树莓派开发自己的智能语音系统-实现播报新闻

上一篇介绍如何利用百度音乐的API构建互动的音乐播放器，接下来我们继续增加播报新闻的功能，这个实现起来也不难，如果你对网络爬虫有所研究，应该还可以实现很多你想要实现的功能，你可以定制化你需要的信息，让智能音箱帮你播报给你听。

基本的逻辑就是，编写一个爬虫函数，抓取百度新闻页面的新闻内容，返回文本文件给百度语音合成音频，然后调用播放器播放就是了。直接上代码：

import urllib2, urllib
#from urllib import request
import re
from voice import Voice
import voiceAPI
import random
voice = Voice()
baiduAPI = voiceAPI.BaiDuAPI()
baiduAPI.getToken()
def dialogue(text):
 try:
 url = baiduAPI.voiceSynthesis(text)
 except:
 url1 = "audio/cnnerror.mp3"
 os.system('mpg123 "%s"'%url1)
 return
 voice.playVoice(url)
def getNews_guonei(): #获取国内新闻
 url = "http://news.baidu.com/guonei"
 response = urllib2.urlopen(url)
 html = response.read().decode('utf-8')
 pattern_of_instant_news = re.compile('<div id="instant-news.*?</div>',re.S)
 instant_news_html = re.findall(pattern_of_instant_news,html)[0]
 pattern_of_news = re.compile('<li><a.*?>(.*?)</a></li>',re.S)
 news_list = re.findall(pattern_of_news,instant_news_html)
 for news in news_list:
 #print(news)
 dialogue(news) #播放新闻
 #return news
def getNews_guoji(): #获取国际新闻
 url = "http://news.baidu.com/guoji"
 response = urllib2.urlopen(url)
 html = response.read().decode('utf-8')
 pattern_of_instant_news = re.compile('<div id="instant-news.*?</div>',re.S)
 instant_news_html = re.findall(pattern_of_instant_news,html)[0]
 pattern_of_news = re.compile('<li><a.*?>(.*?)</a></li>',re.S)
 news_list = re.findall(pattern_of_news,instant_news_html)
 for news in news_list:
 #print(news)
 dialogue(news)
def getNews_mil(): #获取军事新闻
 url = "http://news.baidu.com/mil"
 response = urllib2.urlopen(url)
 html = response.read().decode('utf-8')
 pattern_of_instant_news = re.compile('<div id="instant-news.*?</div>',re.S)
 instant_news_html = re.findall(pattern_of_instant_news,html)[0]
 pattern_of_news = re.compile('<li><a.*?>(.*?)</a></li>',re.S)
 news_list = re.findall(pattern_of_news,instant_news_html)
 for news in news_list:
 #print(news)
 dialogue(news)
 
def getNews_caijing(): #播报财经新闻
 url = "http://news.baidu.com/finance"
 response = urllib2.urlopen(url)
 html = response.read().decode('utf-8')
 pattern_of_instant_news = re.compile('<div id="instant-news.*?</div>',re.S)
 instant_news_html = re.findall(pattern_of_instant_news,html)[0]
 pattern_of_news = re.compile('<li><a.*?>(.*?)</a></li>',re.S)
 news_list = re.findall(pattern_of_news,instant_news_html)
 for news in news_list:
 #print(news)
 dialogue(news)
def getNews_yule(): #播报娱乐新闻
 url = "http://news.baidu.com/ent"
 response = urllib2.urlopen(url)
 html = response.read().decode('utf-8')
 pattern_of_instant_news = re.compile('<div id="instant-news.*?</div>',re.S)
 instant_news_html = re.findall(pattern_of_instant_news,html)[0]
 pattern_of_news = re.compile('<li><a.*?>(.*?)</a></li>',re.S)
 news_list = re.findall(pattern_of_news,instant_news_html)
 for news in news_list:
 #print(news)
 dialogue(news)
 
def getNews_tech(): #播报科技新闻
 url = "http://news.baidu.com/tech"
 response = urllib2.urlopen(url)
 html = response.read().decode('utf-8')
 pattern_of_instant_news = re.compile('<div id="instant-news.*?</div>',re.S)
 instant_news_html = re.findall(pattern_of_instant_news,html)[0]
 pattern_of_news = re.compile('<li><a.*?>(.*?)</a></li>',re.S)
 news_list = re.findall(pattern_of_news,instant_news_html)
 for news in news_list:
 #print(news)
 dialogue(news)
 
def getNews_net(): #播报互联网新闻
 url = "http://news.baidu.com/internet"
 response = urllib2.urlopen(url)
 html = response.read().decode('utf-8')
 pattern_of_instant_news = re.compile('<div id="internet_news.*?</div>',re.S)
 instant_news_html = re.findall(pattern_of_instant_news,html)[0]
 pattern_of_news = re.compile('<li><a.*?>(.*?)</a></li>',re.S)
 news_list = re.findall(pattern_of_news,instant_news_html)
 for news in news_list:
 #print(news)
 dialogue(news)

只需要把播报新闻的函数放到主程序中调用即可。顺便也整一个笑话的爬虫，至于怎么让智能音箱播报给你听，自己开动脑筋，按照上面播报新闻的思路应该也很容易完成。

糗事爬虫代码清单：

# -*- coding:utf-8 -*-
import requests
from bs4 import BeautifulSoup
from itertools import *
import time

#伪装成浏览器
user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
headers = {'User-Agent': user_agent}

def get_url(start, end):
 #根据网址结构构造爬取多页的函数
 for num in (start, end):
 url = 'http://www.qiushibaike.com/text/page/'+str(num)+'/'
 get(url)
 time.sleep(3)

def get(url):
 #删选出搞笑数大于1000并且评论在十条以上的段子
 wb = requests.get(url,headers = headers)
 soup = BeautifulSoup(wb.text,'lxml')
 contents = soup.select('a > div[class="content"] > span')
 marks = soup.select('div > span > i')
 comments = soup.select('div > span > a > i')
 for content, mark, comment in zip(contents, marks, comments):
 if int(mark.get_text()) > 1000 and int(comment.get_text()) > 10:
 print (content.get_text())

关于新闻类的播报实现，就介绍到这里，回去自己动手比什么都有成就感。智能音箱的唤醒除了用语音唤醒之外，其实你可以通过传感器来唤醒，比如加一个定时器，到点自动播放你喜欢的节目，或者加上一个红外传感器，当人接近时，启动对话，等等，在树莓派上，你可以定制你自己喜欢的方式来交互，只有想不到，没有什么不可能的。