A data-driven integral sliding mode control scheme is proposed for a class discrete-time repetitive nonlinear system in this article. First, an iterative dynamic linearization data model is established in the iterative domain based on iterative dynamic linearization technology, which is only related to the online data of the system. Then, considering the time and iterative domain at the same time, an iterative integral sliding mode surface is designed, and an iterative integral sliding mode controller is proposed. Moreover, the stability of the proposed scheme is proved by theoretical analysis. Finally, the effectiveness of the proposed scheme is verified by simulation research. Comparative results with optimal iterative learning controller demonstrate that the proposed controller can provide the minimize the control effort and less tracking error.