In this paper, we propose a novel approach to enhancing web proxy caching, an approach that integrates content management with performance tuning techniques. We first develop a hierarchical model for management of web data, which consists of physical pages, logical pages and topics corresponding to different abstraction levels. Content management based on this model enables active utilization of the cached web contents. By defining priority on each abstraction level, the cache manager can make replacement decisions on topics, logical pages, and physical pages hierarchically. As a result, a cache can always keep the most relevant, popular, and high-quality content. To verify the proposed approach, we have designed a content-aware replacement algorithm, LRU-SP+. We evaluate the algorithm through preliminary experiments. The results show that content management can achieve 30% improvement of caching performance in terms of hit ratios and profit ratios (considering significance of topics) compared to content-blind schemes.