def morse_audio( item ):
from pyglet import media
import pyglet
import time
import glob
import os
import wave
from contextlib import closing
files = []
audios = []
for file in glob.glob('C:\\Users\\MQ\'s Virual World\\Downloads\\Morse\\*.wav'):
ass = str(os.path.join('C:\\Users\MQ\'s Virual World\\Downloads\\Morse', file))
print (ass)
files.append(ass)
#audio = media.load(files[1])
#audio.play()
#print (len(files))
one = list(item)
str_list = [x.strip(' ') for x in one]
str_list = [x.strip('/') for x in str_list]
for s in str_list[0]:
if s != "-" and s != ".":
list(item)
for letter in item:
for i in range(0, 51):
if letter == " ":
time.sleep(1.5)
audios.append("noise3.wav")
break
if letter != letterlst[i] and letter != letterlst[i].lower():
continue
else:
print (files[i])
audio = media.load(files[i])
audio.play()
audios.append(files[i])
audios.append("noise2.wav")
time.sleep(1)
else:
lst = item.split()
print (' '.join(lst))
for code in lst:
for i in range(0, 51):
if code == "/":
time.sleep(1.5)
audios.append("noise3.wav")
break
if code != morse[i]:
continue
else:
print (files[i])
audio = media.load(files[i])
audio.play()
audios.append(files[i])
audios.append("noise2.wav")
time.sleep(1)
break
outfile = "sounds.wav"
data= []
for file in audios:
w = wave.open(file, 'rb')
lol = w.getparams()
print (lol)
data.append( [w.getparams(), w.readframes(w.getnframes())] )
w.close()
with closing(wave.open(outfile, 'wb')) as output:
# find sample rate from first file
with closing(wave.open(audios[0])) as w:
output.setparams(w.getparams())
# write each file to output
for audioo in audios:
with closing(wave.open(audioo)) as w:
output.writeframes(w.readframes(w.getnframes()))()))
So this code previously worked but I wanted to use different file types other then .wav files but because that worked so poorly I went back to .wav. These are different .wav files but the ones that worked before get the same error message. Which is:
Traceback (most recent call last):
File "C:\Users\MQ's Virual World\AppData\Local\Programs\Python\Python35-32\morsecode.py", line 187, in <module>
morse_audio("0123456789ÁÄ#&':,$=!-().+?;/_")
File "C:\Users\MQ's Virual World\AppData\Local\Programs\Python\Python35-32\morsecode.py", line 96, in morse_audio
audio.play()
File "C:\Users\MQ's Virual World\AppData\Local\Programs\Python\Python35-32\lib\site-packages\pyglet\media\__init__.py", line 473, in play
player.play()
File "C:\Users\MQ's Virual World\AppData\Local\Programs\Python\Python35-32\lib\site-packages\pyglet\media\__init__.py", line 1012, in play
self._set_playing(True)
File "C:\Users\MQ's Virual World\AppData\Local\Programs\Python\Python35-32\lib\site-packages\pyglet\media\__init__.py", line 993, in _set_playing
self._create_audio_player()
File "C:\Users\MQ's Virual World\AppData\Local\Programs\Python\Python35-32\lib\site-packages\pyglet\media\__init__.py", line 1083, in _create_audio_player
self._audio_player = audio_driver.create_audio_player(group, self)
File "C:\Users\MQ's Virual World\AppData\Local\Programs\Python\Python35-32\lib\site-packages\pyglet\media\drivers\directsound\__init__.py", line 502, in create_audio_player
return DirectSoundAudioPlayer(source_group, player)
File "C:\Users\MQ's Virual World\AppData\Local\Programs\Python\Python35-32\lib\site-packages\pyglet\media\drivers\directsound\__init__.py", line 184, in __init__
None)
File "C:\Users\MQ's Virual World\AppData\Local\Programs\Python\Python35-32\lib\site-packages\pyglet\com.py", line 125, in <lambda>
self.method.get_field()(self.i, self.name)(obj, *args)
File "_ctypes/callproc.c", line 920, in GetResult
OSError: [WinError -2147024809] The parameter is incorrect
I've tried .wav files that used to work. It works when I use a .ogg file. Also works with mp3s. Seems only .wav files are giving it issues. Very suddenly and randomly.
