The market for dried wild edible mushrooms is characterized by quality discrepancies and species disorganization, which are a matter of concern. The feasibility of using fourier transform near-infrared (FT-NIR) spectroscopy with chemometrics to predict the total phenol content and identify species was investigated in dried bolete. For the determination of total phenolic content, FT-NIR spectral acquisition, and two-dimensional correlation spectroscopy (2DCOS) image acquisition, five common species of dried edible bolete (n = 144) were utilized. The results showed that partial least squares regression (PLSR) combined with Fourier transform near-infrared spectroscopy could predict the total phenol content of dried boletes, with the best prediction coefficient of determination (R2p) = 0.79. The partial least squares discriminant analysis (PLS-DA) model accurately identified Phlebopus portentosus, with Matthews correlation coefficient (MCC), Precision (PRC), Sensitivity (SEN), and Specificity (SPE) all being 1. The support vector machines (SVM) model is performed optimally to identify processing edible bolete (Lanmaoa asiatica) with an accuracy of 100 % in the test set. 2DCOS images combined with the residual convolutional neural networks (ResNet) model demonstrated the feasibility of FT-NIR full spectral bands (10,000–4,000 cm−1) and characteristic spectral bands (6,500–4,000 cm−1) for species identification of boletes. The method applies to the case of consistent or inconsistent sample sizes between groups, with an accuracy of 1.00 for both the training and test sets. The study serves as a rapid, non-invasive, and convenient method for real-time evaluation of the quality of dried edible bolete in the market.