Python调用百度接口（情感倾向分析）和讯飞接口（语音识别、关键词提取）处理音频文件

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
讯飞非实时转写调用demo（语音识别）
"""
import base64
import hashlib
import hmac
import json
import os
import time import requests lfasr_host = 'http://raasr.xfyun.cn/api' # 请求的接口名
api_prepare = '/prepare'
api_upload = '/upload'
api_merge = '/merge'
api_get_progress = '/getProgress'
api_get_result = '/getResult'
# 文件分片大下52k
file_piece_sice = 10485760 # ——————————————————转写可配置参数————————————————
# 参数可在官网界面（https://doc.xfyun.cn/rest_api/%E8%AF%AD%E9%9F%B3%E8%BD%AC%E5%86%99.html）查看，根据需求可自行在gene_params方法里添加修改
# 转写类型
lfasr_type = 0
# 是否开启分词
has_participle = 'false'
has_seperate = 'true'
# 多候选词个数
max_alternatives = 0
# 子用户标识
suid = '' class SliceIdGenerator:
"""slice id生成器""" def __init__(self):
self.__ch = 'aaaaaaaaa`' def getNextSliceId(self):
ch = self.__ch
j = len(ch) - 1
while j >= 0:
cj = ch[j]
if cj != 'z':
ch = ch[:j] + chr(ord(cj) + 1) + ch[j + 1:]
break
else:
ch = ch[:j] + 'a' + ch[j + 1:]
j = j - 1
self.__ch = ch
return self.__ch class RequestApi(object):
def __init__(self, appid, secret_key, upload_file_path):
self.appid = appid
self.secret_key = secret_key
self.upload_file_path = upload_file_path # 根据不同的apiname生成不同的参数,本示例中未使用全部参数您可在官网(https://doc.xfyun.cn/rest_api/%E8%AF%AD%E9%9F%B3%E8%BD%AC%E5%86%99.html)查看后选择适合业务场景的进行更换
def gene_params(self, apiname, taskid=None, slice_id=None):
appid = self.appid
secret_key = self.secret_key
upload_file_path = self.upload_file_path
ts = str(int(time.time()))
m2 = hashlib.md5()
m2.update((appid + ts).encode('utf-8'))
md5 = m2.hexdigest()
md5 = bytes(md5, encoding='utf-8')
# 以secret_key为key, 上面的md5为msg， 使用hashlib.sha1加密结果为signa
signa = hmac.new(secret_key.encode('utf-8'), md5, hashlib.sha1).digest()
signa = base64.b64encode(signa)
signa = str(signa, 'utf-8')
file_len = os.path.getsize(upload_file_path)
file_name = os.path.basename(upload_file_path)
param_dict = {} if apiname == api_prepare:
# slice_num是指分片数量，如果您使用的音频都是较短音频也可以不分片，直接将slice_num指定为1即可
slice_num = int(file_len / file_piece_sice) + (0 if (file_len % file_piece_sice == 0) else 1)
param_dict['app_id'] = appid
param_dict['signa'] = signa
param_dict['ts'] = ts
param_dict['file_len'] = str(file_len)
param_dict['file_name'] = file_name
param_dict['slice_num'] = str(slice_num)
elif apiname == api_upload:
param_dict['app_id'] = appid
param_dict['signa'] = signa
param_dict['ts'] = ts
param_dict['task_id'] = taskid
param_dict['slice_id'] = slice_id
elif apiname == api_merge:
param_dict['app_id'] = appid
param_dict['signa'] = signa
param_dict['ts'] = ts
param_dict['task_id'] = taskid
param_dict['file_name'] = file_name
elif apiname == api_get_progress or apiname == api_get_result:
param_dict['app_id'] = appid
param_dict['signa'] = signa
param_dict['ts'] = ts
param_dict['task_id'] = taskid
param_dict['has_seperate'] = has_seperate
return param_dict # 请求和结果解析，结果中各个字段的含义可参考：https://doc.xfyun.cn/rest_api/%E8%AF%AD%E9%9F%B3%E8%BD%AC%E5%86%99.html
