Last active
December 19, 2015 07:49
-
-
Save reclosedev/5921016 to your computer and use it in GitHub Desktop.
Seekable remote stream. Can be used to obtain listing (or download selected files) from huge .zip archives (or another structured file) from internet without downloading whole file. Requires Requests library.
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 | |
# -*- coding: utf-8 -*- | |
import requests | |
class RemoteFile(object): | |
def __init__(self, url, session=None): | |
self._url = url | |
self._session = session or requests.Session() | |
self._need_to_close_session = session is None | |
self._response = None | |
self._position = 0 | |
self._stream_position = 0 | |
self._bytes_in_stream_left = 0 | |
self.total_bytes_downloaded = 0 | |
self._ensure_ranges_supported() | |
def _ensure_ranges_supported(self): | |
try: | |
r = self._session.get(self._url, stream=True) | |
except Exception as e: | |
raise IOError(e) | |
size = r.headers['Content-Length'] | |
if not size: | |
raise IOError("Unknown Content-Length") | |
if not 'bytes' in r.headers.get('Accept-Ranges', ''): | |
raise IOError("Doesn't accept ranges") | |
self._bytes_in_stream_left = self._size = int(size) | |
self._response = r | |
def seek(self, offset, whence=0): | |
if whence == 0: | |
self._position = offset | |
if whence == 1: | |
self._position += offset | |
elif whence == 2: | |
self._position = self._size + offset | |
if not (0 <= self._position <= self._size): | |
raise IOError("Out of bounds") | |
def tell(self): | |
return self._position | |
def read(self, size=None): | |
if (self._bytes_in_stream_left | |
and self._stream_position == self._position): | |
return self._read_stream(size) | |
self._stream_position = self._position | |
end = self._size if size is None else self._position + size | |
if end > self._size: | |
return '' | |
self._bytes_in_stream_left = end - self._position | |
headers = {'Range': 'bytes=%s-%s' % (self._position, end)} | |
r = self._session.get(self._url, stream=True, headers=headers) | |
if self._response: | |
self._response.close() | |
self._response = r | |
return self._read_stream(size) | |
def _read_stream(self, size=None): | |
data = self._response.raw.read(size) | |
received = len(data) | |
self._position += received | |
self._stream_position += received | |
self._bytes_in_stream_left -= received | |
self.total_bytes_downloaded += received | |
return data | |
def close(self): | |
if self._response: | |
self._response.close() | |
if self._need_to_close_session: | |
self._session.close() | |
def __del__(self): | |
self.close() | |
# TODO tests | |
# TODO docstrings | |
if __name__ == '__main__': | |
import zipfile | |
#url = 'http://mirror.yandex.ru/mirrors/ftp.mysql.com/Downloads/MySQL-6.0/mysql-6.0.11-alpha.zip' | |
url = 'http://mirror.yandex.ru/mirrors/ftp.mysql.com/Downloads/Connector-Python/mysql-connector-python-1.0.10.zip' | |
rf = RemoteFile(url) | |
archive = zipfile.ZipFile(rf) | |
archive.printdir() | |
print 'Size:', rf._size, 'Downloaded:', rf.total_bytes_downloaded |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment