parse_shakespeare.py

import xml.etree.ElementTree as ET

def getDialogueList(*plays):
    dialogues = []
    for p in plays:
        root = ET.parse("shakespeare/"+p+".xml")

        playtitle = root.findtext("TITLE")
        playsubt = root.findtext("PLAYSUBT")
        print playtitle

        dialogue_by_scene = []

        acts = root.findall("ACT")
        for act in acts:
            print "    "+act.findtext("TITLE")
            scenes = act.findall("SCENE")
            for scene in scenes:
                print "        "+scene.findtext("TITLE")
                speeches = scene.findall("SPEECH")
                dialogue = ["\n".join([s.text for s in speech.findall("LINE") if s.text]) for speech in speeches]
                dialogue_by_scene.append(dialogue)
        dialogues.append(dialogue_by_scene)
        print "\n\n"
    return dialogues

if __name__ == "__main__":
    print getDialogueList("j_caesar", "hamlet")

train.py

import chatterbot
import parse_shakespeare

bot = chatterbot.ChatBot("Julius Caesar", storage_adapter="chatterbot.adapters.storage.JsonDatabaseAdapter", database="julius_caesar.db")

# dialogue = parse_shakespeare.getDialogueList("j_caesar")[0]
# lines_trained = 0
# for d in dialogue:
#     bot.train(d)
#     lines_trained += 1
#     print "Training scene", lines_trained

locked_bot = bot = chatterbot.ChatBot("Julius Caesar", storage_adapter="chatterbot.adapters.storage.JsonDatabaseAdapter", database="julius_caesar.db", read_only=True)
import time

while 1:
    query = raw_input(">")
    a = time.time()
    locked_bot.get_response(query)
    print time.time() - a