Recently, expression signatures of exosomal long non-coding RNAs (lncRNAs) have been proposed as potential non-invasive biomarkers for cancer detection. In this study, we aimed to develop a urinary exosome (UE)-derived lncRNA panel for diagnosis and recurrence prediction of bladder cancer (BC). Quantitative real-time polymerase chain reaction (qRT-PCR) was performed to screen and evaluate the expressions of eight candidate lncRNAs in a training set (208 urine samples) and a validation set (160 urine samples). A panel consisting of three differently expressed lncRNAs (MALAT1, PCAT-1 and SPRY4-IT1) was established for BC diagnosis in the training set, showing an area under the receiver-operating characteristic (ROC) curve (AUC) of 0.854. Subsequently, the performance of the panel was further verified with an AUC of 0.813 in the validation set, which was significantly higher than that of urine cytology (0.619). In addition, Kaplan-Meier analysis suggested that the up-regulation of PCAT-1 and MALAT1 was associated with poor recurrence-free survival (RFS) of non-muscle-invasive BC (NMIBC) (p < 0.001 and p = 0.002, respectively), and multivariate Cox proportional hazards regression analysis revealed that exosomal PCAT-1 overexpression was an independent prognostic factor for the RFS of NMIBC (p = 0.018). Collectively, our findings indicated that UE-derived lncRNAs possessed considerable clinical value in the diagnosis and prognosis of BC.