A new method for direction finding with partly calibrated uniform linear arrays (ULAs) is presented. It is based on the conventional estimation of signal parameters via rotational invariance techniques (ESPRIT) by modeling the imperfections of the ULAs as gain and phase uncertainties. For a fully calibrated array, it reduces to the conventional ESPRIT algorithm. Moreover, the direction-of-arrivals (DOAs), unknown gains, and phases of the uncalibrated sensors can be estimated in closed form without performing a spectral search. Hence, it is computationally very attractive. The Cramér-Rao bounds (CRBs) of the partly calibrated ULAs are also given. Simulation results show that the root mean squared error (RMSE) performance of the proposed algorithm is better than the conventional methods when the number of uncalibrated sensors is large. It also achieves satisfactory performance even at low signal-to-noise ratios (SNRs).