def start(self):
print 'Start Speech Download Service...'
language = self._language
download_dir = self.setup_download_dir()
# Create a queue to communicate with the worker threads
queue = Queue()
with open(self._text_file_path, 'r') as f:
progress = Progress(len(f.readlines()))
f.seek(0)
queue.count = 0
queue.progress = progress
for text in f:
text = text.rstrip('\n')
encoded_args = urlencode({
'hl': language,
'src': text,
'key': config.API_KEY
})
url = config.SPEECH_URL + encoded_args
download_path = os.path.join(download_dir, text + config.DOWNLOAD_FILE_TYPE)
# queue accepts only one object
queue.put(
(url, download_path)
)
# Create 8 worker threads
for _ in range(self.THREAD_POOL_SIZE):
thread = SpeechDownloadThread(queue)
# Setting daemon to true will let the main thread exit
# even though the workers are blocking
thread.daemon = True
thread.start()
# Block until all tasks are done
queue.join()
print 'Done, Downloaded %d Speeches' % queue.count
