With the advent of big data, the number of web pages and information are increasing exponentially. Much of the information we retrieve is mixed and redundant, which affects the effectiveness of retrieval. Therefore, information retrieval has become an indispensable technology. Compared with ordinary retrieval, the retrieval of laws and regulations needs higher relevance and accuracy. Aiming at the poor retrieval effect and unreasonable results in terms of legal retrieval, this paper proposes a legal and regulation retrieval system, our work is establishing a high-quality database, removing the stop word, and increasing hierarchical retrieval. Experimental results show that the proposed method in terms of legal retrieval is more effective than general legal search systems and wide-area search systems. In the end, we complete the design and visual display of the whole retrieval system to ensure the accuracy of retrieval results and the conciseness of retrieval contents.