Automatic processing of websites is of great importance for applications such as search engine that extract information from web pages. Search engines use meta tag values when classifying pages of websites. Meta tag names can change for different languages. For example, for login page, entries such as login, login page or giris, giris sayfasi may change from language to language. When the websites are examined, it can be seen that each of the pages created for the same purpose has similar designs. In this study, a deep learning based model was proposed for functional classification of web pages, regardless of language. Transfer learning was used to reduce the cost during the feature extraction process from recorded web page images. Finally, the results of two different experiments are presented for show the effectiveness of the proposed method in the classification of web pages according to their functions.