Upload main.py

main.py

@@ -0,0 +1,54 @@
+import pandas as pd
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.model_selection import train_test_split
+from sklearn.naive_bayes import MultinomialNB
+from sklearn.metrics import accuracy_score
+import nltk
+from nltk.corpus import stopwords
+import re
+
+# Download NLTK stopwords
+nltk.download('stopwords')
+
+# Load dataset
+# Assuming you have a CSV file with 'url' and 'label' columns
+data = pd.read_csv('malicious_phish.csv')
+
+# Preprocess URLs
+def preprocess_url(url):
+    url = re.sub(r"http\S+", "", url)  # Remove http links
+    url = re.sub(r"\d+", "", url)      # Remove digits
+    url = re.sub(r"\W", " ", url)      # Remove non-word characters
+    url = url.lower()                  # Convert to lowercase
+    return url
+
+data['url'] = data['url'].apply(preprocess_url)
+
+# Split data into training and testing sets
+X = data['url']
+y = data['type']
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+# Vectorize URLs using TF-IDF
+vectorizer = TfidfVectorizer(stop_words=stopwords.words('english'))
+X_train_tfidf = vectorizer.fit_transform(X_train)
+X_test_tfidf = vectorizer.transform(X_test)
+
+# Train a Naive Bayes classifier
+model = MultinomialNB()
+model.fit(X_train_tfidf, y_train)
+
+# Predict and evaluate
+y_pred = model.predict(X_test_tfidf)
+accuracy = accuracy_score(y_test, y_pred)
+print(f"Accuracy: {accuracy * 100:.2f}%")
+
+# Function to predict if a URL is malicious
+def predict_url(url):
+    processed_url = preprocess_url(url)
+    vectorized_url = vectorizer.transform([processed_url])
+    prediction = model.predict(vectorized_url)
+    return prediction[0]
+
+# Example usage
+print(predict_url("br-icloud.com.br"))