Related
I have a code that uses multiprocessing over about 10000 files on a 12 core vcpu on Ubuntu.
def process_file(name):
inp = open(name)
out = open(name.split('.')[0]+'wikiout.txt','a')
for row in inp:
row = row.strip()
sent_text = nltk.sent_tokenize(text)
for sent in sent_text:
# process sentence
inp.close()
out.close()
if __name__ == '__main__':
processes = []
for i in 'ABCDEF':
for j in 'ABCDEFGHIJKLMNOPQRSTUVWXYZ':
for k in range(100)
filename = os.path.join(os.path.dirname(__file__), (i + j + '/' + 'wiki_' + str(k) + '.txt'))
p = multiprocessing.Process(target=process_file, args=(filename,))
processes.append(p)
p.start()
for process in processes:
process.join()
For some reason I get this issue
File "wikirules.py", line 37, in <module>
p.start()
File "/usr/lib/python3.8/multiprocessing/process.py", line 121, in start
self._popen = self._Popen(self)
File "/usr/lib/python3.8/multiprocessing/context.py", line 224, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "/usr/lib/python3.8/multiprocessing/context.py", line 277, in _Popen
return Popen(process_obj)
File "/usr/lib/python3.8/multiprocessing/popen_fork.py", line 19, in __init__
self._launch(process_obj)
File "/usr/lib/python3.8/multiprocessing/popen_fork.py", line 69, in _launch
child_r, parent_w = os.pipe()
OSError: [Errno 24] Too many open files
Traceback (most recent call last):
File "/usr/lib/python3.8/multiprocessing/process.py", line 315, in _bootstrap
File "/usr/lib/python3.8/multiprocessing/process.py", line 108, in run
File "wikirules.py", line 13, in process_file
File "/usr/local/lib/python3.8/dist-packages/nltk/tokenize/__init__.py", line 106, in sent_tokenize
File "/usr/local/lib/python3.8/dist-packages/nltk/data.py", line 752, in load
File "/usr/local/lib/python3.8/dist-packages/nltk/data.py", line 877, in _open
File "/usr/local/lib/python3.8/dist-packages/nltk/data.py", line 327, in open
OSError: [Errno 24] Too many open files: '/root/nltk_data/tokenizers/punkt/PY3/english.pickle'
Any clue why this might be happening? Im still new to multiprocessing. So shouldn't this not open more than 12 files at once.
Your code is trying to run
len('ABCDEF') * len('ABCD...Z') * len(range(100)) = 6 * 26 * 100 = 15 600
operating system processes simultaneously.
Actually multiprocessing module contains relatively low level primitives to work with multiprocessing, and for basic tasks standard library suggests more safe and convenient option - module concurrent.futures which contains Pools implementations for threads and processes, and could be very useful especially for "embarrassingly parallel" workloads.
Here is example how the code from your question could be transformed using concurrent.futures and some other python features like generators, context managers and pathlib module.
import concurrent.futures as futures
import itertools
import pathlib
import nltk
BASE_PATH = pathlib.Path(__file__).parent.absolute()
def filename_generator():
"""produce filenames sequence"""
for i, j, k in itertools.product("ABCDEF", "ABCDEFGHIJKLMNOPQRSTUVWXYZ", range(100)):
yield BASE_PATH / f"{i}{j}/wiki_{k}.txt"
def worker(filename: pathlib.Path):
"""do all the job"""
out_filename = filename.with_suffix('.wikiout.txt')
with open(filename) as inp, open(out_filename, "a") as out:
for row in inp:
text = row.strip()
sent_text = nltk.sent_tokenize(text)
for sent in sent_text:
"""process sentence"""
def main():
with futures.ProcessPoolExecutor() as pool:
# mapping future->filename, useful in case of error
task_to_filename = {pool.submit(worker, f): f for f in filename_generator()}
for f in futures.as_completed(task_to_filename):
try:
f.result()
except Exception as e:
filename = task_to_filename[f]
print(f"{filename} processing failed: {e}")
if __name__ == "__main__":
main()
I am on a project that trims video at specific time ,then converts it to an audio file and save it.
