def urlretrieve(url, filename, reporthook=None, data=None):
def chunk_read(response, chunk_size=8192, reporthook=None):
total_size = response.info().get('Content-Length').strip()
total_size = int(total_size)
count = 0
while 1:
chunk = response.read(chunk_size)
count += 1
if not chunk:
reporthook(count, total_size, total_size)
break
if reporthook:
reporthook(count, chunk_size, total_size)
yield chunk
response = urlopen(url, data)
with open(filename, 'wb') as fd:
for chunk in chunk_read(response, reporthook=reporthook):
fd.write(chunk)
python类urlretrieve()的实例源码
def maybe_download(url, filename, prefix, num_bytes=None):
"""Takes an URL, a filename, and the expected bytes, download
the contents and returns the filename
num_bytes=None disables the file size check."""
local_filename = None
if not os.path.exists(os.path.join(prefix, filename)):
try:
print("Downloading file {}...".format(url + filename))
with tqdm(unit='B', unit_scale=True, miniters=1, desc=filename) as t:
local_filename, _ = urlretrieve(url + filename, os.path.join(prefix,filename), reporthook=reporthook(t))
except AttributeError as e:
print("An error occurred when downloading the file! Please get the dataset using a browser.")
raise e
# We have a downloaded file
# Check the stats and make sure they are ok
file_stats = os.stat(os.path.join(prefix,filename))
if num_bytes is None or file_stats.st_size == num_bytes:
print("File {} successfully loaded".format(filename))
else:
raise Exception("Unexpected dataset size. Please get the dataset using a browser.")
return local_filename
def download_exchange_symbols(exchange_name, environ=None):
"""
Downloads the exchange's symbols.json from the repository.
Parameters
----------
exchange_name: str
environ:
Returns
-------
str
"""
filename = get_exchange_symbols_filename(exchange_name)
url = SYMBOLS_URL.format(exchange=exchange_name)
response = request.urlretrieve(url=url, filename=filename)
return response
def urlretrieve(url, filename, reporthook=None, data=None):
def chunk_read(response, chunk_size=8192, reporthook=None):
total_size = response.info().get('Content-Length').strip()
total_size = int(total_size)
count = 0
while 1:
chunk = response.read(chunk_size)
count += 1
if not chunk:
reporthook(count, total_size, total_size)
break
if reporthook:
reporthook(count, chunk_size, total_size)
yield chunk
response = urlopen(url, data)
with open(filename, 'wb') as fd:
for chunk in chunk_read(response, reporthook=reporthook):
fd.write(chunk)
def urlretrieve(url, filename, reporthook=None, data=None):
'''
This function is adpated from: https://github.com/fchollet/keras
Original work Copyright (c) 2014-2015 keras contributors
'''
def chunk_read(response, chunk_size=8192, reporthook=None):
total_size = response.info().get('Content-Length').strip()
total_size = int(total_size)
count = 0
while 1:
chunk = response.read(chunk_size)
if not chunk:
break
count += 1
if reporthook:
reporthook(count, chunk_size, total_size)
yield chunk
response = urlopen(url, data)
with open(filename, 'wb') as fd:
for chunk in chunk_read(response, reporthook=reporthook):
fd.write(chunk)
def maybe_download(filename, expected_bytes, force=False):
"""Download a file if not present, and make sure it's the right size."""
if force or not os.path.exists(filename):
print('Attempting to download:', filename)
filename, _ = urlretrieve(url + filename, filename,
reporthook=download_progress_hook)
print('\nDownload Complete!')
statinfo = os.stat(filename)
if statinfo.st_size == expected_bytes:
print('Found and verified', filename)
else:
raise Exception(
'Failed to verify ' + filename + \
'. Can you get to it with a browser?')
return filename
def urlretrieve(url, filename, reporthook=None, data=None):
def chunk_read(response, chunk_size=8192, reporthook=None):
total_size = response.info().get('Content-Length').strip()
total_size = int(total_size)
count = 0
while 1:
chunk = response.read(chunk_size)
count += 1
if not chunk:
reporthook(count, total_size, total_size)
break
if reporthook:
reporthook(count, chunk_size, total_size)
yield chunk
response = urlopen(url, data)
with open(filename, 'wb') as fd:
for chunk in chunk_read(response, reporthook=reporthook):
fd.write(chunk)
def urlretrieve(url, filename, reporthook=None, data=None):
def chunk_read(response, chunk_size=8192, reporthook=None):
total_size = response.info().get('Content-Length').strip()
total_size = int(total_size)
count = 0
while 1:
chunk = response.read(chunk_size)
if not chunk:
break
count += 1
if reporthook:
reporthook(count, chunk_size, total_size)
yield chunk
response = urlopen(url, data)
with open(filename, 'wb') as fd:
for chunk in chunk_read(response, reporthook=reporthook):
fd.write(chunk)
def download(number, save_dir='./'):
"""Download pre-trained word vector
:param number: integer, default ``None``
:param save_dir: str, default './'
:return: file path for downloaded file
"""
df = load_datasets()
row = df.iloc[[number]]
url = ''.join(row.URL)
if not url:
print('The word vector you specified was not found. Please specify correct name.')