def gene_request(self, apiname, data, files=None, headers=None):
response = requests.post(lfasr_host + apiname, data=data, files=files, headers=headers)
result = json.loads(response.text)
if result["ok"] == 0:
# print("{} success:".format(apiname) + str(result))
print('treating...')
return result
else:
# print("{} error:".format(apiname) + str(result))
exit(0)
return result # 预处理
def prepare_request(self):
return self.gene_request(apiname=api_prepare,
data=self.gene_params(api_prepare)) # 上传
def upload_request(self, taskid, upload_file_path):
file_object = open(upload_file_path, 'rb')
try:
index = 1
sig = SliceIdGenerator()
while True:
content = file_object.read(file_piece_sice)
if not content or len(content) == 0:
break
files = {
"filename": self.gene_params(api_upload).get("slice_id"),
"content": content
}
response = self.gene_request(api_upload,
data=self.gene_params(api_upload, taskid=taskid,
slice_id=sig.getNextSliceId()),
files=files)
if response.get('ok') != 0:
# 上传分片失败
print('upload slice fail, response: ' + str(response))
return False
# print('upload slice ' + str(index) + ' success')
print('treating...')
index += 1
finally:
'file index:' + str(file_object.tell())
file_object.close()
return True # 合并
def merge_request(self, taskid):
return self.gene_request(api_merge, data=self.gene_params(api_merge, taskid=taskid)) # 获取进度
def get_progress_request(self, taskid):
return self.gene_request(api_get_progress, data=self.gene_params(api_get_progress, taskid=taskid)) # 获取结果
def get_result_request(self, taskid):
return self.gene_request(api_get_result, data=self.gene_params(api_get_result, taskid=taskid)) def all_api_request(self):
# 1. 预处理
pre_result = self.prepare_request()
taskid = pre_result["data"]
# 2 . 分片上传
self.upload_request(taskid=taskid, upload_file_path=self.upload_file_path)
# 3 . 文件合并
self.merge_request(taskid=taskid)
# 4 . 获取任务进度
while True:
# 每隔20秒获取一次任务进度
progress = self.get_progress_request(taskid)
progress_dic = progress
if progress_dic['err_no'] != 0 and progress_dic['err_no'] != 26605:
# print('task error: ' + progress_dic['failed'])
return
else:
data = progress_dic['data']
task_status = json.loads(data)
if task_status['status'] == 9:
# print('task ' + taskid + ' finished')
break
print('The task ' + taskid + ' is in processing, task status: ' + str(data))
print('processing...')
# 每次获取进度间隔20S
time.sleep(20)
# 5 . 获取结果
return self.get_result_request(taskid=taskid) def get_text_result(upload_file_path):
"""
封装该接口，获取接口返回的内容
:param upload_file_path:
:return: 识别出来的文本数据
"""
api = RequestApi(appid="xxx", secret_key="xxx", upload_file_path=upload_file_path)
return api.all_api_request() # 注意：如果出现requests模块报错："NoneType" object has no attribute 'read', 请尝试将requests模块更新到2.20.0或以上版本(本demo测试版本为2.20.0)
# 输入讯飞开放平台的appid，secret_key和待转写的文件路径
if __name__ == '__main__':
result = get_text_result('input/xxx.m4a')
print(result)
print(type(result))