But the problem is i cannot get every Newly created audio file with a specific name that is stored inside a .txt file
Here's the Code
from moviepy.editor import *
import shutil
s= open("begin.txt") #Starting time
lines1 = s.readlines()
e = open("end.txt") #End Time
lines2 = e.readlines()
t = open("title.txt") #The text file which contain the file name
lines3 = t.readlines()
print("Starting...")
for x in range(1776): #Iam triming the video files to 1777 parts
st=lines1[x]
en=lines2[x]
t=lines3[x]
print("Start Time: "+st)
print("End Time: "+en)
video = VideoFileClip("J:\Movie\SM.mp4").subclip(st, en)
video.audio.write_audiofile("J:\Movie\ audio.mp3")
shutil.move("J:\Movie\ audio.mp3","J:\Movie\Data\ "+t+".mp3")
I have tried using both shutil.move and os.rename but both produce the same Error
Here's the Output:
Starting...
Start Time: 39.33
End Time: 41.958
MoviePy - Writing audio in J:\Movie\ audio.mp3
Traceback (most recent call last):
File "C:\Users\CRPSM\Anaconda3\lib\shutil.py", line 563, in move
os.rename(src, real_dst)
OSError: [WinError 123] The filename, directory name, or volume label syntax
is incorrect: 'J:\\Marvel\\ audio.mp3' -> 'J:\\Marvel\\Data\\ Things are
never
gonna bethe same now\n.mp3'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "C:/Users/CRPSM/PycharmProjects/AC#/venv/fdsh.py", line 27, in <module>
shutil.move("J:\Marvel\ audio.mp3","J:\Marvel\Data\ "+t+".mp3")
File "C:\Users\CRPSM\Anaconda3\lib\shutil.py", line 577, in move
copy_function(src, real_dst)
File "C:\Users\CRPSM\Anaconda3\lib\shutil.py", line 263, in copy2
copyfile(src, dst, follow_symlinks=follow_symlinks)
File "C:\Users\CRPSM\Anaconda3\lib\shutil.py", line 121, in copyfile
with open(dst, 'wb') as fdst:
OSError: [Errno 22] Invalid argument: 'J:\\Marvel\\Data\\ Things are never
gonna bethe same now\n.mp3'
MoviePy - Done.
Process finished with exit code 1
1: You have an indentation error for the for-loop.
2: You should remove the '\n', which stands for newline, from each file name in you list:
from moviepy.editor import *
import shutil
s= open("begin.txt") #Starting time
lines1 = [l.strip() for l in s.readlines()]
e = open("end.txt") #End Time
lines2 = [l.strip() for l in e.readlines()]
t = open("title.txt") #The text file which contain the file name
lines3 = [l.strip() for l in t.readlines()]
print("Starting...")
