功能如下

googlekey.json

@@ -0,0 +1,12 @@
+{
+  "type": "service_account",
+  "project_id": "wechatbot-154909",
+  "private_key_id": "e53738e2d14ccd6a29de580163d1ff49cc08e0c5",
+  "private_key": "-----BEGIN PRIVATE KEY-----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\nX3s6PmAl5aYA3kiItAlvbms=\n-----END PRIVATE KEY-----\n",
+  "client_email": "[email protected]",
+  "client_id": "106655796840196313946",
+  "auth_uri": "https://accounts.google.com/o/oauth2/auth",
+  "token_uri": "https://accounts.google.com/o/oauth2/token",
+  "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
+  "client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/webot-361%40wechatbot-154909.iam.gserviceaccount.com"
+}

language_codes.py

@@ -0,0 +1,45 @@
+LC_AFRIKAANS = "af"
+LC_ARABIC = "ar"
+LC_BULGARIAN = "bg"
+LC_CATALAN = "ca"
+LC_CHINESE_SIMPLIFIED = "ch"
+LC_CZECH = "cs"
+LC_CYMRAEG = "cy"
+LC_DANSK = "da"
+LC_DEUTSCH = "de"
+LC_GREEK = "el"
+LC_ENGLISH = "en"
+LC_SPANISH = "es"
+LC_EUSKARA = "eu"
+LC_SUOMI = "fi"
+LC_FRENCH = "fr"
+LC_HEBREW = "he"
+LC_HINDI = "hi"
+LC_CROATIAN = "hr"
+LC_HUNGARIAN = "hu"
+LC_INDONESIAN = "id"
+LC_ITALIANO = "it"
+LC_JAPANESE = "ja"
+LC_KHMER = "kh"
+LC_KOREAN = "ko"
+LC_LITHUANIAN = "lt"
+LC_MALAYALAM = "ml"
+LC_BAHASA_MELAYU = "ms"
+LC_NORSK = "nb"
+LC_NEDERLANDS = "nl"
+LC_PUNJABI = "pa"
+LC_FILIPINO = "ph"
+LC_POLSKI = "pl"
+LC_PORTUGUESE = "pt"
+LC_ROMANIAN = "ro"
+LC_SERBIAN = "rs"
+LC_RUSSIAN = "ru"
+LC_SLOVAK = "sk"
+LC_SVENSKA = "sv"
+LC_TAMIL = "ta"
+LC_TELUGU = "te"
+LC_THAI = "th"
+LC_TURKISH = "tr"
+LC_UKRAINIAN = "uk"
+LC_TIENG_VIET = "vn"
+LC_CHINESE_TRADITIONAL = "zh"

maintest.py

@@ -0,0 +1,60 @@
+
+import subprocess
+import os
+import codecs
+import json
+import re 
+
+vedio_formats = ['mp4','avi','wmv','mov'] # 1
+audio_formats = ['wav','flac','mp3','aiff'] # 2
+
+def file_upload(voice):
+	regex = r"(.+)\/(.+)"
+	if re.search(regex, voice):
+		match = re.search(regex, voice)
+		file_dir = match.group(1) + '/'
+		file_name_and_type = match.group(2).lower() 
+	else: 
+		raise fileNameError('fileNameError')
+	regex = r"(.+)\.(.+)"
+	if re.search(regex, file_name_and_type):
+	    match = re.search(regex, file_name_and_type)
+	    file_name = match.group(1)
+	    file_type = match.group(2).lower()
+	else: 
+		raise fileNameError('fileNameError')
+	file_pwd = file_dir + file_name_and_type
+	transcripts_timed_pwd = file_dir + file_name + '.json'
+	autosubing(file_pwd,transcripts_timed_pwd,file_type)
+	json_data = open(transcripts_timed_pwd)
+	transcripts_timed = json.load(json_data)
+	transcripts_content = ''
+	for i in transcripts_timed:
+		transcripts_content = transcripts_content + ' ' + i['content']
+	json_data.close()
+	return transcripts_content
+
+def autosubing(file_pwd,transcripts_timed_pwd,file_type):
+	if file_format(file_type) == 1:	
+		# command = "python autosub.py -F json -V %s" %(file_pwd)
+		command = "python autosub.py %s -F json" %(file_pwd)
+	else: 
+		command = "python autosub.py %s -F json" %(file_pwd)
+	subprocess.call(command, shell=True)	
+	print "Autosubed"
+
+
+# throw formatError
+def file_format(file_type):
+	if file_type in vedio_formats:
+		return 1;
+	elif file_type in audio_formats:
+		return 2
+	else: raise Exception('Format prohibited')
+
+# dir1 = '/Users/n0where/GoogleDrive/WeixinBot/saved/voices/voice_2546547996039896197.mp3'
+# dir2 = '/Users/n0where/Desktop/DFA_01.flac'
+# dir3 = '/Users/n0where/GoogleDrive/ASQ/ASQ/transcripts/Chem101.mp4'
+# dir4 = '/Users/n0where/GoogleDrive/WeixinBot/saved/voices/voice_1089270824656503909.mp3'
+# dir5 = '/Users/n0where/GoogleDrive/WeixinBot/saved/voices/voice_8675834799709315495.mp3'
+# print file_upload(dir5)

response_codes.py

@@ -0,0 +1,5 @@
+RESPONSE_OK = 100
+RESPONSE_BAD_REQUEST = 400
+RESPONSE_UNAUTHORIZED = 401
+RESPONSE_NOT_FOUND = 404
+RESPONSE_500 = 500