python weblfasr_python3_demo.py
treating...
treating...
treating...
treating...
treating...
The task e3e3284aee4a4e3b86a4fd506960e0f2 is in processing, task status: {"status":,"desc":"音频并完成"}
processing...
treating...
The task e3e3284aee4a4e3b86a4fd506960e0f2 is in processing, task status: {"status":,"desc":"音频写中"}
processing...
treating...
treating...
{'data': '[{"bg":"480","ed":"1810","onebest":"我好高兴！","speaker":"2"},{"bg":"1820","ed":"4440ebest":"啊明天就放假了！","speaker":"1"}]', 'err_no': , 'failed': None, 'ok': }
<class 'dict'>

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
百度情感倾向分析：
get_sentiment_result 用于 demo 进行调用
# 参数 说明 描述
# log_id uint64 请求唯一标识码
# sentiment int 表示情感极性分类结果，0:负向，1:中性，2:正向
# confidence float 表示分类的置信度，取值范围[0,1]
# positive_prob float 表示属于积极类别的概率 ，取值范围[0,1]
# negative_prob float 表示属于消极类别的概率，取值范围[0,1]
"""
import json
import requests def get_sentiment_result(text):
"""
利用情感倾向分析API来获取返回数据
:param text: 输入文本
:return response: 返回的响应
"""
if text == '':
return ''
# 请求接口
url = 'https://aip.baidubce.com/oauth/2.0/token'
# 需要先获取一个 token
client_id = 'xxx'
client_secret = 'xxx'
params = {
'grant_type': 'client_credentials',
'client_id': client_id,
'client_secret': client_secret
}
headers = {'Content-Type': 'application/json; charset=UTF-8'}
response = requests.post(url=url, params=params, headers=headers).json()
access_token = response['access_token'] # 通用版情绪识别接口
url = 'https://aip.baidubce.com/rpc/2.0/nlp/v1/sentiment_classify'
# 定制版情绪识别接口
# url = 'https://aip.baidubce.com/rpc/2.0/nlp/v1/sentiment_classify_custom'
# 使用 token 调用情感倾向分析接口
params = {
'access_token': access_token
}
payload = json.dumps({
'text': text
})
headers = {'Content-Type': 'application/json; charset=UTF-8'}
response = requests.post(url=url, params=params, data=payload, headers=headers).json()
return response if __name__ == '__main__':
print(get_sentiment_result('白日放歌须纵酒，青春作伴好还乡。'))
print(get_sentiment_result('思悠悠，恨悠悠，恨到归时方始休。'))

python baidu_sentiment.py
{'log_id': , 'text': '白日放歌须纵酒，青春作伴好还乡。', 'items': [{'positive_prob': 0.537741, 'confidence': 0.245186, 'negative_prob': 0.462259, 'sentiment': }]}
{'log_id': , 'text': '思悠悠，恨悠悠，恨到归时方始休。', 'items': [{'positive_prob': 0.345277, 'confidence': 0.232717, 'negative_prob': 0.654723, 'sentiment': }]}

#!/usr/bin/python
# -*- coding: UTF-8 -*-
"""
讯飞关键词提取接口
"""
import time
import urllib.request
import urllib.parse
import json
import hashlib
import base64 # 接口地址
url = "http://ltpapi.xfyun.cn/v1/ke"
# 开放平台应用ID
x_appid = "xxx"
# 开放平台应用接口秘钥
api_key = "xxx"
# 语言文本
TEXT = "汉皇重色思倾国，御宇多年求不得。杨家有女初长成，养在深闺人未识。天生丽质难自弃，一朝选在君王侧。" def get_keyword_result(text):
"""
这是讯飞官方文档给出的示例
:param text: 输入文本
:return response: 返回对象
"""
if text == '':
return ''
body = urllib.parse.urlencode({'text': text}).encode('utf-8')
param = {"type": "dependent"}
x_param = base64.b64encode(json.dumps(param).replace(' ', '').encode('utf-8'))
x_time = str(int(time.time()))
x_checksum = hashlib.md5(api_key.encode('utf-8') +
str(x_time).encode('utf-8') +
x_param).hexdigest()
x_header = {'X-Appid': x_appid,
'X-CurTime': x_time,
'X-Param': x_param,
'X-CheckSum': x_checksum}
req = urllib.request.Request(url, body, x_header)
result = urllib.request.urlopen(req)
result = result.read()
return result.decode('utf-8') if __name__ == '__main__':
keyword_result = get_keyword_result(TEXT)
print(keyword_result)
print(type(keyword_result))

python WebLtp_python3_demo.py
{"code":"","data":{"ke":[{"score":"0.646","word":"汉皇"},{"score":"0.634","word":"御宇"},{"score":"0.633","word":"重色"},{"score":"0.632","word":"王侧"},{"score":"0.628","word":"思倾国"},{"score":"0.601","word":"自弃"},{"score":"0.600","word":"杨家"},{"score":"0.588","word":"深闺人未识"},{"score":"0.588","word":"求不得"},{"score":"0.586","word":"天生丽质"}]},"desc":"success","sid":"ltp000aed03@dx589210907749000100"}
<class 'str'>

