Created
January 19, 2018 18:59
-
-
Save acdha/669d36f57454a1e576756acfaf9b2a24 to your computer and use it in GitHub Desktop.
Example of a chunked downloader using Requests
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
# encoding: utf-8 | |
"""Download one or more URLs with a running progress display""" | |
from __future__ import (absolute_import, division, print_function, | |
unicode_literals) | |
import os | |
import sys | |
from timeit import default_timer | |
if sys.version_info < (3, ): | |
from urllib import quote | |
from urlparse import urlsplit | |
else: | |
from urllib.parse import quote, urlsplit | |
import requests | |
if sys.version_info < (2, 7, 9): | |
print('This script requires Python >= 2.7.9 for the PEP-466 SSL improvements', | |
file=sys.stderr) | |
sys.exit(123) | |
DEFAULT_CHUNK_SIZE = 1024 * 1024 | |
def sizeof_fmt(num, suffix='B'): | |
# https://stackoverflow.com/a/1094933/59984 as an alternative to humanize | |
# or Django's filesizeformat | |
for unit in ['', 'Ki', 'Mi', 'Gi', 'Ti', 'Pi', 'Ei', 'Zi']: | |
if abs(num) < 1024.0: | |
return "%3.1f%s%s" % (num, unit, suffix) | |
num /= 1024.0 | |
return "%.1f%s%s" % (num, 'Yi', suffix) | |
def download_url(url, filename=None, chunk_size=DEFAULT_CHUNK_SIZE): | |
"""Save the contents of a URL to the provided filename""" | |
if filename is None: | |
scheme, netloc, path, query, fragment = urlsplit(url) | |
filename = os.path.basename(path) | |
if not filename: | |
filename = quote(filename, safe="") | |
print('Downloading %s to %s' % (url, filename)) | |
start_time = default_timer() | |
bytes_received = 0 | |
resp = requests.get(url, stream=True, allow_redirects=True) | |
if not resp.ok: | |
print('HTTP %d: %s for %s' % (resp.status_code, resp.reason, url)) | |
return | |
try: | |
with open(filename, 'wb') as f: | |
for chunk in resp.iter_content(chunk_size=chunk_size): | |
f.write(chunk) | |
bytes_received += len(chunk) | |
elapsed = default_timer() - start_time | |
print('Received %s in %0.03f seconds (%s/s)' % ( | |
sizeof_fmt(bytes_received), | |
elapsed, | |
sizeof_fmt(bytes_received / elapsed), | |
)) | |
except Exception as exc: | |
print('Error while retrieving %s to %s: %s' % (url, filename, exc)) | |
os.unlink(filename) | |
return | |
finally: | |
resp.close() | |
if __name__ == '__main__': | |
for url in sys.argv[1:]: | |
download_url(url) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment