运行代码时，Python传递/忽略Google Cloud Storage中的`create_bucket`和`upload_blob`函数，错误为404

Question

运行代码时遇到问题。它正在传递/忽略create_bucket()和upload_blob()函数，并返回一个NotFound: 404 No such object: gcspeechstorage/output.wav错误。我已经隔离了代码的工作部分，剩下的还有这两个有问题的功能。我还要注意，在我问的上一个问题中，我被指示测试transcribe_gcs，并且 did 确实仅在手动上传文件时有效。因此，我的问题是创建存储桶，然后上传所述文件。感谢您的帮助。

预期结果：创建一个存储桶，将WAV文件上传到GCS存储桶，然后检索该文件进行转录，然后分析情感。

实际结果：录制音频，然后崩溃，出现上述404错误。

完整代码（为您提供更好的图片）：

import pyaudio
import wave
import pprint
import argparse
import datetime
import io
import json
import os
import nltk
from nltk.sentiment.vader import SentimentIntensityAnalyzer
from google.cloud import storage
import sys
from oauth2client.service_account import ServiceAccountCredentials

CHUNK = 1024
FORMAT = pyaudio.paInt16
CHANNELS = 1
RATE = 44100
RECORD_SECONDS = 10
WAVE_OUTPUT_FILENAME = "output.wav"

p = pyaudio.PyAudio()

stream = p.open(format=FORMAT,
                channels=CHANNELS,
                rate=RATE,
                input=True,
                frames_per_buffer=CHUNK)

print("* recording")

frames = []

for i in range(0, int(RATE / CHUNK * RECORD_SECONDS)):
    data = stream.read(CHUNK)
    frames.append(data)

print("* done recording")

stream.stop_stream()
stream.close()
p.terminate()

wf = wave.open(WAVE_OUTPUT_FILENAME, 'wb')
wf.setnchannels(CHANNELS)
wf.setsampwidth(p.get_sample_size(FORMAT))
wf.setframerate(RATE)
wf.writeframes(b''.join(frames))
wf.close()

os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = 'C:/Users/Dave/Desktop/mizu/Project Mizu-7e2ecd8c5804.json'

bucket_name = "gcspeechstorage"
source_file_name = "C:/Users/Dave/Desktop/mizu/output.wav"
destination_blob_name = "output.wav"
gcs_uri = "gs://gcspeechstorage/output.wav"

def create_bucket(bucket_name):
    """Creates a new bucket."""
    storage_client = storage.Client()
    bucket = storage_client.create_bucket(bucket_name)
    print('Bucket {} created'.format(bucket.name))

def upload_blob(bucket_name, source_file_name, destination_blob_name):
    """Uploads a file to the bucket."""
    storage_client = storage.Client()
    bucket = storage_client.get_bucket(bucket_name)
    blob = bucket.blob(destination_blob_name)

    blob.upload_from_filename(source_file_name)

    print('File {} uploaded to {}.'.format(
        source_file_name,
        destination_blob_name))

# [START speech_transcribe_async_gcs]
def transcribe_gcs(gcs_uri):
    """Asynchronously transcribes the audio file specified by the gcs_uri."""
    from google.cloud import speech
    from google.cloud.speech import enums
    from google.cloud.speech import types
    client = speech.SpeechClient()

    audio = types.RecognitionAudio(uri=gcs_uri)
    config = types.RecognitionConfig(
        encoding= 'LINEAR16',
        sample_rate_hertz=44100,
        language_code='en-US')

    operation = client.long_running_recognize(config, audio)

    print('Waiting for operation to complete...')
    response = operation.result(timeout=90)

