import pickle import os import shutil from langchain.document_loaders import BSHTMLLoader, DirectoryLoader !git clone https://github.com/TheMITTech/shakespeare from glob import glob files = glob("./shakespeare/**/*.html") os.mkdir('./data') destination_folder = './data/' for html_file in files: shutil.move(html_file, destination_folder + html_file.split("/"[-1])) bshtml_dir_loader = DirectoryLoader('./data/', loader_cls = BSHTMLLoader) data = bshtml_dir_loader.load() with open("shakespeare.pkl", "wb") as fp: pickle.dump(data, fp)