r"upgrades\s+available",
+                r"instant\s+rewards",
+            ],
+        },
+
+        # Health/Supplement spam
+        "Health Spam": {
+            "score": 22,
+            "type": SpamRule.KEYWORD,
+            "patterns": [
+                r"vitalit[äa]t", r"nahrungserg[äa]nzungsmittel",
+                r"libido", r"fruchtbarkeit", r"energie",
+                r"hormonelle\s+balance", r"perforan",
+            ],
+        },
+    }
+
+    inserted, skipped = 0, 0
+    for note, config in rules.items():
+        for pattern in config["patterns"]:
+            exists = SpamRule.objects.filter(
+                Q(pattern=pattern) & Q(type=config["type"])
+            ).exists()
+            if not exists:
+                SpamRule.objects.create(
+                    type=config["type"],
+                    pattern=pattern,
+                    score=config["score"],
+                    notes=note,
+                )
+                inserted += 1
+            else:
+                skipped += 1
+
+    print(f"✅ Inserted {inserted} new rules, skipped {skipped} existing ones.")
+
+
+# Run it
+seed_spam_rules()

static/website/templates/index.html

@@ -93,6 +93,7 @@ <h3 align="center">Answers</h3>
             <ul class="nav nav-tabs">
                 <li class="active"><a data-toggle="tab" href="#recent_question">Recent questions</a></li>
                 <li><a data-toggle="tab" href="#most_active">Most active questions</a></li>
+                <li><a data-toggle="tab" href="#spam_pending">Spam Pending-Approval</a></li>
             </ul>
         </div>
         <div class="panel-body">
@@ -114,6 +115,7 @@ <h3 align="center">Answers</h3>
 							</thead>
 							<tbody>
                 {% for question in questions %}
+                {% if 'test-' not in question.category %}
                 <tr>
                     <td>
                         <span href="#" class="category" data-toggle="tooltip" data-placement="top" title="{{ question.category}}">
@@ -177,6 +179,7 @@ <h3 align="center">Answers</h3>
                         </span>
                     </td>
                 </tr>
+                {% endif %}
                 {% endfor %}
                 </tbody>
             </table>
@@ -279,7 +282,45 @@ <h3 align="center">Answers</h3>
                         </tbody>
                     </table>
             </div>
-        </div>
+            <div id="spam_pending" class="tab-pane fade">
+                <table id="spamTable" class="tablesorter-blue">
+                    <thead>
+                        <tr>
+                            <th>FOSS</th>
+                            <th>Tutorial</th>
+                            <th>Min</th>
+                            <th>Sec</th>
+                            <th>Question</th>
+                            <th>Date</th>
+                            <th>User</th>
+                            <th>Actions</th>
+                        </tr>
+                    </thead>
+                    <tbody>
+                        {% for question in spam_questions %}
+                        <tr id="spam-row-{{ question.id }}">
+                            <td>{{ question.category|truncatechars:12 }}</td>
+                            <td>{{ question.tutorial|truncatechars:12 }}</td>
+                            <td>{{ question.minute_range }}</td>
+                            <td>{{ question.second_range }}</td>
+                            <td>
+                                <a href="{% url 'website:get_question' question.id %}{% prettify question.title %}">
+                                    {{ question.title|truncatechars:40 }}
+                                </a>
+                            </td>
+                            <td>{{ question.date_created|date:"d-m-y" }}</td>
+                            <td>{{ question.user|truncatechars:10 }}</td>
+                            <td>
+                                <button class="btn btn-xs btn-success spam-approve" data-qid="{{ question.id }}">Approve</button>
+                                <button class="btn btn-xs btn-danger spam-reject" data-qid="{{ question.id }}">Reject</button>
+                            </td>
+                        </tr>
+                        {% empty %}
+                        <tr><td colspan="8">No spam questions pending approval.</td></tr>
+                        {% endfor %}
+                    </tbody>
+                </table>
+            </div>
         </div> <!-- /.panel-body -->
     </div> <!-- /.panel -->
 {% endblock %}
@@ -324,6 +365,41 @@ <h3 align="center">Answers</h3>
             }
             e.preventDefault();
         });
+
+        // Spam approval handlers
+        $('.spam-approve').click(function() {
+            var qid = $(this).data('qid');
+            var row = $('#spam-row-' + qid);
+
+            $.post('/ajax-spam-approve/', {
+                question_id: qid,
+                csrfmiddlewaretoken: $('[name=csrfmiddlewaretoken]').val()
+            }, function(response) {
+                if(response.success) {
+                    row.fadeOut(function() { $(this).remove(); });
+                    alert('Question approved!');
+                } else {
+                    alert('Error approving question: ' + (response.error || 'Unknown error'));
+                }
+            }, 'json');
+        });
+
+        $('.spam-reject').click(function() {
+            var qid = $(this).data('qid');
+            var row = $('#spam-row-' + qid);
+
+            $.post('/ajax-spam-reject/', {
+                question_id: qid,
+                csrfmiddlewaretoken: $('[name=csrfmiddlewaretoken]').val()
+            }, function(response) {
+                if(response.success) {
+                    row.fadeOut(function() { $(this).remove(); });
+                    alert('Question rejected as spam!');
+                } else {
+                    alert('Error rejecting question: ' + (response.error || 'Unknown error'));
+                }
+            }, 'json');
+        });
     });
     $('span').tooltip();
 </script>

website/forms.py

@@ -69,4 +69,4 @@ def __init__(self, *args, **kwargs):
 
 class AnswerQuesitionForm(forms.Form):
     question = forms.IntegerField(widget=forms.HiddenInput())
-    body = forms.CharField(widget=forms.Textarea())
+    body = forms.CharField(widget=forms.Textarea())