The past few years have witnessed the growing interest in vehicular ad hoc networks(VANETs) and their potential applications for Internet of Things (IoT). Since the mobility model is crucial to simulation based researches of VANET, using a realistic mobility model can ensurethe consistency between simulation results and real deployments. Although there are many mobility models characterizing the movement of mobile nodes, none of them consider the behaviorof vehicles in a metropolitan scenario. In this paper, we present our study of extracting a mobility model for VANET from a large amount of real taxi GPS trace data. In order to capture charac-teristics of the urban vehicle network from microscopic to macroscopic aspects, we design three parameters and extract their values from the GPS trace data. Using this mobility model, we cangenerate the synthetic trace to simulate the movement of taxis in the urban area of a metropolis. The validation is carried through extensive comparisons between the synthetic trace and the realtrace. The results show that our mobility model has a good approximation with the real scenario.