How to measure download speed and progress using r

Question

I am using requests to download files, but for large files I need to check the size of the file on disk every time because I can't display the progress in percentage and I would also like to know the download speed. How can I go about doing it ? Here's my code :

import requests
import sys
import time
import os

def downloadFile(url, directory) :
  localFilename = url.split('/')[-1]
  r = requests.get(url, stream=True)

  start = time.clock()
  f = open(directory + '/' + localFilename, 'wb')
  for chunk in r.iter_content(chunk_size = 512 * 1024) :
        if chunk :
              f.write(chunk)
              f.flush()
              os.fsync(f.fileno())
  f.close()
  return (time.clock() - start)

def main() :
  if len(sys.argv) > 1 :
        url = sys.argv[1]
  else :
        url = raw_input("Enter the URL : ")
  directory = raw_input("Where would you want to save the file ?")

  time_elapsed = downloadFile(url, directory)
  print "Download complete..."
  print "Time Elapsed: " + time_elapsed


if __name__ == "__main__" :
  main()

I think one way to do it would be to read the file every time in the for loop and calculate the percentage of progress based on the header Content-Length. But that would be again an issue for large files(around 500MB). Is there any other way to do it?

Answer 1

see here: Python progress bar and downloads

i think the code would be something like this, it should show the average speed since start as bytes per second:

import requests
import sys
import time

def downloadFile(url, directory) :
  localFilename = url.split('/')[-1]
  with open(directory + '/' + localFilename, 'wb') as f:
    start = time.clock()
    r = requests.get(url, stream=True)
    total_length = r.headers.get('content-length')
    dl = 0
    if total_length is None: # no content length header
      f.write(r.content)
    else:
      for chunk in r.iter_content(1024):
        dl += len(chunk)
        f.write(chunk)
        done = int(50 * dl / total_length)
        sys.stdout.write("\r[%s%s] %s bps" % ('=' * done, ' ' * (50-done), dl//(time.clock() - start)))
        print ''
  return (time.clock() - start)

def main() :
  if len(sys.argv) > 1 :
        url = sys.argv[1]
  else :
        url = raw_input("Enter the URL : ")
  directory = raw_input("Where would you want to save the file ?")

  time_elapsed = downloadFile(url, directory)
  print "Download complete..."
  print "Time Elapsed: " + time_elapsed


if __name__ == "__main__" :
  main()