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
这是主要的demo
流程是：
音频->讯飞语音识别API->文本
文本再作两种处理：
文本->百度情绪识别API->情绪识别的响应
文本->讯飞关键词提取API->关键词提取的响应
"""
import sys
import json
from weblfasr_python3_demo import get_text_result
from baidu_sentiment import get_sentiment_result
from WebLtp_python3_demo import get_keyword_result # 硬编码选定需要离线分析的音频
# 以下是一些测试--------------------------
# SOURCE_PATH = 'input/test.mp3'
# SOURCE_PATH = 'input/test.pcm'
# SOURCE_PATH = 'input/test.m4a'
# SOURCE_PATH = 'input/test.wav'
# 以上是一些测试--------------------------
# 或者，通过命令行参数选定需要离线分析的音频
# 如：python demo.py test.wav
SOURCE_PATH = 'input/' + sys.argv[1]
# STEP 1: 调用讯飞语音识别 API
# 获取讯飞识别出来的响应
TEXT_RESULT = get_text_result(SOURCE_PATH) def save_file(data, destin):
"""
数据持久化函数
:param data: 数据
:param destin: 目标路径
:return: None
"""
data = str(data)
if data:
with open(destin, "w", encoding='utf-8') as f:
f.write(data) def whole_method():
"""
将音频文本不作区分地提取（两个人的对话不做区分）
:return: None
"""
# 解析语音识别出来的数据
data_list = json.loads(TEXT_RESULT['data'])
# text 用于拼接
text_result = ''
for data in data_list:
text_result += data['onebest']
print('text_result:', text_result)
print('text_result completed')
# 把文本写入到文件中
save_file(text_result, 'output/text_result.txt')
# STEP 2: 情感倾向分析
# 输入文本，使用情绪识别函数获取响应
sentiment_result = get_sentiment_result(text_result)
# 保存数据
save_file(sentiment_result, 'output/sentiment_result.txt')
print('sentiment_result completed')
# STEP 3: 关键词提取
# 输入文本，调用讯飞提取关键词的接口，对文本做关键词提取
keyword_result = get_keyword_result(text_result)
# 保存数据
save_file(keyword_result, 'output/keyword_result.txt')
print('keyword_result completed') def seperate_method():
"""
将音频文本作区分地提取（区分两个人的对话）
:return: None
"""
data_list = json.loads(TEXT_RESULT['data'])
text_result1 = ''
text_result2 = ''
# 假设有两个人，把文本分别做整合
for data in data_list:
# print(data)
if data['speaker'] == '':
text_result1 += data['onebest']
else:
text_result2 += data['onebest']
print('text_result1', text_result1)
print('text_result2', text_result2)
print('text_result1 text_result2 completed')
save_file(text_result1, 'output/text_result1.txt')
save_file(text_result2, 'output/text_result2.txt')
# STEP 2: 情感倾向分析
# 输入文本，使用情绪识别函数获取响应
# A 的对话
sentiment_result1 = get_sentiment_result(text_result1)
save_file(sentiment_result1, 'output/sentiment_result1.txt')
print('result_get_result1 completed')
# B 的对话
sentiment_result2 = get_sentiment_result(text_result2)
save_file(sentiment_result2, 'output/sentiment_result2.txt')
print('result_get_result2 completed')
# STEP 3: 关键词提取
# 调用讯飞接口做文本的关键字提取
# A 的对话
keyword_result1 = get_keyword_result(text_result1)
save_file(keyword_result1, 'output/keyword_result1.txt')
print('keyword_result1 completed')
# B 的对话
keyword_result2 = get_keyword_result(text_result2)
save_file(keyword_result2, 'output/keyword_result2.txt')
print('keyword_result2 completed') if __name__ == '__main__':
if TEXT_RESULT:
whole_method()
seperate_method()

python demo.py test.mp3
treating...
treating...
treating...
treating...
treating...
The task 8552d13470ed4839b11e0f3693f296f9 is in processing, task status: {"status":,"desc":"音频合并完成"}
processing...
treating...
...
The task 8552d13470ed4839b11e0f3693f296f9 is in processing, task status: {"status":,"desc":"音频转写中"}
processing...
treating...
treating...
text_result: 喂喂你好，是xxx的机主是吧？谁？呀我是xxx的工作人员，您在今天中午12点多在我们xxx提交了xxx是吧？那怎么？...那没有关系，我说您是否办理xxx？什么有什么有关系，啊有什么有关系啊。
text_result completed
sentiment_result completed
keyword_result completed
text_result1 喂喂你好，是xxx的机主是吧？呀我是xxx的工作人员，您在今天中午12点多在我们xxx提交了xxx是吧？...那没有关系，我说您是否办理xxx？
text_result2 谁？那怎么？...什么有什么有关系，啊有什么有关系啊。
text_result1 text_result2 completed
result_get_result1 completed
result_get_result2 completed
keyword_result1 completed
keyword_result2 completed