Multi-view clustering aims to cluster data with multiple sources of information. Comparing with single view clustering, it is challenging to make use of the extra information embedded in multiple views. This paper presents a multi-view subspace clustering method (MSC-GL) by simultaneously combining both the global low-rank constraint and local cross topology preserving constraints. The global constraint maximizes the correlation between representational matrices while encouraging each of them to be low rank. The local constraints enable representational matrices under different views to share local structure information. An efficiently iterative algorithm is developed to minimize the proposed joint learning problem, and extensive experiments on five multi-view benchmarks demonstrate that the proposed model outperforms the state-of-the-art multi-view clustering methods.