    # Each result is for a consecutive portion of the audio. Iterate through
    # them to get the transcripts for the entire audio file.
    for result in response.results:
        # The first alternative is the most likely one for this portion.
        print(u'Transcript: {}'.format(result.alternatives[0].transcript))

        transcribedSpeechFile = open('speechToAnalyze.txt', 'a+')  # this is where a text file is made with the transcribed speech

        transcribedSpeechFile.write(format(result.alternatives[0].transcript))

        transcribedSpeechFile.close()

        print('Confidence: {}'.format(result.alternatives[0].confidence))
# [END speech_transcribe_async_gcs]


if __name__ == '__main__':
    transcribe_gcs(gcs_uri)


audio_rec = open('speechToAnalyze.txt', 'r')

sid = SentimentIntensityAnalyzer()
for sentence in audio_rec:
    ss = sid.polarity_scores(sentence)
    for k in ss:
        print('{0}: {1}, '.format(k, ss[k]), end='')
    print()

错误消息：

C:\Users\Dave\AppData\Local\Programs\Python\Python37\python.exe C:/Users/Dave/Desktop/mizu/FrankensteinedFile.py
* recording
* done recording
Traceback (most recent call last):
  File "C:\Users\Dave\AppData\Roaming\Python\Python37\site-packages\google\api_core\grpc_helpers.py", line 57, in error_remapped_callable
    return callable_(*args, **kwargs)
  File "C:\Users\Dave\AppData\Roaming\Python\Python37\site-packages\grpc\_channel.py", line 565, in __call__
    return _end_unary_response_blocking(state, call, False, None)
  File "C:\Users\Dave\AppData\Roaming\Python\Python37\site-packages\grpc\_channel.py", line 467, in _end_unary_response_blocking
    raise _Rendezvous(state, None, None, deadline)
grpc._channel._Rendezvous: <_Rendezvous of RPC that terminated with:
    status = StatusCode.NOT_FOUND
    details = "No such object: gcspeechstorage/output.wav"
    debug_error_string = "{"created":"@1562878577.907000000","description":"Error received from peer ipv6:[2607:f8b0:4000:806::200a]:443","file":"src/core/lib/surface/call.cc","file_line":1052,"grpc_message":"No such object: gcspeechstorage/output.wav","grpc_status":5}"
>

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "C:/Users/Dave/Desktop/mizu/FrankensteinedFile.py", line 112, in <module>
    transcribe_gcs(gcs_uri)
  File "C:/Users/Dave/Desktop/mizu/FrankensteinedFile.py", line 90, in transcribe_gcs
    operation = client.long_running_recognize(config, audio)
  File "C:\Users\Dave\AppData\Local\Programs\Python\Python37\lib\site-packages\google\cloud\speech_v1\gapic\speech_client.py", line 326, in long_running_recognize
    request, retry=retry, timeout=timeout, metadata=metadata
  File "C:\Users\Dave\AppData\Roaming\Python\Python37\site-packages\google\api_core\gapic_v1\method.py", line 143, in __call__
    return wrapped_func(*args, **kwargs)
  File "C:\Users\Dave\AppData\Roaming\Python\Python37\site-packages\google\api_core\retry.py", line 273, in retry_wrapped_func
    on_error=on_error,
  File "C:\Users\Dave\AppData\Roaming\Python\Python37\site-packages\google\api_core\retry.py", line 182, in retry_target
    return target()
  File "C:\Users\Dave\AppData\Roaming\Python\Python37\site-packages\google\api_core\timeout.py", line 214, in func_with_timeout
    return func(*args, **kwargs)
  File "C:\Users\Dave\AppData\Roaming\Python\Python37\site-packages\google\api_core\grpc_helpers.py", line 59, in error_remapped_callable
    six.raise_from(exceptions.from_grpc_error(exc), exc)
  File "<string>", line 3, in raise_from
google.api_core.exceptions.NotFound: 404 No such object: gcspeechstorage/output.wav

Answer 1

它不会传递或忽略您的功能。您只是没有在if __name__ == '__main__':块内调用它们。脚本的编写方式，只有在使用以下命令运行时，它才会尝试调用transcribe_gcs(gcs_uri) python FrankensteinedFile.py。因此，完全没有意义，因为它从未被记录和上传，因此无法在存储桶中找到特定文件。

