We Keep Coding

How To Record Video and Audio using the Intel Realsense cameras and a microphone?

I wrote this code using the realSense SDK and as well as the sounddevice libary to record audio. I am having trouble with running them both at the same time I am unsure if this is the correct way to write threads in python.
The errors:
The error I get is input overflow but I am unsure what this means and how I can make this work. The audio is initiated but never saved. The program never enters the final statement for the audio.
import argparse
from concurrent.futures import thread
from multiprocessing.dummy import Process
import tempfile
import queue
import sys
import cv2
import time
import sounddevice as sd
import soundfile as sf
import pyrealsense2 as rs
import numpy as np
from pathlib import Path
#audio
def int_or_str(text):
"""Helper function for argument parsing."""
try:
return int(text)
except ValueError:
return text
print("hello ---")
parser = argparse.ArgumentParser(add_help=False)
parser.add_argument(
'-l', '--list-devices', action='store_true',
help='show list of audio devices and exit')
args, remaining = parser.parse_known_args()
if args.list_devices:
print(sd.query_devices())
parser.exit(0)
parser = argparse.ArgumentParser(
description=__doc__,
formatter_class=argparse.RawDescriptionHelpFormatter,
parents=[parser])
parser.add_argument(
'filename', nargs='?', metavar='FILENAME',
help='audio file to store recording to')
parser.add_argument(
'-d', '--device', type=int_or_str,
help='input device (numeric ID or substring)')
parser.add_argument(
'-r', '--samplerate', type=int, help='sampling rate')
parser.add_argument(
'-c', '--channels', type=int, default=1, help='number of input channels')
parser.add_argument(
'-t', '--subtype', type=str, help='sound file subtype (e.g. "PCM_24")')
args = parser.parse_args(remaining)
q = queue.Queue()
def callback(indata, frames, time, status):
"""This is called (from a separate thread) for each audio block."""
if status:
print(status, file=sys.stderr)
q.put(indata.copy())
def recordAudio():
try:
if args.samplerate is None:
#TODO: this will change to be microphones and other devices
device_info = sd.query_devices(args.device, 'input')
# soundfile expects an int, sounddevice provides a float:
args.samplerate = int(device_info['default_samplerate'])
if args.filename is None:
args.filename = tempfile.mktemp(prefix='delme_rec_unlimited_',
suffix='.wav', dir='')
# Make sure the file is opened before recording anything:
with sf.SoundFile(args.filename, mode='x', samplerate=args.samplerate,
channels=args.channels, subtype=args.subtype) as file:
with sd.InputStream(samplerate=args.samplerate, device=args.device,
channels=args.channels, callback=callback):
print('#')
print('press Ctrl+C to stop the recording')
print('#')
while True:
file.write(q.get())
if cv2.waitKey(1) & 0xFF == ord('q'):
print("q was pressed in audio")
break
except KeyboardInterrupt:
print('\nRecording finished: ' + repr(args.filename))
parser.exit(0)
except Exception as e:
print("exeption e was found ",e)
parser.exit(type(e).__name__ + ': ' + str(e))
finally:
# Stop recording
print('\nRecording finished: ' + repr(args.filename))
print("audioRecording has stoped")
#video
#part of the displayvideo
def recordVideo():
print("Video Recording has initialized")
print("#")
# Configure depth and color streams
pipeline = rs.pipeline()
config = rs.config()
#create a device
#device1 = rs.device
#create a path
recording_path = Path('C:','/','appli','/','Documents','/','test recordings')
print(recording_path)
#create a recorder
#rec1 = rs.recorder(recording_path,device1)
# Get device product line for setting a supporting resolution
pipeline_wrapper = rs.pipeline_wrapper(pipeline)
pipeline_profile = config.resolve(pipeline_wrapper)
device = pipeline_profile.get_device()
device_product_line = str(device.get_info(rs.camera_info.product_line))
found_rgb = False
for s in device.sensors:
if s.get_info(rs.camera_info.name) == 'RGB Camera':
found_rgb = True
break
if not found_rgb:
print("The demo requires Depth camera with Color sensor")
exit(0)
config.enable_stream(rs.stream.depth, 640, 480, rs.format.z16, 30)
if device_product_line == 'L500':
config.enable_stream(rs.stream.color, 960, 540, rs.format.bgr8, 30)
else:
config.enable_stream(rs.stream.color, 640, 480, rs.format.bgr8, 30)
#rs.recorder()
# Start streaming
config.enable_record_to_file('test2.bag')
profile = pipeline.start(config)
recorder = profile.get_device().as_recorder() # Obtain the streaming device and cast it to recorder type
try:
while True:
#current_time = time.time()
#elapsed_time = current_time - start_time
# Wait for a coherent pair of frames: depth and color
frames = pipeline.wait_for_frames()
depth_frame = frames.get_depth_frame()
color_frame = frames.get_color_frame()
if not depth_frame or not color_frame:
continue
# Convert images to numpy arrays
depth_image = np.asanyarray(depth_frame.get_data())
color_image = np.asanyarray(color_frame.get_data())
# Apply colormap on depth image (image must be converted to 8-bit per pixel first)
depth_colormap = cv2.applyColorMap(cv2.convertScaleAbs(depth_image, alpha=0.03), cv2.COLORMAP_JET)
depth_colormap_dim = depth_colormap.shape
color_colormap_dim = color_image.shape
# If depth and color resolutions are different, resize color image to match depth image for display
if depth_colormap_dim != color_colormap_dim:
resized_color_image = cv2.resize(color_image, dsize=(depth_colormap_dim[1], depth_colormap_dim[0]), interpolation=cv2.INTER_AREA)
images = np.hstack((resized_color_image, depth_colormap))
else:
images = np.hstack((color_image, depth_colormap))
# Show images
cv2.namedWindow('RealSense', cv2.WINDOW_AUTOSIZE)
cv2.imshow('RealSense', images)
if cv2.waitKey(1) & 0xFF == ord('q'):
print("q was pressed in Video")
break
finally:
# Stop recording
recorder.pause() # Pause recording while continuing to stream
pipeline.stop()
pipeline = rs.pipeline()
pipeline.start()
pipeline.stop()
print("Video Recording Has stoped")
if __name__ == "__main__":
thread1 = Process(target = recordAudio)
thread2 = Process(target = recordVideo)
thread1.start()
thread2.start()

