In this information era, the number of websites in the Internet has dramatically increased over a few years. Any information and services can be retrieved from the website. However, the most valuable content of the website is still a text which is related to the topic or category of the websites. But there has only few researches focusing on categorizing Thai language information. The rest of researches which focus on Thai language information do not use the automatic system. Moreover, the complexity of the algorithms and computation time are high. These models are not flexible to add any new terms that occur all the time. In this paper, we propose the automatic keyword extraction system and Thai website categorization system which can automatically update the dictionary and categorize website in Thai. The dictionary is a collection of vector which is created from the automatic keyword extraction system. The result in term of accuracy shows that our system can yield the F-measure up to 0.96.