widgets = ['Test: ', Percentage(), ' ', Bar(marker=RotatingMarker()), ' ', ETA(), ' ', FileTransferSpeed()]
pbar = ProgressBar(widgets=widgets)
def dlProgress(count, blockSize, totalSize):
if pbar.max_value is None:
pbar.max_value = totalSize
pbar.start()
pbar.update(min(count * blockSize, totalSize))
file_name = url.split('/')[-1]
if not os.path.exists(save_dir):
os.makedirs(save_dir)
save_path = os.path.join(save_dir, file_name)
path, _ = urlretrieve(url, save_path, reporthook=dlProgress)
pbar.finish()
return path
def download_model(url, folder="."):
"""Download a model."""
dest = path.join(folder, path.basename(url))
urlreq.urlretrieve(url, dest)
return dest
def try_download(corpus_name):
store_path = corpus_path(corpus_name)
if os.path.exists(store_path):
return True, store_path
try:
url = download_url(corpus_name)
filename, header = urlretrieve(url, store_path)
return True, filename
except:
print("Can't download: " + corpus_name)
return False, None
def download_mnist_data():
print('Downloading {:s}...'.format(train_images))
request.urlretrieve('{:s}/{:s}'.format(parent, train_images), train_images)
print('Done')
print('Downloading {:s}...'.format(train_labels))
request.urlretrieve('{:s}/{:s}'.format(parent, train_labels), train_labels)
print('Done')
print('Downloading {:s}...'.format(test_images))
request.urlretrieve('{:s}/{:s}'.format(parent, test_images), test_images)
print('Done')
print('Downloading {:s}...'.format(test_labels))
request.urlretrieve('{:s}/{:s}'.format(parent, test_labels), test_labels)
print('Done')
print('Converting training data...')
data_train, target_train = load_mnist(train_images, train_labels,
num_train)
print('Done')
print('Converting test data...')
data_test, target_test = load_mnist(test_images, test_labels, num_test)
mnist = {}
mnist['data'] = np.append(data_train, data_test, axis=0)
mnist['target'] = np.append(target_train, target_test, axis=0)
print('Done')
print('Save output...')
with open('mnist.pkl', 'wb') as output:
six.moves.cPickle.dump(mnist, output, -1)
print('Done')
print('Convert completed')
def maybe_download(filename, expected_bytes):
"""Download a file if not present, and make sure it's the right size."""
if not os.path.exists(filename):
print('Downloading ', filename, " ...")
filename, _ = urlretrieve(url + filename, filename)
statinfo = os.stat(filename)
if statinfo.st_size == expected_bytes:
print('Found and verified', filename)
else:
raise Exception('Failed to verify' +
filename + '. Can you get to it with a browser?')
else:
print('Found and verified', filename)
return filename
def maybe_download(url, download_path, filename):
if not os.path.exists(os.path.join(download_path, filename)):
try:
print("Downloading file {}...".format(url + filename))
with TqdmUpTo(unit='B', unit_scale=True, miniters=1, desc=filename) as t:
local_filename, _ = urlretrieve(url, os.path.join(download_path, filename), reporthook=t.update_to)
except AttributeError as e:
print("An error occurred when downloading the file! Please get the dataset using a browser.")
raise e
def download_mnist_data():
print('Downloading {:s}...'.format(train_images))
request.urlretrieve('{:s}/{:s}'.format(parent, train_images), train_images)
print('Done')
print('Downloading {:s}...'.format(train_labels))
request.urlretrieve('{:s}/{:s}'.format(parent, train_labels), train_labels)
print('Done')
print('Downloading {:s}...'.format(test_images))
request.urlretrieve('{:s}/{:s}'.format(parent, test_images), test_images)
print('Done')
print('Downloading {:s}...'.format(test_labels))
request.urlretrieve('{:s}/{:s}'.format(parent, test_labels), test_labels)
print('Done')
print('Converting training data...')
data_train, target_train = load_mnist(train_images, train_labels,
num_train)
print('Done')
print('Converting test data...')
data_test, target_test = load_mnist(test_images, test_labels, num_test)
mnist = {'data': np.append(data_train, data_test, axis=0),
'target': np.append(target_train, target_test, axis=0)}
print('Done')
print('Save output...')
with open('mnist.pkl', 'wb') as output:
six.moves.cPickle.dump(mnist, output, -1)
print('Done')
print('Convert completed')
def urlretrieve(url, filename, reporthook=None, data=None):
"""Replacement for `urlretrive` for Python 2.
