Search engine is one of the most important tools for managing the massive amount of distributed web content. Web spamming tries to deceive search engines to rank some pages higher than they deserve. Many methods have been proposed to combat web spamming and to detect spam pages. One basic one is using classification, i.e., learning a classification model for classifying web pages to spam or non-spam. This work tries to select the best feature set for classification of web spam using imperialist competitive algorithm and genetic algorithm. Imperialist competitive algorithm is a novel optimization algorithm that is inspired by socio-political process of imperialism in the real world. Experiments are carried out on WEBSPAM-UK2007 data set, which show feature selection improves classification accuracy, and imperialist competitive algorithm outperforms GA.