for x in range(1776): #Iam triming the video files to 1777 parts
st=lines1[x]
en=lines2[x]
t=lines3[x]
print("Start Time: "+st)
print("End Time: "+en)
video = VideoFileClip("J:\Movie\SM.mp4").subclip(st, en)
video.audio.write_audiofile("J:\Movie\ audio.mp3")
shutil.move("J:\Movie\ audio.mp3","J:\Movie\Data\ "+t+".mp3")
I want make a converter based on python 3.8
I'm using imageoi API 2.6.1
Here's some of my codes what i think i did it wrong
from tkinter import *
from tkinter import filedialog
import imageio
import os
root = Tk()
ftypes = [('All Files', "*.*"), ('Webm', "*.webm")]
ttl = "Select Files(s)"
dir1 = 'D:/My Pictures/9gag'
root.fileName = filedialog.askopenfilenames(filetypes=ftypes, initialdir=dir1, title=ttl)
lst = list(root.fileName)
def path_leaf(path):
return path.strip('/').strip('\\').split('/')[-1].split('\\')[-1]
print([path_leaf(path) for path in lst])
lst2 = [path_leaf(path) for path in lst]
print(lst)
def gifMaker(inputPath, targetFormat):
outputPath = os.path.splitext(inputPath)[0] + targetFormat
print(f'converting {inputPath} \n to {outputPath}')
reader = imageio.get_reader(inputPath)
fps = reader.get_meta_data()['fps']
writer = imageio.get_writer(outputPath, fps=fps)
for frames in reader:
writer.append_data(frames)
print(f'Frame {frames}')
print('Done!')
writer.close()
for ad in lst2:
gifMaker(ad, '.gif')
And the error are shown like this
Traceback (most recent call last):
File "D:/My Pictures/GIF/GIF.py", line 41, in <module>
gifMaker(ad, '.gif')
File "D:/My Pictures/GIF/GIF.py", line 28, in gifMaker
reader = imageio.get_reader(inputPath)
File "C:\Python\Anaconda3\lib\site-packages\imageio\core\functions.py", line 173, in get_reader
request = Request(uri, "r" + mode, **kwargs)
File "C:\Python\Anaconda3\lib\site-packages\imageio\core\request.py", line 126, in __init__
self._parse_uri(uri)
File "C:\Python\Anaconda3\lib\site-packages\imageio\core\request.py", line 278, in _parse_uri
raise FileNotFoundError("No such file: '%s'" % fn)
FileNotFoundError: No such file: 'D:\My Pictures\GIF\a6VOVL2_460sv.mp4'
So, what am i missing or fault? I don't understand why the error is showing "file is not found". Can someone explain to me in detail, how these lines of error occurred?
There are several possibilities
Maybe you misstyped the path/filename.
Maybe the space in the path is causing trouble.
I'm using python 2.7
Here is my code to parse files in a folder
import linecache
import glob
path = r"G:\test\folder1"
Key = '''testresult="NOK"'''
Files = glob.glob(path+'\*.xml')
for FileName in Files:
Loop_Count = 1
while Loop_Count!= 50:
Line_Read = linecache.getline(FileName, Loop_Count)
if (Key in Line_Read):
a = FileName.split('\\')
b = len(a)-1
print a[b]
break
elif(Loop_Count == 49):
pass
Loop_Count = Loop_Count+1
print "Completed"
if folder1 has many files, i'm getting memory error
Traceback (most recent call last):
File "C:\Users\whoKnows\Desktop\test_Check111.py", line 10, in <module> Line_Read = linecache.getline(FileName, Loop_Count)
File "C:\Python27\lib\linecache.py", line 14, in getline
lines = getlines(filename, module_globals)
File "C:\Python27\lib\linecache.py", line 40, in getlines
return updatecache(filename, module_globals)
File "C:\Python27\lib\linecache.py", line 128, in updatecache
lines = fp.readlines()
MemoryError
I think its because i'm opening all the files for reading and i'm not closing them. Can anyone please tell me how to close the files While using glob.
MemoryError means you have run out of memory. You are probably loading all the files into the memory at once. Try deleting lines not needed anymore with linecache.clearcache().
I am trying to create a Python script using the PyPDF Module. What the script does it take the 'Root' folder, merges all the PDFs in it and outputs the merged PDF in an 'Output' folder and renames it to 'Root.pdf' (the folder which containes the split PDFs). What it does then is do the same with the sub-directories, giving the final output a name equal to the sub-directories.