Under Python 2, `urlretrieve` relies on `FancyURLopener` from legacy
`urllib` module, known to have issues with proxy management.
# Arguments
url: url to retrieve.
filename: where to store the retrieved data locally.
reporthook: a hook function that will be called once
on establishment of the network connection and once
after each block read thereafter.
The hook will be passed three arguments;
a count of blocks transferred so far,
a block size in bytes, and the total size of the file.
data: `data` argument passed to `urlopen`.
"""
def chunk_read(response, chunk_size=8192, reporthook=None):
total_size = response.info().get('Content-Length').strip()
total_size = int(total_size)
count = 0
while 1:
chunk = response.read(chunk_size)
count += 1
if not chunk:
reporthook(count, total_size, total_size)
break
if reporthook:
reporthook(count, chunk_size, total_size)
yield chunk
response = urlopen(url, data)
with open(filename, 'wb') as fd:
for chunk in chunk_read(response, reporthook=reporthook):
fd.write(chunk)
def download_mnist_data():
print('Downloading {:s}...'.format(train_images))
request.urlretrieve('{:s}/{:s}'.format(parent, train_images), train_images)
print('Done')
print('Downloading {:s}...'.format(train_labels))
request.urlretrieve('{:s}/{:s}'.format(parent, train_labels), train_labels)
print('Done')
print('Downloading {:s}...'.format(test_images))
request.urlretrieve('{:s}/{:s}'.format(parent, test_images), test_images)
print('Done')
print('Downloading {:s}...'.format(test_labels))
request.urlretrieve('{:s}/{:s}'.format(parent, test_labels), test_labels)
print('Done')
print('Converting training data...')
data_train, target_train = load_mnist(train_images, train_labels,
num_train)
print('Done')
print('Converting test data...')
data_test, target_test = load_mnist(test_images, test_labels, num_test)
mnist = {}
mnist['data'] = np.append(data_train, data_test, axis=0)
mnist['target'] = np.append(target_train, target_test, axis=0)
print('Done')
print('Save output...')
with open('mnist.pkl', 'wb') as output:
six.moves.cPickle.dump(mnist, output, -1)
print('Done')
print('Convert completed')
def download_mnist_data():
print('Downloading {:s}...'.format(train_images))
request.urlretrieve('{:s}/{:s}'.format(parent, train_images), train_images)
print('Done')
print('Downloading {:s}...'.format(train_labels))
request.urlretrieve('{:s}/{:s}'.format(parent, train_labels), train_labels)
print('Done')
print('Downloading {:s}...'.format(test_images))
request.urlretrieve('{:s}/{:s}'.format(parent, test_images), test_images)
print('Done')
print('Downloading {:s}...'.format(test_labels))
request.urlretrieve('{:s}/{:s}'.format(parent, test_labels), test_labels)
print('Done')
print('Converting training data...')
data_train, target_train = load_mnist(train_images, train_labels,
num_train)
print('Done')
print('Converting test data...')
data_test, target_test = load_mnist(test_images, test_labels, num_test)
mnist = {'data': np.append(data_train, data_test, axis=0),
'target': np.append(target_train, target_test, axis=0)}
print('Done')
print('Save output...')
with open('mnist.pkl', 'wb') as output:
six.moves.cPickle.dump(mnist, output, -1)
print('Done')
print('Convert completed')
def _download_recipe(file_url, filename, contrib):
file_path = path.join(contrib, filename)
request.urlretrieve(file_url, file_path)
def maybe_download(url, data_dir, filename, expected_bytes, force=False):
"""
Download a file if not present, and make sure it's the right size.