cant seem to get sounddevice module to change to the sound device i want to

im making a type of "aux switch" and I decided that i was going to use python module sounddevice to do that and I use it BUT i cant seem to get it to use the sound device that i want it too. every time that i try to change it for some reason it dose not work
import argparse
import sounddevice as sd
import numpy # Make sure NumPy is loaded before it is used in the callback
assert numpy # avoid "imported but unused" message (W0611)
print(sd.query_devices())
sd.check_input_settings(device= "VoiceMeeter Aux Output (VB-Audio VoiceMeeter AUX VAIO), Windows DirectSound")
sd.check_output_settings(device= "CABLE Input (VB-Audio Virtual Cable), Windows DirectSound ")
def int_or_str(text):
"""Helper function for argument parsing."""
try:
return int(text)
except ValueError:
return text
parser = argparse.ArgumentParser(add_help=False)
parser.add_argument(
'-l', '--list-devices', action='store_true',
help='show list of audio devices and exit')
args, remaining = parser.parse_known_args()
if args.list_devices:
print(sd.query_devices())
parser.exit(0)
parser = argparse.ArgumentParser(
description=__doc__,
formatter_class=argparse.RawDescriptionHelpFormatter,
parents=[parser])
parser.add_argument(
'-i', '--input-device', type=int_or_str,
help='')
parser.add_argument(
'-o', '--output-device', type=int_or_str,
help='output device (numeric ID or substring)')
parser.add_argument(
'-c', '--channels', type=int, default=2,
help='number of channels')
parser.add_argument('--dtype', help='audio data type')
parser.add_argument('--samplerate', type=float, help='sampling rate')
parser.add_argument('--blocksize', type=int, help='block size')
parser.add_argument('--latency', type=float, help='latency in seconds')
args = parser.parse_args(remaining)
def callback(indata, outdata, frames, time, status):
if status:
print(status)
outdata[:] = indata
try:
with sd.Stream(device=(args.input_device, args.output_device),
samplerate=args.samplerate, blocksize=args.blocksize,
dtype=args.dtype, latency=args.latency,
channels=args.channels, callback=callback):
print('#' * 80)
print('press Return to quit')
print('#' * 80)
input()
except KeyboardInterrupt:
parser.exit('')
except Exception as e:
parser.exit(type(e).__name__ + ': ' + str(e))

