- A New Heuristic Based Phishing Detection Approach Utilizing Selenium Web-driver
- Publication at University of Tartu
Use Python 3.6
pip install -r requirements.txt
Built With:
- Selenium Selenium web driver
- Alexa_scrapper Scrapper for Alexa to get new Legit webpages
- Google_scrapper Scrapper for google
- MongoDB Main database
- InfluxDB Logging Database
- Graphana Graph server for Influx db to show log data
- Dnspython Dns package for python
- Whois whois python package
Scrapping login pages from google
GoogleScraper -m http --keyword "login" -n 10 -p 1000 --num-workers 10 --search-engines "google" --output-filename legit.json
scrapping Phishing pages from phishtank
cd scraper
./scrapper.sh
python phish_detect.py
Run Graphana and check results
http://localhost:3306