In this work, a flow-guided temporal-spatial network (FGTSN) is proposed to enhance the quality of HEVC compressed video. Specially, we first employ a motion estimation subnet via trainable optical flow module to estimate the motion flow between current frame and its adjacent frames. Guiding by the predicted motion flow, the adjacent frames are aligned to current frame. Then, a temporal encoder is designed to discover the variations between current frame and its warped frames. Finally, the reconstruction frame is generated by training the model in a multi-supervised fashion. Our method takes advantage of temporal-spatial information to enhance the compressed video Quality. Experimental results demonstrate the superior performance of our FGTSN method.