import argparse
import sounddevice as sd
import numpy # Make sure NumPy is loaded before it is used in the callback
assert numpy # avoid "imported but unused" message (W0611)
print(sd.query_devices())
inpdev = "VoiceMeeter Aux Output (VB-Audio VoiceMeeter AUX VAIO), Windows DirectSound"
outdev = "CABLE Input (VB-Audio Virtual Cable), Windows DirectSound "
def int_or_str(text):
"""Helper function for argument parsing."""
try:
return int(text)
except ValueError:
return text
parser = argparse.ArgumentParser(add_help=False)
parser.add_argument(
'-l', '--list-devices', action='store_true',
help='show list of audio devices and exit')
args, remaining = parser.parse_known_args()
if args.list_devices:
print(sd.query_devices())
parser.exit(0)
parser = argparse.ArgumentParser(
description=__doc__,
formatter_class=argparse.RawDescriptionHelpFormatter,
parents=[parser])
parser.add_argument(
'-i', '--input-device', type=int_or_str,
help='')
parser.add_argument(
'-o', '--output-device', type=int_or_str,
help='output device (numeric ID or substring)')
parser.add_argument(
'-c', '--channels', type=int, default=2,
help='number of channels')
parser.add_argument('--dtype', help='audio data type')
parser.add_argument('--samplerate', type=float, help='sampling rate')
parser.add_argument('--blocksize', type=int, help='block size')
parser.add_argument('--latency', type=float, help='latency in seconds')
args = parser.parse_args(remaining)
def callback(indata, outdata, frames, time, status):
if status:
print(status)
outdata[:] = indata
try:
with sd.Stream(device=(inpdev, outdev),
samplerate=args.samplerate, blocksize=args.blocksize,
dtype=args.dtype, latency=args.latency,
channels=args.channels, callback=callback):
print('#' * 80)
print('press Return to quit')
print('#' * 80)
input()
except KeyboardInterrupt:
parser.exit('')
except Exception as e:
parser.exit(type(e).__name__ + ': ' + str(e))

python try...except in handling argument from user input

my python file would read two files from command line using argparse.
I want to use 'try...except...' to handle incorrect user input, like non-exist file and incorrect command:
for example, I use '-f' to open file, then '-g' is incorrect command.
my codes are:
> parser = argparse.ArgumentParser(description = "Handle with input
files")
parser.add_argument('-m', dest = "model", type=argparse.FileType('r'))
parser.add_argument('-t', dest = "test", type=argparse.FileType('r'))
parser.add_argument('-d', dest = "permute",type=argparse.FileType('r'))
args = parser.parse_args()
# Parse file names from command line
model_file = open(args.model.name)
test_file = open(args.test.name)
decoy_file = open(args.permute.name)
I try to implement 'try...except' in my code but failed. Here is what I did:
> parser = argparse.ArgumentParser(description = "Handle with input
files")
parser.add_argument('-m', dest = "model", type=argparse.FileType('r'))
parser.add_argument('-t', dest = "test", type=argparse.FileType('r'))
parser.add_argument('-d', dest = "permute",type=argparse.FileType('r'))
args = parser.parse_args()
# Parse file names from command line
try:
model_file = open(args.model.name)
test_file = open(args.test.name)
decoy_file = open(args.permute.name)
except IOError:
print('Wrong file name')

I would suggest adding something like this to make sure all arguments are there. Also argparse.FileType('r') will already open the file (meaning you can do something like args.model.readlines()).
if not all([args.model, args.test, args.permute]):
print("All Arguments are required")
exit(1)

Firstly the error happend at args = parser.parse_args() when it parse your command param.
As we can see from argparse's origin code:
...
def parse_args(self, args=None, namespace=None):
args, argv = self.parse_known_args(args, namespace)
if argv:
msg = _('unrecognized arguments: %s')
self.error(msg % ' '.join(argv))
return args
...
def error(self, message):
"""error(message: string)
Prints a usage message incorporating the message to stderr and
exits.
If you override this in a subclass, it should not return -- it
should either exit or raise an exception.
"""
self.print_usage(_sys.stderr)
args = {'prog': self.prog, 'message': message}
self.exit(2, _('%(prog)s: error: %(message)s\n') % args)
# exit here ,that's why can not catch the exception
So when you input incorrectly, like what you mentioned above, like non-exist file or incorrect command , it will call error function in the end, and exit the thread, that's why you cannot catch a exception by try .. except synax.
If you want to catch the exception, you can inherit the main class ArgumentParser, and rewrite the method error. you can take my codes as reference:
import argparse
import sys as _sys
from argparse import ArgumentParser
class ArgumentParserSub(ArgumentParser):
def error(self, message):
self.print_usage(_sys.stderr)
args = {'prog': self.prog, 'message': message}
raise Exception(('error: %(message)s\n') % args)
parser = ArgumentParserSub(description = "Handle with input files")
parser.add_argument('-m', dest = "model", type=argparse.FileType('r'))
parser.add_argument('-t', dest = "test", type=argparse.FileType('r'))
parser.add_argument('-d', dest = "permute",type=argparse.FileType('r'))
try:
args = parser.parse_args()
# Parse file names from command line
model_file = open(args.model.name)
test_file = open(args.test.name)
decoy_file = open(args.permute.name)
except Exception as e:
print(e)
print('Wrong file name')