I'm stuck when coming to process the sub-directories, giving me an error code related to some hex values. (it seems that it is getting a null value which is not in hex)
Here is the error code generated:
Traceback (most recent call last):
File "C:\Documents and Settings\student3\Desktop\Test\pdfMergerV1.py", line 76, in <module>
files_recursively(path)
File "C:\Documents and Settings\student3\Desktop\Test\pdfMergerV1.py", line 74, in files_recursively
os.path.walk(path, process_file, ())
File "C:\Python27\lib\ntpath.py", line 263, in walk
walk(name, func, arg)
File "C:\Python27\lib\ntpath.py", line 259, in walk
func(arg, top, names)
File "C:\Documents and Settings\student3\Desktop\Test\pdfMergerV1.py", line 38, in process_file
pdf = PdfFileReader(file( filename, "rb"))
File "C:\Python27\lib\site-packages\pyPdf\pdf.py", line 374, in __init__
self.read(stream)
File "C:\Python27\lib\site-packages\pyPdf\pdf.py", line 775, in read
newTrailer = readObject(stream, self)
File "C:\Python27\lib\site-packages\pyPdf\generic.py", line 67, in readObject
return DictionaryObject.readFromStream(stream, pdf)
File "C:\Python27\lib\site-packages\pyPdf\generic.py", line 531, in readFromStream
value = readObject(stream, pdf)
File "C:\Python27\lib\site-packages\pyPdf\generic.py", line 58, in readObject
return ArrayObject.readFromStream(stream, pdf)
File "C:\Python27\lib\site-packages\pyPdf\generic.py", line 153, in readFromStream
arr.append(readObject(stream, pdf))
File "C:\Python27\lib\site-packages\pyPdf\generic.py", line 69, in readObject
return readHexStringFromStream(stream)
File "C:\Python27\lib\site-packages\pyPdf\generic.py", line 276, in readHexStringFromStream
txt += chr(int(x, base=16))
ValueError: invalid literal for int() with base 16: '\x00\x00'
This is the source code for the script:
#----------------------------------------------------------------------------------------------
# Name: pdfMerger
# Purpose: Automatic merging of all PDF files in a directory and its sub-directories and
# rename them according to the folder itself. Requires the pyPDF Module
#
# Current: Processes all the PDF files in the current directory
# To-Do: Process the sub-directories.
#
# Version: 1.0
# Author: Brian Livori
#
# Created: 03/08/2011
# Copyright: (c) Brian Livori 2011
# Licence: Open-Source
#---------------------------------------------------------------------------------------------
#!/usr/bin/env <strong class="highlight">python</strong>
import os
import glob
import sys
import fnmatch
from pyPdf import PdfFileReader, PdfFileWriter
output = PdfFileWriter()
path = str(os.getcwd())
x = 0
def process_file(_, path, filelist):
for filename in filelist:
if filename.endswith('.pdf'):
filename = os.path.join(path, filename)
print "Merging " + filename
pdf = PdfFileReader(file( filename, "rb"))
x = pdf.getNumPages()
i = 0
while (i != x):
output.addPage(pdf.getPage(i))
print "Merging page: " + str(i+1) + "/" + str(x)
i += 1
output_dir = "\Output\\"
ext = ".pdf"
dir = os.path.basename(path)
outputpath = str(os.getcwd()) + output_dir
final_output = outputpath
if os.path.exists(final_output) != True:
os.mkdir(final_output)
outputStream = file(final_output + dir + ext, "wb")
os.path.join(outputStream)
output.write(outputStream)
outputStream.close()
else:
outputStream = file(final_output + dir + ext, "wb")
os.path.join(outputStream)
output.write(outputStream)
outputStream.close()
def files_recursively(topdir):
os.path.walk(path, process_file, ())
files_recursively(path)
It looks like the PDF files you are reading are not valid PDF files, or they are more exotic than PyPDF is prepared for. Are you sure you have good PDF files to read?
Also, there are a few odd things in your code, but this one might really matter:
output_dir = "\Output\\"
You have a \O escape sequence there which isn't what you want.