"""
if force or not os.path.exists(os.path.join(data_dir, filename)):
filename, _ = urlretrieve(url + filename, os.path.join(data_dir, filename))
statinfo = os.stat(os.path.join(data_dir, filename))
if statinfo.st_size == expected_bytes:
print('Found and verified', filename)
else:
raise Exception(
'Failed to verify' + filename + '. Can you get to it with a browser?')
return filename
def download():
url = 'https://www.cs.toronto.edu/~kriz'
request.urlretrieve(url+'/'+fname, fname)
def download():
url = 'http://yann.lecun.com/exdb/mnist'
request.urlretrieve(url+'/'+train_image, train_image)
request.urlretrieve(url+'/'+train_label, train_label)
request.urlretrieve(url+'/'+test_image, test_image)
request.urlretrieve(url+'/'+test_label, test_label)
def download_mnist_data():
print('Downloading {:s}...'.format(train_images))
request.urlretrieve('{:s}/{:s}'.format(parent, train_images), train_images)
print('Done')
print('Downloading {:s}...'.format(train_labels))
request.urlretrieve('{:s}/{:s}'.format(parent, train_labels), train_labels)
print('Done')
print('Downloading {:s}...'.format(test_images))
request.urlretrieve('{:s}/{:s}'.format(parent, test_images), test_images)
print('Done')
print('Downloading {:s}...'.format(test_labels))
request.urlretrieve('{:s}/{:s}'.format(parent, test_labels), test_labels)
print('Done')
print('Converting training data...')
data_train, target_train = load_mnist(train_images, train_labels,
num_train)
print('Done')
print('Converting test data...')
data_test, target_test = load_mnist(test_images, test_labels, num_test)
mnist = {'data': np.append(data_train, data_test, axis=0),
'target': np.append(target_train, target_test, axis=0)}
print('Done')
print('Save output...')
with open('mnist.pkl', 'wb') as output:
six.moves.cPickle.dump(mnist, output, -1)
print('Done')
print('Convert completed')
def maybe_download(filename, expected_bytes):
"""Download a file if not present, and make sure it's the right size."""
if not os.path.exists(filename):
filename, _ = urlretrieve(url + filename, filename)
statinfo = os.stat(filename)
if statinfo.st_size == expected_bytes:
print('Found and verified %s' % filename)
else:
print(statinfo.st_size)
raise Exception(
'Failed to verify ' + filename + '. Can you get to it with a browser?')
return filename
def maybe_download(filename, expected_bytes, force=False):
"""Download a file if not present, and make sure it's the right size."""
if force or not os.path.exists(filename):
print('Attempting to download:', filename)
filename, _ = urlretrieve(url + filename, filename, reporthook=download_progress_hook)
print('\nDownload Complete!')
statinfo = os.stat(filename)
if statinfo.st_size == expected_bytes:
print('Found and verified', filename)
else:
raise Exception(
'Failed to verify ' + filename + '. Can you get to it with a browser?')
return filename
def maybe_download(filename, expected_bytes):
"""Download a file if not present, and make sure it's the right size."""
if not os.path.exists(filename):
filename, _ = urlretrieve(url + filename, filename)
statinfo = os.stat(filename)
if statinfo.st_size == expected_bytes:
print('Found and verified %s' % filename)
else:
print(statinfo.st_size)
raise Exception(
'Failed to verify ' + filename + '. Can you get to it with a browser?')
return filename
def maybe_download(filename, work_directory):
"""Download the data from Yann's website, unless it's already here."""
if not os.path.exists(work_directory):
os.mkdir(work_directory)
filepath = os.path.join(work_directory, filename)
if not os.path.exists(filepath):
filepath, _ = urlretrieve(SOURCE_URL + filename, filepath)
statinfo = os.stat(filepath)
print('Succesfully downloaded', filename, statinfo.st_size, 'bytes.')
return filepath
def maybe_download(filename, work_directory):
"""Download the data from Yann's website, unless it's already here."""
if not os.path.exists(work_directory):
os.mkdir(work_directory)
filepath = os.path.join(work_directory, filename)
if not os.path.exists(filepath):
filepath, _ = urlretrieve(SOURCE_URL + filename, filepath)
statinfo = os.stat(filepath)
print('Succesfully downloaded', filename, statinfo.st_size, 'bytes.')
return filepath
def maybe_download(filename, work_directory):
"""Download the data from Yann's website, unless it's already here."""
if not os.path.exists(work_directory):
os.mkdir(work_directory)
filepath = os.path.join(work_directory, filename)
if not os.path.exists(filepath):
filepath, _ = urlretrieve(SOURCE_URL + filename, filepath)
statinfo = os.stat(filepath)
print('Succesfully downloaded', filename, statinfo.st_size, 'bytes.')
return filepath
def maybe_download(filename, expected_bytes):
"""Download a file if not present, and make sure it's the right size."""
if not os.path.exists(filename):
filename, _ = urlretrieve(url + filename, filename)
statinfo = os.stat(filename)
if statinfo.st_size == expected_bytes:
print('Found and verified %s' % filename)
else:
print(statinfo.st_size)
raise Exception(
'Failed to verify ' + filename + '. Can you get to it with a browser?')
return filename