With the rapid growth of the e-commerce landscape, classifying e-commerce merchants has become an important task as it is an integral part of various processes in e-commerce. One of the examples is merchant on boarding, where the category of an e-commerce merchant has proven to be a good indicator of the risk of the merchant. However, since most of e-commerce businesses do not have brick-and-mortar stores from which we can assess it directly, the only source of information regarding the merchant itself is its website. Thus, we can view this problem as a web classification problem, where we classify e-commerce websites into a category. In this research, we aim to build an end-to-end classification system for e-commerce websites. There are a few challenges such as the number of pages to be processed, imbalanced dataset, and the language of e-commerce websites that can be mixed language. We built a website classification system and experimented with case study of Indonesian and English e-commerce webs, that are classified into 37 different categories. Our best result achieved an F-score of 0.83.