In this work, we present a catalog of cataclysmic variables (CVs) identified from the sixth data release (DR6) of the Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST). To single out the CV spectra, we introduce a novel machine-learning algorithm called UMAP to screen out a total of 169509 H{alpha} emission spectra, and obtain a classification accuracy of the algorithm of over 99.6% from the cross-validation set. We then apply the template-matching program PyHammer v2.0 to the LAMOST spectra to obtain the optimal spectral type with metallicity, which help us identify the chromospherically active stars and potential binary stars from the 169509 spectra. After visually inspecting all of the spectra, we identify 323 CV candidates from the LAMOST database, among them 52 objects are new. We further classify the new CV candidates in subtypes based on their spectral features, including five DN subtypes during outbursts, five NL subtypes, and four magnetic CVs (three AM Her type and one IP type). We also find two CVs that have been previously identified by photometry and confirm their previous classification with the LAMOST spectra.