Web Usage Mining (WUM) is the major application of data mining to the web data and analyzes the user’s visiting
activities and attains their interests by inspecting the web log files. The first and crucial step in WUM is preprocessing of log for
cleaning data, after that it can be suitable for mining purposes. The cleaning includes removal of unnecessary data such as
image files, unclear data and robots. The aim of this research is to identify Robot Requests by analyzing web server log file using
different methods such as IP address check, User agent check, Head request check, URL weight calculation and URL similarity
calculation. Web Robots are the software programs that retrieve Web resources by traversing the hyperlink structure of Web.
These robots can be used for malicious intensions; therefore they must be detected and removed from the log files.
