Initial fix

Author: sannjayy

.gitignore

@@ -1,3 +1,4 @@
 zenv/
 __pycache__/
-logs/
+
+logs.log

README.md

@@ -1,3 +1,75 @@
 # Python Phishing URL Detection
 ---
-Python 3.12.3
+**Python 3.11.9 _(Currently Using)_**
+
+
+## How to Run?
+
+- Clone or download [python-phishing-url-detection](https://github.com/sannjayy/python-phishing-url-detection) 
+
+`git clone [email protected]:sannjayy/python-phishing-url-detection.git`
+
+
+- Create a virtual environment
+```bash
+python -m venv zenv
+source zenv/Scripts/activate # Windows
+source zenv/bin/activate # Mac
+```
+
+
+- Install basic requirements
+```bash
+pip install -r requirements.txt
+
+# OR INITIAL INSTALLATION 
+pip install --upgrade pip
+pip install --upgrade setuptools
+
+pip install pandas whois httpx
+pip install pycaret # It will take sometime.
+```
+
+### Replace Domain
+
+```python
+if __name__ == "__main__": 
+    phishing_url_1 = 'https://bafybeifqd2yktzvwjw5g42l2ghvxsxn76khhsgqpkaqfdhnqf3kiuiegw4.ipfs.dweb.link/'
+    phishing_url_2 = 'http://about-ads-microsoft-com.o365.frc.skyfencenet.com'
+    real_url_1 = 'https://chat.openai.com'
+    real_url_2 = 'https://github.com/'
+    
+    
+    print(predict(phishing_url_1))
+    print(predict(phishing_url_2))
+    print(predict(real_url_1))
+    print(predict(real_url_2))
+```
+
+### To Run
+
+```bash
+python main.py
+
+
+# OUTPUT: {'prediction_label': 0, 'prediction_score': 68.39} 
+
+# 0 = False | 1 True
+```
+
+
+
+
+--- 
+---
+
+- 🌏 [GitHub Repo](https://github.com/sannjayy/python-phishing-url-detection) 
+- 🌏 [Website](https://www.sanjaysikdar.dev) 
+- 📫 <[email protected]>
+- 📖 [read.sanjaysikdar.dev](https://read.sanjaysikdar.dev)
+- 📦 [pypi releases](https://pypi.org/user/sannjayy/) | [npm releases](https://www.npmjs.com/~sannjayy)
+
+---
+
+[![](https://img.shields.io/github/followers/sannjayy?style=social)](https://github.com/sannjayy)  
+Developed with ❤️ by *[sanjaysikdar.dev](https://www.sanjaysikdar.dev)*.

extractorFunctions.py

@@ -1,8 +1,7 @@
 # importing required packages for Address Bar Based feature Extraction
-from urllib.parse import urlparse,urlencode, unquote
+from urllib.parse import urlparse, urlencode, unquote
 import re
 # importing required packages for Domain Based Feature Extraction
-import whois
 from datetime import datetime
 
 

featureExtractor.py

@@ -42,7 +42,7 @@ def featureExtraction(url):
 
   features.append(ef.has_unicode(url)+ef.haveAtSign(url)+ef.havingIP(url))
 
-  with open('pca_model.pkl', 'rb') as file:
+  with open('model/pca_model.pkl', 'rb') as file:
     pca = pk.load(file)
 
   #converting the list to dataframe

main.py

@@ -0,0 +1,32 @@
+from featureExtractor import featureExtraction
+from pycaret.classification import load_model, predict_model
+
+model = load_model('model/phishingdetection')
+
+
+def predict(url):
+    data = featureExtraction(url)
+    result = predict_model(model, data=data)
+    
+    # Get the prediction score for the positive class (Phishing)
+    prediction_score = result['prediction_score'][0]  
+    prediction_label = result['prediction_label'][0]  
+    # domain_age = result['Domain_Age'][0]  
+    # print('Result -> ', url)
+    
+    return {
+        'prediction_label': prediction_label,
+        'prediction_score': prediction_score * 100,
+    }
+
+if __name__ == "__main__": 
+    phishing_url_1 = 'https://bafybeifqd2yktzvwjw5g42l2ghvxsxn76khhsgqpkaqfdhnqf3kiuiegw4.ipfs.dweb.link/'
+    phishing_url_2 = 'http://about-ads-microsoft-com.o365.frc.skyfencenet.com'
+    real_url_1 = 'https://chat.openai.com'
+    real_url_2 = 'https://github.com/'
+    
+    
+    print(predict(phishing_url_1))
+    print(predict(phishing_url_2))
+    print(predict(real_url_1))
+    print(predict(real_url_2))

pca_model.pkl renamed to model/pca_model.pkl

@@ -8,7 +8,6 @@ numpy==1.26.4
 pandas==2.2.2
 python-dateutil==2.9.0.post0
 pytz==2024.1
-regex==2024.4.16
 six==1.16.0
 sniffio==1.3.1
 tzdata==2024.1