One of the great challenges of the environmental diagnoses of soils contaminated with hydrocarbons is the optimization of analytical determinations. For this reason, this chapter evaluates the extraction of hydrocarbons by the Soxhlet method through the design of experiments (DOE), variating three different solvents, three soils, and three extraction times. Soil was experimentally contaminated at different concentrations, and hydrocarbons totals relying on conditions organic matter, electrical conductivity, pH and textures, amount of sample, solvents, and NaSO4, were studied. The variables were evaluated by means of an analysis of the Taguchi design and a factorial design, with the results the significant and optimal parameters of the process were determined, which were solvent type and time (10 hours and dielectric constant of 9). Also, the model discards the soil properties. These results will save time and resources, and they reduce errors.