If you don't want the parser to catch and exit bad files, open the files yourself. Just ask the parser for names, not open files.
parser = argparse.ArgumentParser(description = "Handle with input files")
parser.add_argument('-m', dest = "model") # no type
parser.add_argument('-t', dest = "test")
parser.add_argument('-d', dest = "permute")
args = parser.parse_args()
# print(args) # good idea when debugging
# Open file names from command line
try:
model_file = open(args.model)
test_file = open(args.test)
decoy_file = open(args.permute)
except IOError:
print('Wrong file name')

How to change python program to write output into a file?

I used the "pdf2txt.py" program which came as part of the pdfminer package in GitHub to try convert pdf file to text.As per the instruction , I ran the program by typing "python pdf2txt.py somefile.pdf" in the Mac OS terminal.The output was correctly generated and printed in the terminal itself. Now my question is this, how do I direct this output to a text file.I only know the bare basics of python and I am not able to figure out which line in the program actually prints the output and what needs to be changed to direct the same into a .txt file?
import argparse
import logging
import six
import sys
import pdfminer.settings
pdfminer.settings.STRICT = False
import pdfminer.high_level
import pdfminer.layout
from pdfminer.image import ImageWriter
def extract_text(files=[], outfile='-',
_py2_no_more_posargs=None, # Bloody Python2 needs a shim
no_laparams=False, all_texts=None, detect_vertical=None, # LAParams
word_margin=None, char_margin=None, line_margin=None, boxes_flow=None, # LAParams
output_type='text', codec='utf-8', strip_control=False,
maxpages=0, page_numbers=None, password="", scale=1.0, rotation=0,
layoutmode='normal', output_dir=None, debug=False,
disable_caching=False, **other):
if _py2_no_more_posargs is not None:
raise ValueError("Too many positional arguments passed.")
if not files:
raise ValueError("Must provide files to work upon!")
# If any LAParams group arguments were passed, create an LAParams object and
# populate with given args. Otherwise, set it to None.
if not no_laparams:
laparams = pdfminer.layout.LAParams()
for param in ("all_texts", "detect_vertical", "word_margin", "char_margin", "line_margin", "boxes_flow"):
paramv = locals().get(param, None)
if paramv is not None:
setattr(laparams, param, paramv)
else:
laparams = None
imagewriter = None
if output_dir:
imagewriter = ImageWriter(output_dir)
if output_type == "text" and outfile != "-":
for override, alttype in ( (".htm", "html"),
(".html", "html"),
(".xml", "xml"),
(".tag", "tag") ):
if outfile.endswith(override):
output_type = alttype
if outfile == "-":
outfp = sys.stdout
if outfp.encoding is not None:
codec = 'utf-8'
else:
outfp = open(outfile, "wb")
for fname in files:
with open(fname, "rb") as fp:
pdfminer.high_level.extract_text_to_fp(fp, **locals())
return outfp
def maketheparser():
parser = argparse.ArgumentParser(description=__doc__, add_help=True)
parser.add_argument("files", type=str, default=None, nargs="+", help="File to process.")
parser.add_argument("-d", "--debug", default=False, action="store_true", help="Debug output.")
parser.add_argument("-p", "--pagenos", type=str, help="Comma-separated list of page numbers to parse. Included for legacy applications, use --page-numbers for more idiomatic argument entry.")
parser.add_argument("--page-numbers", type=int, default=None, nargs="+", help="Alternative to --pagenos with space-separated numbers; supercedes --pagenos where it is used.")
parser.add_argument("-m", "--maxpages", type=int, default=0, help="Maximum pages to parse")
parser.add_argument("-P", "--password", type=str, default="", help="Decryption password for PDF")
parser.add_argument("-o", "--outfile", type=str, default="-", help="Output file (default \"-\" is stdout)")
parser.add_argument("-t", "--output_type", type=str, default="text", help="Output type: text|html|xml|tag (default is text)")
parser.add_argument("-c", "--codec", type=str, default="utf-8", help="Text encoding")
parser.add_argument("-s", "--scale", type=float, default=1.0, help="Scale")
parser.add_argument("-A", "--all-texts", default=None, action="store_true", help="LAParams all texts")
parser.add_argument("-V", "--detect-vertical", default=None, action="store_true", help="LAParams detect vertical")
parser.add_argument("-W", "--word-margin", type=float, default=None, help="LAParams word margin")
parser.add_argument("-M", "--char-margin", type=float, default=None, help="LAParams char margin")
parser.add_argument("-L", "--line-margin", type=float, default=None, help="LAParams line margin")
parser.add_argument("-F", "--boxes-flow", type=float, default=None, help="LAParams boxes flow")
parser.add_argument("-Y", "--layoutmode", default="normal", type=str, help="HTML Layout Mode")
parser.add_argument("-n", "--no-laparams", default=False, action="store_true", help="Pass None as LAParams")
parser.add_argument("-R", "--rotation", default=0, type=int, help="Rotation")
parser.add_argument("-O", "--output-dir", default=None, help="Output directory for images")
parser.add_argument("-C", "--disable-caching", default=False, action="store_true", help="Disable caching")
parser.add_argument("-S", "--strip-control", default=False, action="store_true", help="Strip control in XML mode")
return parser
# main
def main(args=None):
P = maketheparser()
A = P.parse_args(args=args)
if A.page_numbers:
A.page_numbers = set([x-1 for x in A.page_numbers])
if A.pagenos:
A.page_numbers = set([int(x)-1 for x in A.pagenos.split(",")])
imagewriter = None
if A.output_dir:
imagewriter = ImageWriter(A.output_dir)
if six.PY2 and sys.stdin.encoding:
A.password = A.password.decode(sys.stdin.encoding)
if A.output_type == "text" and A.outfile != "-":
for override, alttype in ( (".htm", "html"),
(".html", "html"),
(".xml", "xml" ),
(".tag", "tag" ) ):
if A.outfile.endswith(override):
A.output_type = alttype
if A.outfile == "-":
outfp = sys.stdout
if outfp.encoding is not None:
# Why ignore outfp.encoding? :-/ stupid cathal?
A.codec = 'utf-8'
else:
outfp = open(A.outfile, "wb")
## Test Code
outfp = extract_text(**vars(A))
outfp.close()
return 0
if __name__ == '__main__': sys.exit(main())

