itchat个人练习 语音与文本图灵测试例程

 1 import binascii
 2 import hashlib
 3 import hmac
 4 import urllib.parse
 5 import urllib.request
 6 import time
 7 import random
 8 import base64
 9 
10 def asr(msg):
11     msg[‘Text‘](msg[‘FileName‘])#保存mp3语音
12     timeData = str(int(time.time())) # 时间戳
13     nonceData = int(random.random()*10000) # Nonce，官网给的信息：随机正整数，与 Timestamp 联合起来， 用于防止重放攻击
14     with open(msg[‘FileName‘], ‘rb‘) as f:
15         voiceData = f.read()#读取mp3语音，获得byte数据，格式是b‘\x..‘
16     os.remove(msg[‘FileName‘])#删除mp3语音
17     DataLenData = len(voiceData)#读取未base64编码之前的文件长度
18     tmp = int(timeData)#time stamp
19     signDictData = {#需要注意的是字典的key值要按照ascii码升序排序，并不一定是字典序，可以使用sorted(signDictData.keys())来查看ascii码排序结果
20         ‘Action‘ : actionData,
21         ‘Data‘: base64.b64encode(voiceData).decode(‘utf8‘),#base64编码，编码后是二进制，再用decode解码
22         # ‘Data‘: voiceData,
23         ‘DataLen‘: DataLenData,
24         ‘EngSerViceType‘: EngSerViceTypeData,
25         ‘Nonce‘ : nonceData,
26         ‘ProjectId‘:0,
27         ‘Region‘: ‘ap-shanghai‘,
28         ‘SecretId‘ : secretId,
29         # ‘SignatureMethod‘: ‘HmacSHA256‘,#加密算法可选，不指定这个参数默认是HmacSHA1加密
30         ‘SourceType‘: SourceTypeData,
31         ‘SubServiceType‘: SubServiceTypeData,
32         ‘Timestamp‘ : tmp,
33         ‘UsrAudioKey‘: UsrAudioKeyData,
34         ‘Version‘: versionData,
35         ‘VoiceFormat‘: VoiceFormatData
36     }
37     #   请求方法 + 请求主机 +请求路径 + ? + 请求字符串
38     requestStr = "%s%s%s%s%s"%(requestMethod,uriData,"/","?",dictToStr(signDictData))
39     # signData = urllib.parse.quote(sign(secretKey,requestStr,‘HmacSHA1‘))
40     #生成签名字符的时候一定是使用的没有经过urlencode编码的requestStr字符串，下面的加了encode的就是把字符串变成byte，sha1是算法，decode是把二进制解码为字符串。digest()是把hmac.new()的结果解析成字符串，然后经过base64编码为byte，再解码为字符串
41     signData = binascii.b2a_base64(hmac.new(secretKey.encode(‘utf-8‘), requestStr.encode(‘utf-8‘), hashlib.sha1).digest())[:-1].decode()
42     # 上述操作是实现签名，下面即进行请求
43     # 先建立请求参数, 此处参数只在签名时多了一个Signature
44     actionArgs = {
45         ‘Action‘ : actionData,
46         ‘Data‘: base64.b64encode(voiceData).decode(‘utf8‘),
47         # ‘Data‘: voiceData,
48         ‘DataLen‘: DataLenData,
49         ‘EngSerViceType‘: EngSerViceTypeData,
50         ‘Nonce‘ : nonceData,
51         ‘ProjectId‘:0,
52         ‘Region‘: ‘ap-shanghai‘,
53         ‘SecretId‘ : secretId,
54         ‘SourceType‘: SourceTypeData,
55         ‘SubServiceType‘: SubServiceTypeData,
56         ‘Timestamp‘ : tmp,
57         ‘UsrAudioKey‘: UsrAudioKeyData,
58         ‘Version‘: versionData,
59         ‘VoiceFormat‘: VoiceFormatData,
60         "Signature": signData
61     }
62     # 根据uri构建请求的url
63     requestUrl = "https://%s/?"%(uriData)
64     # 将请求的url和参数进行拼接，使用urlencode会修改掉参数中的/和=等符号的表示方式
65     requestUrlWithArgs = requestUrl + urllib.parse.urlencode(actionArgs)
66 
67     # actionArgs = signDictData #这是深复制，两个字典就是一个字典
68     # actionArgs["Signature"] = signData
69 
70     # # 根据uri构建请求的url
71     # requestUrl = "https://%s/?"%(uriData)
72     # # 将请求的url和参数进行拼接
73     # requestUrlWithArgs = requestUrl + dictToStr(actionArgs)
74 
75     # 获得response
76     responseData = urllib.request.urlopen(requestUrlWithArgs).read().decode("utf-8")# 根据uri构建
77     # return json.loads(responseData)["Response"]["Error"]["Message"] #处理错误消息
78     return json.loads(responseData)["Response"]["Result"]#处理正确消息

"""
        Performs speech recognition on ``audio_data`` (an ``AudioData`` instance), using the Microsoft Bing Speech API.

        The Microsoft Bing Speech API key is specified by ``key``. Unfortunately, these are not available without `signing up for an account <https://azure.microsoft.com/en-ca/pricing/details/cognitive-services/speech-api/>`__ with Microsoft Azure.

        To get the API key, go to the `Microsoft Azure Portal Resources <https://portal.azure.com/>`__ page, go to "All Resources" > "Add" > "See All" > Search "Bing Speech API > "Create", and fill in the form to make a "Bing Speech API" resource. On the resulting page (which is also accessible from the "All Resources" page in the Azure Portal), go to the "Show Access Keys" page, which will have two API keys, either of which can be used for the `key` parameter. Microsoft Bing Speech API keys are 32-character lowercase hexadecimal strings.

        The recognition language is determined by ``language``, a BCP-47 language tag like ``"en-US"`` (US English) or ``"fr-FR"`` (International French), defaulting to US English. A list of supported language values can be found in the `API documentation <https://docs.microsoft.com/en-us/azure/cognitive-services/speech/api-reference-rest/bingvoicerecognition#recognition-language>`__ under "Interactive and dictation mode".

        Returns the most likely transcription if ``show_all`` is false (the default). Otherwise, returns the `raw API response <https://docs.microsoft.com/en-us/azure/cognitive-services/speech/api-reference-rest/bingvoicerecognition#sample-responses>`__ as a JSON dictionary.

        Raises a ``speech_recognition.UnknownValueError`` exception if the speech is unintelligible. Raises a ``speech_recognition.RequestError`` exception if the speech recognition operation failed, if the key isn‘t valid, or if there is no internet connection.
        """