带有kivy GUI的语音助手

Question

大家好，我正在做一个使用python的语音助手项目，我想为这个助手开发一个只有两个按钮start和exit的kivy GUI。我做按钮，但我有麻烦连接按钮与助理脚本我在kivy上太业余了，为什么请l将非常感谢这些是我的文件: main.py (助理脚本)：

import speech_recognition as sr  # recognise speech
import playsound  # to play an audio file
from gtts import gTTS  # google text to speech
import random
from time import ctime  # get time details
import webbrowser  # open browser
import ssl
import certifi
import time
import os  # to remove created audio files
from PIL import Image
import subprocess
import pyautogui  # screenshot
import pyttsx3
import bs4 as bs
import urllib.request


class person:
    name = ''

    def setName(self, name):
        self.name = name


class asis:
    name = ''

    def setName(self, name):
        self.name = name


def there_exists(terms):
    for term in terms:
        if term in voice_data:
            return True


def engine_speak(text):
    text = str(text)
    engine.say(text)
    engine.runAndWait()


r = sr.Recognizer()  # initialise a recogniser


# listen for audio and convert it to text:
def record_audio(ask=""):
    with sr.Microphone() as source:  # microphone as source
        if ask:
            engine_speak(ask)
        audio = r.listen(source, 5, 5)  # listen for the audio via source
        print("Done Listening")
        voice_data = ''
        try:
            voice_data = r.recognize_google(audio)  # convert audio to text
        except sr.UnknownValueError:  # error: recognizer does not understand
            engine_speak('I did not get that')
        except sr.RequestError:
            engine_speak('Sorry, the service is down')  # error: recognizer is not connected
        print(">>", voice_data.lower())  # print what user said
        return voice_data.lower()


# get string and make a audio file to be played
def engine_speak(audio_string):
    audio_string = str(audio_string)
    tts = gTTS(text=audio_string, lang='en')  # text to speech(voice)
    r = random.randint(1, 20000000)
    audio_file = 'audio' + str(r) + '.mp3'
    tts.save(audio_file)  # save as mp3
    playsound.playsound(audio_file)  # play the audio file
    print(asis_obj.name + ":", audio_string)  # print what app said
    os.remove(audio_file)  # remove audio file


def respond(voice_data):
    # 1: greeting
    if there_exists(['hey', 'hi', 'hello']):
        greetings = ["hey, how can I help you" + person_obj.name, "hey, what's up?" + person_obj.name,
                     "I'm listening" + person_obj.name, "how can I help you?" + person_obj.name,
                     "hello" + person_obj.name]
        greet = greetings[random.randint(0, len(greetings) - 1)]
        engine_speak(greet)

    # 2: name
    if there_exists(["what is your name", "what's your name", "tell me your name"]):
        if person_obj.name:
            engine_speak("whats with my name ")
        else:
            engine_speak("my name is Jexi . what's your name?")

    if there_exists(["my name is"]):
        person_name = voice_data.split("is")[-1].strip()
        engine_speak("okay, i will remember that " + person_name)
        person_obj.setName(person_name)  # remember name in person object

    if there_exists(["your name should be"]):
        asis_name = voice_data.split("be")[-1].strip()
        engine_speak("okay, i will remember that my name is " + asis_name)
        asis_obj.setName(asis_name)  # remember name in asis object

    

    # 3: greeting
    if there_exists(["how are you", "how are you doing"]):
        engine_speak("I'm very well, thanks for asking " + person_obj.name)

    # 4: time
    if there_exists(["what's the time", "tell me the time", "what time is it"]):
        time = ctime().split(" ")[3].split(":")[0:2]
        if time[0] == "00":
            hours = '12'
        else:
            hours = time[0]
        minutes = time[1]
        time = hours + " hours and " + minutes + "minutes"
        engine_speak(time)

    # 5: search google
    if there_exists(["search for"]) and 'youtube' not in voice_data:
        search_term = voice_data.split("for")[-1]
        url = "https://google.com/search?q=" + search_term
        webbrowser.get().open(url)
        engine_speak("Here is what I found for" + search_term + "on google")

    # 6: search youtube
    if there_exists(["youtube"]):
        search_term = voice_data.split("for")[-1]
        url = "https://www.youtube.com/results?search_query=" + search_term
        webbrowser.get().open(url)
        engine_speak("Here is what I found for " + search_term + "on youtube")

    # 7: get stock price
    if there_exists(["price of"]):
        search_term = voice_data.split("for")[-1]
        url = "https://google.com/search?q=" + search_term
        webbrowser.get().open(url)
        engine_speak("Here is what I found for " + search_term + " on google")

    # 8 time table
    if there_exists(["show my time table"]):
        im = Image.open(r"D:\WhatsApp Image 2019-12-26 at 10.51.10 AM.jpeg")
        im.show()

    # 9 weather
    if there_exists(["weather"]):
        search_term = voice_data.split("for")[-1]
        url = "https://www.google.com/search?sxsrf=ACYBGNSQwMLDByBwdVFIUCbQqya-ET7AAA%3A1578847393212&ei=oUwbXtbXDN-C4-EP-5u82AE&q=weather&oq=weather&gs_l=psy-ab.3..35i39i285i70i256j0i67l4j0i131i67j0i131j0i67l2j0.1630.4591..5475...1.2..2.322.1659.9j5j0j1......0....1..gws-wiz.....10..0i71j35i39j35i362i39._5eSPD47bv8&ved=0ahUKEwiWrJvwwP7mAhVfwTgGHfsNDxsQ4dUDCAs&uact=5"
        webbrowser.get().open(url)
        engine_speak("Here is what I found for on google")