检查this link以了解if __name__ == '__main__':块的工作方式。 这是代码的结构，它可以调用您编写的所有内容：

import pyaudio
import wave
import pprint
import argparse
import datetime
import io
import json
import os
import nltk
from nltk.sentiment.vader import SentimentIntensityAnalyzer
from google.cloud import storage
import sys
from oauth2client.service_account import ServiceAccountCredentials


def record_audio(chunk, format, channels, rate, record_seconds, wave_output_filename):
  p = pyaudio.PyAudio()

  stream = p.open(format=format,
                  channels=channels,
                  rate=rate,
                  input=True,
                  frames_per_buffer=chunk)

  print("* recording")

  frames = []

  for i in range(0, int(rate / chunk * record_seconds)):
      data = stream.read(chunk)
      frames.append(data)

  print("* done recording")

  stream.stop_stream()
  stream.close()
  p.terminate()

  wf = wave.open(wave_output_filename, 'wb')
  wf.setnchannels(channels)
  wf.setsampwidth(p.get_sample_size(format))
  wf.setframerate(rate)
  wf.writeframes(b''.join(frames))
  wf.close()

def create_bucket(bucket_name):
    """Creates a new bucket."""
    storage_client = storage.Client()
    bucket = storage_client.create_bucket(bucket_name)
    print('Bucket {} created'.format(bucket.name))

def upload_blob(bucket_name, source_file_name, destination_blob_name):
    """Uploads a file to the bucket."""
    storage_client = storage.Client()
    bucket = storage_client.get_bucket(bucket_name)
    blob = bucket.blob(destination_blob_name)

    blob.upload_from_filename(source_file_name)

    print('File {} uploaded to {}.'.format(
        source_file_name,
        destination_blob_name))

# [START speech_transcribe_async_gcs]
def transcribe_gcs(gcs_uri):
    """Asynchronously transcribes the audio file specified by the gcs_uri."""
    from google.cloud import speech
    from google.cloud.speech import enums
    from google.cloud.speech import types
    client = speech.SpeechClient()

    audio = types.RecognitionAudio(uri=gcs_uri)
    config = types.RecognitionConfig(
        encoding= 'LINEAR16',
        sample_rate_hertz=44100,
        language_code='en-US')

    operation = client.long_running_recognize(config, audio)

    print('Waiting for operation to complete...')
    response = operation.result(timeout=90)

    # Each result is for a consecutive portion of the audio. Iterate through
    # them to get the transcripts for the entire audio file.
    for result in response.results:
        # The first alternative is the most likely one for this portion.
        print(u'Transcript: {}'.format(result.alternatives[0].transcript))

        transcribedSpeechFile = open('speechToAnalyze.txt', 'a+')  # this is where a text file is made with the transcribed speech

        transcribedSpeechFile.write(format(result.alternatives[0].transcript))

        transcribedSpeechFile.close()

        print('Confidence: {}'.format(result.alternatives[0].confidence))
# [END speech_transcribe_async_gcs]

def analyze_text():
  audio_rec = open('speechToAnalyze.txt', 'r')

  sid = SentimentIntensityAnalyzer()
  for sentence in audio_rec:
      ss = sid.polarity_scores(sentence)
      for k in ss:
          print('{0}: {1}, '.format(k, ss[k]), end='')
      print()

if __name__ == '__main__':
  os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = 'C:/Users/Dave/Desktop/mizu/Project Mizu-7e2ecd8c5804.json'

  bucket_name = "gcspeechstorage"
  source_file_name = "C:/Users/Dave/Desktop/mizu/output.wav"
  destination_blob_name = "output.wav"
  gcs_uri = "gs://gcspeechstorage/output.wav"  

  chunk = 1024
  format = pyaudio.paInt16
  channels = 1
  rate = 44100
  record_seconds = 10
  wave_output_filename = "output.wav"

  record_audio(chunk, format, channels, rate, record_seconds, wave_output_filename)
  create_bucket(bucket_name)
  upload_blob(bucket_name, source_file_name, destination_blob_name)
  transcribe_gcs(gcs_uri)
  analyze_text()