import requests
import re #正则表达式
#链接
url = 'https://www.ibswtan.com/70/70672/19808959.html'

res = requests.get(url)

a = res.encoding = 'utf-8'  #万国码

#提取数据
contents = re.findall('<div id="content">(.*?)</div>',res.text)
print(contents)

#自动创建文件 replace文本替换函数
with open('demo.txt','w') as f:
    for content in contents:
        f.write(content.replace('&nbsp;&nbsp;&nbsp;&nbsp;','').replace('<br/><br/>',''))

#初始化
import pyttsx3
# engine = pyttsx3.init()
# engine.say("你哈阿萨德")
# engine.runAndWait()

with open('demo.txt','r') as f:
    line = f.read()
    engine = pyttsx3.init()
    engine.say(line)
    engine.runAndWait()