Concerns regarding the potential harm associated with endocrine dysfunction are increasing, particularly in children, due to the immaturity of their metabolic system and skin barrier. In this work, parabens, which are esters widely used as preservatives in cosmetics, were quantified in commercial samples of diaper rash cream. For this purpose, a green and efficient liquid–liquid microextraction (LLME) method was accomplished using a deep eutectic solvent (DES). To enhance recovery rates, the extraction parameters were optimized using a central composite design (CCD) on blank matrix samples spiked. The quantification was based on excitation-emission fluorescence spectroscopy, combined with parallel factor analysis (PARAFAC) decomposition, which proved be an advantageous tool to solve the overlap of uncalibrated constituents in the complex matrix. The PARAFAC modeling strategy provided satisfactory results within a linear range response of 100–1300 ng g−1, with LOD equal to 23 ng g−1. A validation set, with various proportions of methyl, ethyl, propyl, and butyl paraben standards, was used to validate the calibration model, resulting in root mean square error (RMSE) and relative error of prediction (REP) values of 32 ng g−1 and 4.5%, respectively. Moreover, acceptable root mean square error of prediction (RMSEP) and REP values (105 ng g−1 and 15%, respectively) were obtained, when a set of blank matrix samples spiked was applied. The proposed method was successfully applied to quantify total paraben content in commercial samples of diaper rash cream, yielding recoveries ranging from 83% to 125%. The method proved to be sensitive, accurate, and green, as it significantly reduced the consumption of organic solvents. Furthermore, it could serve as an alternative for the determination of preservatives in complex cosmetic samples.