    # 10 stone paper scisorrs
    if there_exists(["game"]):
        voice_data = record_audio("choose among rock paper or scissor")
        moves = ["rock", "paper", "scissor"]

        cmove = random.choice(moves)
        pmove = voice_data

        engine_speak("The computer chose " + cmove)
        engine_speak("You chose " + pmove)
        # engine_speak("hi")
        if pmove == cmove:
            engine_speak("the match is draw")
        elif pmove == "rock" and cmove == "scissor":
            engine_speak("Player wins")
        elif pmove == "rock" and cmove == "paper":
            engine_speak("Computer wins")
        elif pmove == "paper" and cmove == "rock":
            engine_speak("Player wins")
        elif pmove == "paper" and cmove == "scissor":
            engine_speak("Computer wins")
        elif pmove == "scissor" and cmove == "paper":
            engine_speak("Player wins")
        elif pmove == "scissor" and cmove == "rock":
            engine_speak("Computer wins")

    # 11 toss a coin
    if there_exists(["toss", "flip", "coin"]):
        moves = ["head", "tails"]
        cmove = random.choice(moves)
        engine_speak("The computer chose " + cmove)

    # 12 calc
    if there_exists(["plus", "minus", "multiply", "divide", "power", "+", "-", "*", "/"]):
        opr = voice_data.split()[1]

        if opr == '+':
            engine_speak(int(voice_data.split()[0]) + int(voice_data.split()[2]))
        elif opr == '-':
            engine_speak(int(voice_data.split()[0]) - int(voice_data.split()[2]))
        elif opr == 'multiply':
            engine_speak(int(voice_data.split()[0]) * int(voice_data.split()[2]))
        elif opr == 'divide':
            engine_speak(int(voice_data.split()[0]) / int(voice_data.split()[2]))
        elif opr == 'power':
            engine_speak(int(voice_data.split()[0]) ** int(voice_data.split()[2]))
        else:
            engine_speak("Wrong Operator")

    # 13 screenshot
    if there_exists(["capture", "my screen", "screenshot"]):
        myScreenshot = pyautogui.screenshot()
        myScreenshot.save('D:/screenshot/screen.png')

        # 14 to search wikipedia for definition
    if there_exists(["definition of"]):
        definition = record_audio("what do you need the definition of")
        url = urllib.request.urlopen('https://en.wikipedia.org/wiki/' + definition)
        soup = bs.BeautifulSoup(url, 'lxml')
        definitions = []
        for paragraph in soup.find_all('p'):
            definitions.append(str(paragraph.text))
        if definitions:
            if definitions[0]:
                engine_speak('im sorry i could not find that definition, please try a web search')
            elif definitions[1]:
                engine_speak('here is what i found ' + definitions[1])
            else:
                engine_speak('Here is what i found ' + definitions[2])
        else:
            engine_speak("im sorry i could not find the definition for " + definition)

    if there_exists(["exit", "quit", "goodbye"]):
        engine_speak("bye")
        exit()


time.sleep(1)

person_obj = person()
asis_obj = asis()
asis_obj.name = 'kiki'
engine = pyttsx3.init()

while (1):
    voice_data = record_audio("Recording")  # get the voice input
    print("Done")
    print("Q:", voice_data)
    respond(voice_data)  # respond

kv.py (用于图形用户界面)：

from kivy import Config
Config.set('graphics', 'multisamples', '0')
Config.set('graphics', 'width', '360')
Config.set('graphics', 'height', '600')
import os
os.environ['KIVY_GL_BACKEND'] = 'angle_sdl2'
import kivy
kivy.require('1.9.0')
from kivy.app import App
from kivy.uix.label import Label
from kivy.uix.gridlayout import GridLayout
from kivy.uix.textinput import TextInput
from kivy.uix.button import Button
from kivy.uix.widget import Widget
from kivy.uix.boxlayout import BoxLayout
from kivy.core.window import Window

import random
from kivy.uix.boxlayout import BoxLayout
from kivy.uix.textinput import TextInput

# Window.clearcolor = (237, 235, 235, 235)
# create a background class which inherits the boxlayout class 
class Background(BoxLayout): 
    def __init__(self, **kwargs): 
        super().__init__(**kwargs) 
    pass
  
# Create App class with name of your app 
class SampleApp(App): 
  
# return the Window having the background template. 
    def build(self): 
        return Background() 

  
# run app in the main function 
if __name__ == '__main__': 
    SampleApp().run() 

和sample.kv文件：

#:kivy 1.0
<Background>: 
    id: main_win 
    orientation: "vertical"
    spacing: 10
    space_x: self.size[0]/3


    canvas.before: 
        Color: 
            rgba: (1, 1, 1, 1) 
        Rectangle: 
            source:'back1.jpg'
            size: root.width, root.height 
            pos: self.pos 


    Button: 
        text: " Start "
        pos_hint :{'center_x':0.5, 'center_y':0} 
        size_hint: .26,0
        background_color:(1, 1, 1, 1)
        on_press:
            #




    Button: 
        text: " exit "
        pos_hint :{'center_x':0.5, 'center_y':0} 
        size_hint: .26,0
        background_color:(1, 1, 1, 1)
        on_press:
            #

Answer 1

它不会工作，因为像time，os这样的库是为windows编写的。如果你尝试转换它，将会崩溃。