This paper presents a content-aware attention network (CatNet) for action recognition task, which can leverage attention mechanism to aggregate frame-level features into a compact video-level representation. Unlike most previous methods that consider every video frame equally, our CatNet contains an attention module which can adaptively emphasize the representative frames, and thus can benefit the action recognition task. Moreover, the CatNet can take an action video with arbitrary length yet produce a compact video representation with fixed length. The attention module consists of two cascaded blocks, an adaptive attention weighting block and a content-aware weighting block. The experiments are carried on two challenging video action datasets, i.e., the UCF-101 dataset and HMDB-51 dataset. Our method achieves significantly improvements on both datasets compared with existing methods. The results show that our proposed CatNet is able to focus on the representative frames corresponding to a specific action category, and meanwhile significantly improve the recognition performance.