Web usage mining (WUM) is the application of data mining techniques to discover the knowledge hidden in the web log file, such as user access patterns from web data and for analyzing users’ behavioral patterns and website usage statistics that can be used for various website design tasks. However, the data stored in the web log file have a large amount of erroneous, misleading, and incomplete information. Preprocessing which is one of the important phases in WUM is needed to transform a log into a set of web user sessions that are suitable for analysis. A sample web log file was collected from the web server at NASA Kennedy space Centre. This study focuses on the preprocessing of the web log file methods that can be used for the task of session identification from web log file. The work in this study also produces statistical information of user session, such as: (1) total unique IPs; (2) total unique pages; (3) total sessions; (4) Session length and (5) the frequency visited pages. After preprocessing completed, the result will be used for mining user access patterns.