Constantly print Subprocess output while process is running

Question

To launch programs from my Python-scripts, I'm using the following method:

def execute(command):
    process = subprocess.Popen(command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
    output = process.communicate()[0]
    exitCode = process.returncode

    if (exitCode == 0):
        return output
    else:
        raise ProcessException(command, exitCode, output)

So when i launch a process like Process.execute("mvn clean install"), my program waits until the process is finished, and only then i get the complete output of my program. This is annoying if i'm running a process that takes a while to finish.

Can I let my program write the process output line by line, by polling the process output before it finishes in a loop or something?

I found this article which might be related.

Answer 1

You can use iter to process lines as soon as the command outputs them: lines = iter(fd.readline, ""). Here's a full example showing a typical use case (thanks to @jfs for helping out):

from __future__ import print_function # Only Python 2.x
import subprocess

def execute(cmd):
    popen = subprocess.Popen(cmd, stdout=subprocess.PIPE, universal_newlines=True)
    for stdout_line in iter(popen.stdout.readline, ""):
        yield stdout_line 
    popen.stdout.close()
    return_code = popen.wait()
    if return_code:
        raise subprocess.CalledProcessError(return_code, cmd)

# Example
for path in execute(["locate", "a"]):
    print(path, end="")

Answer 2

Ok i managed to solve it without threads (any suggestions why using threads would be better are appreciated) by using a snippet from this question Intercepting stdout of a subprocess while it is running

def execute(command):
    process = subprocess.Popen(command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)

    # Poll process for new output until finished
    while True:
        nextline = process.stdout.readline()
        if nextline == '' and process.poll() is not None:
            break
        sys.stdout.write(nextline)
        sys.stdout.flush()

    output = process.communicate()[0]
    exitCode = process.returncode

    if (exitCode == 0):
        return output
    else:
        raise ProcessException(command, exitCode, output)

Answer 3

To print subprocess' output line-by-line as soon as its stdout buffer is flushed in Python 3:

from subprocess import Popen, PIPE, CalledProcessError

with Popen(cmd, stdout=PIPE, bufsize=1, universal_newlines=True) as p:
    for line in p.stdout:
        print(line, end='') # process line here

if p.returncode != 0:
    raise CalledProcessError(p.returncode, p.args)

Notice: you do not need p.poll() -- the loop ends when eof is reached. And you do not need iter(p.stdout.readline, '') -- the read-ahead bug is fixed in Python 3.

See also, Python: read streaming input from subprocess.communicate().

Answer 4

There is actually a really simple way to do this when you just want to print the output:

import subprocess
import sys

def execute(command):
    subprocess.check_call(command, stdout=sys.stdout, stderr=subprocess.STDOUT)

Here we're simply pointing the subprocess to our own stdout, and using existing succeed or exception api.

Answer 5

@tokland

tried your code and corrected it for 3.4 and windows dir.cmd is a simple dir command, saved as cmd-file

import subprocess
c = "dir.cmd"

def execute(command):
    popen = subprocess.Popen(command, stdout=subprocess.PIPE,bufsize=1)
    lines_iterator = iter(popen.stdout.readline, b"")
    while popen.poll() is None:
        for line in lines_iterator:
            nline = line.rstrip()
            print(nline.decode("latin"), end = "\r\n",flush =True) # yield line

execute(c)

Answer 6

For anyone trying the answers to this question to get the stdout from a Python script note that Python buffers its stdout, and therefore it may take a while to see the stdout.

This can be rectified by adding the following after each stdout write in the target script:

sys.stdout.flush()

Answer 7

In case someone wants to read from both stdout and stderr at the same time using threads, this is what I came up with:

import threading
import subprocess
import Queue

class AsyncLineReader(threading.Thread):
    def __init__(self, fd, outputQueue):
        threading.Thread.__init__(self)

        assert isinstance(outputQueue, Queue.Queue)
        assert callable(fd.readline)

        self.fd = fd
        self.outputQueue = outputQueue

    def run(self):
        map(self.outputQueue.put, iter(self.fd.readline, ''))

    def eof(self):
        return not self.is_alive() and self.outputQueue.empty()

    @classmethod
    def getForFd(cls, fd, start=True):
        queue = Queue.Queue()
        reader = cls(fd, queue)

        if start:
            reader.start()

        return reader, queue


process = subprocess.Popen(command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
(stdoutReader, stdoutQueue) = AsyncLineReader.getForFd(process.stdout)
(stderrReader, stderrQueue) = AsyncLineReader.getForFd(process.stderr)

# Keep checking queues until there is no more output.
while not stdoutReader.eof() or not stderrReader.eof():
   # Process all available lines from the stdout Queue.
   while not stdoutQueue.empty():
       line = stdoutQueue.get()
       print 'Received stdout: ' + repr(line)

       # Do stuff with stdout line.

   # Process all available lines from the stderr Queue.
   while not stderrQueue.empty():
       line = stderrQueue.get()
       print 'Received stderr: ' + repr(line)

       # Do stuff with stderr line.

   # Sleep for a short time to avoid excessive CPU use while waiting for data.
   sleep(0.05)

print "Waiting for async readers to finish..."
stdoutReader.join()
stderrReader.join()

# Close subprocess' file descriptors.
process.stdout.close()
process.stderr.close()

print "Waiting for process to exit..."
returnCode = process.wait()

if returnCode != 0:
   raise subprocess.CalledProcessError(returnCode, command)

I just wanted to share this, as I ended up on this question trying to do something similar, but none of the answers solved my problem. Hopefully it helps someone!

