1
0
mirror of https://gitlab.com/fdroid/fdroidserver.git synced 2024-09-11 15:13:27 +02:00
fdroidserver/fdroidserver/net.py
Hans-Christoph Steiner 107593d3ba net: improve parsing filenames from URL
This is more relevant to issuebot than fdroidserver, but it can't hurt here
also.
2022-05-09 20:59:15 +02:00

75 lines
2.5 KiB
Python

#!/usr/bin/env python3
#
# net.py - part of the FDroid server tools
# Copyright (C) 2015 Hans-Christoph Steiner <hans@eds.org>
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with this program. If not, see <http://www.gnu.org/licenses/>.
import os
import requests
import urllib
HEADERS = {'User-Agent': 'F-Droid'}
def download_file(url, local_filename=None, dldir='tmp'):
filename = urllib.parse.urlparse(url).path.split('/')[-1]
if local_filename is None:
local_filename = os.path.join(dldir, filename)
# the stream=True parameter keeps memory usage low
r = requests.get(url, stream=True, allow_redirects=True, headers=HEADERS)
r.raise_for_status()
with open(local_filename, 'wb') as f:
for chunk in r.iter_content(chunk_size=1024):
if chunk: # filter out keep-alive new chunks
f.write(chunk)
f.flush()
return local_filename
def http_get(url, etag=None, timeout=600):
"""Download the content from the given URL by making a GET request.
If an ETag is given, it will do a HEAD request first, to see if the content changed.
Parameters
----------
url
The URL to download from.
etag
The last ETag to be used for the request (optional).
Returns
-------
A tuple consisting of:
- The raw content that was downloaded or None if it did not change
- The new eTag as returned by the HTTP request
"""
# TODO disable TLS Session IDs and TLS Session Tickets
# (plain text cookie visible to anyone who can see the network traffic)
if etag:
r = requests.head(url, headers=HEADERS, timeout=timeout)
r.raise_for_status()
if 'ETag' in r.headers and etag == r.headers['ETag']:
return None, etag
r = requests.get(url, headers=HEADERS, timeout=timeout)
r.raise_for_status()
new_etag = None
if 'ETag' in r.headers:
new_etag = r.headers['ETag']
return r.content, new_etag