Phishing (also known as online phishing) is an online criminal. Attackers use a fake webpage that imitates trusted websites to steal sensitive personal information such as passwords and credit card details. In this paper, we propose an application named Freeze-Phish, which uses Python to build a web crawler to collect information such as hyperlinks from the website. In addition, we build a brand word and suspicious word database by editing distance algorithms like Levenshtein distance and Hamming distance to compare the difference between the words in the website URL and the suspicious one. Then, we use a neural network to train our model and export our code as executable code(.exe) so that our users can use our code more easily to detect suspicious websites. Compared to other methods, our model’s accuracy is about 97\% true positive rate, and the average execution time is 21.3 seconds.