A novel computational spectral analysis method for multi-component drugs is proposed. The method applies the wavelet denoise processing technique to principle component regression(PCR). Since noise in the original spectral data is effectively filtered, the performance of PCR is obviously improved. A typical example in multi-component drug analysis has been used to verify the effectiveness of the novel algorithm. Compared with that obtained by PCR, the average of mean relative error which obtained by PCRW decreases to 0.46% from 1.48%.