Try
python pdf2txt.py somefile.pd > pdf_text.txt

Thank you everyone for the inputs.
I added a line
sys.stdout=open("somefile.txt","w")
right before the line
outfp=sys.stdout.
worked like a charm.

Delay in live audio recording

I am a noob in audio processing using python. I have got the following python code from internet to perform live audio recording. Whenever, I record using the following code, there is a block of zeros in the beginning of the recorded audio file. The recording doesn't start immediately and it adds zeros until the recording starts.
I want the recording to happen immediately i run code without any zeros in the beginning. Any help is appreciated.
import argparse
import tempfile
import queue
import sys
def int_or_str(text):
"""Helper function for argument parsing."""
try:
return int(text)
except ValueError:
return text
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument(
'-l', '--list-devices', action='store_true',
help='show list of audio devices and exit')
parser.add_argument(
'-d', '--device', type=int_or_str,
help='input device (numeric ID or substring)')
parser.add_argument(
'-r', '--samplerate', type=int, help='sampling rate')
parser.add_argument(
'-c', '--channels', type=int, default=1, help='number of input channels')
parser.add_argument(
'filename', nargs='?', metavar='FILENAME',
help='audio file to store recording to')
parser.add_argument(
'-t', '--subtype', type=str, help='sound file subtype (e.g. "PCM_24")')
args = parser.parse_args()
try:
import sounddevice as sd
import soundfile as sf
import numpy # Make sure NumPy is loaded before it is used in the callback
assert numpy # avoid "imported but unused" message (W0611)
if args.list_devices:
print(sd.query_devices())
parser.exit(0)
if args.samplerate is None:
device_info = sd.query_devices(args.device, 'input')
# soundfile expects an int, sounddevice provides a float:
args.samplerate = int(device_info['default_samplerate'])
if args.filename is None:
args.filename = tempfile.mktemp(prefix='delme_rec_unlimited_',
suffix='.wav', dir='')
q = queue.Queue()
def callback(indata, frames, time, status):
"""This is called (from a separate thread) for each audio block."""
if status:
print(status, file=sys.stderr)
q.put(indata.copy())
# Make sure the file is opened before recording anything:
with sf.SoundFile(args.filename, mode='x', samplerate=args.samplerate,
channels=args.channels, subtype=args.subtype) as file:
with sd.InputStream(samplerate=args.samplerate, device=args.device,
channels=args.channels, callback=callback):
print('#' * 80)
print('press Ctrl+C to stop the recording')
print('#' * 80)
while True:
file.write(q.get())
except KeyboardInterrupt:
print('\nRecording finished: ' + repr(args.filename))
parser.exit(0)
except Exception as e:
parser.exit(type(e).__name__ + ': ' + str(e))