simsimi.py

@@ -0,0 +1,33 @@
+from language_codes import LC_ENGLISH
+import urllib2, urllib, json
+from response_codes import RESPONSE_OK
+
+class SimSimiException(Exception):
+	pass
+
+class SimSimi(object):
+
+	def __init__(self, *args, **kwargs):
+		self.conversation_request_url = kwargs.get('conversation_request_url','http://sandbox.api.simsimi.com/request.p')
+		self.conversation_key = kwargs.get('conversation_key','')
+		self.conversation_language = kwargs.get('conversation_language', LC_ENGLISH)
+		self.conversation_filter = kwargs.get('conversation_filter','0.0')
+
+	def getConversation(self, text):
+
+		requestParam = {
+			'key':self.conversation_key,
+			'lc':self.conversation_language,
+			'ft':self.conversation_filter,
+			'text':text
+		}
+
+		requestUrl = "%s?%s" % (self.conversation_request_url, urllib.urlencode(requestParam))
+
+		response = urllib2.urlopen(requestUrl)
+		responseDict = json.loads(str(response.read()))
+
+		if responseDict['result'] != RESPONSE_OK:
+			raise SimSimiException("SimSimiException occured: %s" % responseDict['msg'])
+
+		return responseDict

simsimitest.py

@@ -0,0 +1,37 @@
+ #coding=utf-8 
+import simsimi
+import language_codes
+import response_codes
+import re
+from simsimi import SimSimiException
+
+keys = ['20666778-3204-480a-b98b-0d705ad7c170','45c0139e-7a59-4c06-9a83-7a9e4c8f6470','59a9d8b2-e4d0-495a-8a9f-1168cbb1193f']
+keys_sum = 0
+simSimis = []
+
+for i in range(len(keys)):
+	simSimis.append(simsimi.SimSimi(
+        conversation_language=language_codes.LC_CHINESE_SIMPLIFIED,
+        conversation_key=keys[i] ))
+simSimi = simSimis[0]
+
+def foo():
+	global simSimi
+	global keys_sum
+	try:
+		response = simSimi.getConversation(u'。。'.encode('utf-8'))
+	except Exception, e:
+		print e
+		if str(e).find("Not found") != -1:
+			response = {'response': "傻逼"}
+		elif str(e).find("Limit Exceeded") != -1:
+			response = {'response': "到达每日上限了，正在自动更换api_key，使用第%d个api_key"%((keys_sum+1) % len(keys)+1)}
+			keys_sum = keys_sum + 1
+			simSimi = simSimis[keys_sum % len(keys)]
+		else: 
+			response = {'response': "代码出现了未知的问题"}
+
+	print response['response']
+
+for i in range(3):
+	foo()

transcribe.py

@@ -0,0 +1,99 @@
+#!/usr/bin/env python
+# coding=utf-8 
+# Copyright 2016 Google Inc. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""Google Cloud Speech API sample application using the REST API for batch
+processing."""
+
+# [START import_libraries]
+import argparse
+import base64
+import json
+
+from googleapiclient import discovery
+import httplib2
+from oauth2client.client import GoogleCredentials
+# [END import_libraries]
+
+
+# [START authenticating]
+DISCOVERY_URL = ('https://{api}.googleapis.com/$discovery/rest?'
+                 'version={apiVersion}')
+
+
+# Application default credentials provided by env variable
+# GOOGLE_APPLICATION_CREDENTIALS
+def get_speech_service():
+    credentials = GoogleCredentials.get_application_default().create_scoped(
+        ['https://www.googleapis.com/auth/cloud-platform'])
+    http = httplib2.Http()
+    credentials.authorize(http)
+
+    return discovery.build(
+        'speech', 'v1beta1', http=http, discoveryServiceUrl=DISCOVERY_URL)
+# [END authenticating]
+
+
+def transcribe(speech_file):
+    """Transcribe the given audio file.
+
+    Args:
+        speech_file: the name of the audio file.
+    """
+    # [START construct_request]
+    with open(speech_file, 'rb') as speech:
+        # Base64 encode the binary audio file for inclusion in the JSON
+        # request.
+        speech_content = base64.b64encode(speech.read())
+
+    service = get_speech_service()
+    service_request = service.speech().syncrecognize(
+        body={
+            'config': {
+                # There are a bunch of config options you can specify. See
+                # https://goo.gl/KPZn97 for the full list.
+                'encoding': 'LINEAR16',  # raw 16-bit signed LE samples
+                'sampleRate': 16000,  # 16 khz
+                # See http://g.co/cloud/speech/docs/languages for a list of
+                # supported languages.
+                'languageCode': 'cmn-Hans-CN',  # a BCP-47 language tag
+            },
+            'audio': {
+                'content': speech_content.decode('UTF-8')
+                }
+            })
+    # [END construct_request]
+    # [START send_request]
+    response = service_request.execute()
+    print response
+    return response
+    # print(json.dumps(response))
+    # [END send_request]
+
+def get_content(speech_file):
+    content = transcribe(speech_file)
+    if content.has_key('results'):
+        return content['results'][0]['alternatives'][0]['transcript']
+    else: return 'Wrong rec'
+
+print get_content('/Users/n0where/GoogleDrive/WeixinBot/saved/voices/voice_2376641155930976295.mp3')
+# [START run_application]
+# if __name__ == '__main__':
+#     parser = argparse.ArgumentParser()
+#     parser.add_argument(
+#         'speech_file', help='Full path of audio file to be recognized')
+#     args = parser.parse_args()
+#     main(args.speech_file)
+    # [END run_application]
+