Note that in my use case, an external process kills the process that we Popen().

Answer 8

In Python >= 3.5 using subprocess.run works for me:

import subprocess

cmd = 'echo foo; sleep 1; echo foo; sleep 2; echo foo'
subprocess.run(cmd, shell=True)

(getting the output during execution also works without shell=True) https://docs.python.org/3/library/subprocess.html#subprocess.run

Answer 9

To answer the original question, the best way IMO is just redirecting subprocess stdout directly to your program's stdout (optionally, the same can be done for stderr, as in example below)

p = Popen(cmd, stdout=sys.stdout, stderr=sys.stderr)
p.communicate()

Answer 10

This PoC constantly reads the output from a process and can be accessed when needed. Only the last result is kept, all other output is discarded, hence prevents the PIPE from growing out of memory:

import subprocess
import time
import threading
import Queue


class FlushPipe(object):
    def __init__(self):
        self.command = ['python', './print_date.py']
        self.process = None
        self.process_output = Queue.LifoQueue(0)
        self.capture_output = threading.Thread(target=self.output_reader)

    def output_reader(self):
        for line in iter(self.process.stdout.readline, b''):
            self.process_output.put_nowait(line)

    def start_process(self):
        self.process = subprocess.Popen(self.command,
                                        stdout=subprocess.PIPE)
        self.capture_output.start()

    def get_output_for_processing(self):
        line = self.process_output.get()
        print ">>>" + line


if __name__ == "__main__":
    flush_pipe = FlushPipe()
    flush_pipe.start_process()

    now = time.time()
    while time.time() - now < 10:
        flush_pipe.get_output_for_processing()
        time.sleep(2.5)

    flush_pipe.capture_output.join(timeout=0.001)
    flush_pipe.process.kill()

print_date.py

#!/usr/bin/env python
import time

if __name__ == "__main__":
    while True:
        print str(time.time())
        time.sleep(0.01)

output: You can clearly see that there is only output from ~2.5s interval nothing in between.

>>>1520535158.51
>>>1520535161.01
>>>1520535163.51
>>>1520535166.01

Answer 11

This works at least in Python3.4

import subprocess

process = subprocess.Popen(cmd_list, stdout=subprocess.PIPE)
for line in process.stdout:
    print(line.decode().strip())

Answer 12

None of the answers here addressed all of my needs.

1. No threads for stdout (no Queues, etc, either)
2. Non-blocking as I need to check for other things going on
3. Use PIPE as I needed to do multiple things, e.g. stream output, write to a log file and return a string copy of the output.

A little background: I am using a ThreadPoolExecutor to manage a pool of threads, each launching a subprocess and running them concurrency. (In Python2.7, but this should work in newer 3.x as well). I don't want to use threads just for output gathering as I want as many available as possible for other things (a pool of 20 processes would be using 40 threads just to run; 1 for the process thread and 1 for stdout...and more if you want stderr I guess)

I'm stripping back a lot of exception and such here so this is based on code that works in production. Hopefully I didn't ruin it in the copy and paste. Also, feedback very much welcome!

import time
import fcntl
import subprocess
import time

proc = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)

# Make stdout non-blocking when using read/readline
proc_stdout = proc.stdout
fl = fcntl.fcntl(proc_stdout, fcntl.F_GETFL)
fcntl.fcntl(proc_stdout, fcntl.F_SETFL, fl | os.O_NONBLOCK)

def handle_stdout(proc_stream, my_buffer, echo_streams=True, log_file=None):
    """A little inline function to handle the stdout business. """
    # fcntl makes readline non-blocking so it raises an IOError when empty
    try:
        for s in iter(proc_stream.readline, ''):   # replace '' with b'' for Python 3
            my_buffer.append(s)

            if echo_streams:
                sys.stdout.write(s)

            if log_file:
                log_file.write(s)
    except IOError:
        pass

# The main loop while subprocess is running
stdout_parts = []
while proc.poll() is None:
    handle_stdout(proc_stdout, stdout_parts)

    # ...Check for other things here...
    # For example, check a multiprocessor.Value('b') to proc.kill()

    time.sleep(0.01)

# Not sure if this is needed, but run it again just to be sure we got it all?
handle_stdout(proc_stdout, stdout_parts)

stdout_str = "".join(stdout_parts)  # Just to demo

I'm sure there is overhead being added here but it is not a concern in my case. Functionally it does what I need. The only thing I haven't solved is why this works perfectly for log messages but I see some print messages show up later and all at once.

Answer 13

In Python 3.6 I used this:

import subprocess

cmd = "command"
output = subprocess.call(cmd, shell=True)
print(process)