def download(force=False):
"""
Downloads and extracts the desired DBpedia datasets.
They are extracted to the app's `DATASETS_PATH` value.
"""
# Get the desired dataset urls.
dataset_urls = [dataset_url for dataset_url in get_dataset_urls() if any(setname in dataset_url for setname in DESIRED_DATASETS)]
for dataset_url in dataset_urls:
# dc = decompressed
dc_filepath = os.path.join(DATASETS_PATH,
os.path.basename(dataset_url)[:-4]) # remove '.bz2'
if os.path.exists(dc_filepath) and not force:
logger.warn('File exists, not re-downloading and extracting. You can force by passing `force=True`.')
continue
# Download the dataset.
logger.info('Downloading knowledge dataset from {0}'.format(dataset_url))
filepath = gullet.download(dataset_url, '/tmp/')
logger.info('Downloaded to {0}'.format(filepath))
# Decompress the files.
logger.info('Extracting to {0}'.format(dc_filepath))
with open(dc_filepath, 'wb+') as dc_file, bz2.BZ2File(filepath, 'rb') as file:
for data in iter(lambda : file.read(100 * 1024), b''):
dc_file.write(data)
# Clean up.
os.remove(filepath)
logger.info('Downloading and extraction complete.')
def test_ignores_existing_download(self):
"""
Download should skip if the file already
is fully downloaded and is not expired.
"""
# Set remote file to not be expired.
mock_resp = self.mock_response()
mock_resp.headers['Last-Modified'] = 'Wed, 01 Sep 2013 08:53:26 GMT'
tmpfile = self.mock_file(complete=True)
self.mock_open.return_value = tmpfile
gullet.download(self.url, self.save_path)
# Should have opened new file to append to,
# but not actually write anything.
self.assertEquals(tmpfile.tell(), self.content_length)
self.mock_open.assert_called_once_with(tmpfile.name, 'ab')
def test_restarts_expired_download(self):
"""
Download should restart if the remote
file is newer than the existing file.
"""
# Set remote file to be expired.
mock_resp = self.mock_response()
mock_resp.headers['Last-Modified'] = 'Wed, 05 Sep 2013 08:53:26 GMT'
tmpfile = self.mock_file()
self.mock_open.return_value = tmpfile
gullet.download(self.url, self.save_path)
# Should have written to new file.
self.assertEquals(tmpfile.tell(), self.content_length)
self.mock_open.assert_called_once_with(tmpfile.name, 'wb')
def test_download_continues(self):
"""
Download should continue if incomplete,
the file has not expired,
and the server supports 'Accept-Ranges'.
"""
# Set remote file to not be expired.
mock_resp = self.mock_response(partial=True)
mock_resp.headers['Last-Modified'] = 'Wed, 01 Sep 2013 08:53:26 GMT'
tmpfile = self.mock_file()
self.mock_open.return_value = tmpfile
gullet.download(self.url, self.save_path)
# Should have appended to existing file.
self.assertEquals(tmpfile.tell(), self.content_length)
self.mock_open.assert_called_once_with(tmpfile.name, 'ab')
def test_restarts_unsupported_download(self):
"""
Download should restart if the server does not
support 'Accept-Ranges'.
"""
# Set remote file to not be expired, and
# Get rid of the Accept-Ranges header.
mock_resp = self.mock_response()
mock_resp.headers['Last-Modified'] = 'Wed, 01 Sep 2013 08:53:26 GMT'
mock_resp.headers.pop('Accept-Ranges', None)
tmpfile = self.mock_file()
self.mock_open.return_value = tmpfile
gullet.download(self.url, self.save_path)
# Should have written to new file.
self.assertEquals(tmpfile.tell(), self.content_length)
self.mock_open.assert_called_with(tmpfile.name, 'wb')
def extract_image(entry_data, filename=None, save_dir='.'):
"""
Extracts and saves a representative
image for the entry.
"""
image_url = ''
if entry_data.top_image:
remote_image_url = entry_data.top_image.src
image_url = download(remote_image_url, save_dir, filename=filename)
return image_url
def extract_image(entry_data, filename=None, save_dir='.'):
"""
Extracts and saves a representative
image for the entry.
"""
image_url = ''
if entry_data.top_image:
remote_image_url = entry_data.top_image.src
image_url = download(remote_image_url, save_dir, filename=filename)
return image_url
def download(self, url):
"""
Downloads a file from the specified URL to replace
this Digester's current file.
Args:
| url (str) -- the url of the file to download
"""
# Get save directory for download.
save_path = os.path.dirname(self.file)
# Download!
saved_filepath = gullet.download(url, save_path)
# Rename downloaded file to match Digester's file.
os.rename(saved_filepath, self.file)
def download(self, url):
"""
Downloads a file from the specified URL to replace
this Digester's current file.
Args:
| url (str) -- the url of the file to download
"""
# Get save directory for download.
save_path = os.path.dirname(self.file)
# Download!
saved_filepath = gullet.download(url, save_path)
# Rename downloaded file to match Digester's file.
os.rename(saved_filepath, self.file)
def download(force=False):
"""
Downloads and extracts the desired DBpedia datasets.
They are extracted to the app's `DATASETS_PATH` value.
"""
# Get the desired dataset urls.
dataset_urls = [
dataset_url for dataset_url in get_dataset_urls()
if any(setname in dataset_url for setname in DESIRED_DATASETS)
]
for dataset_url in dataset_urls:
# dc = decompressed
dc_filepath = os.path.join(
DATASETS_PATH,
os.path.basename(dataset_url)[:-4]) # remove '.bz2'
if os.path.exists(dc_filepath) and not force:
logger.warn(
'File exists, not re-downloading and extracting. You can force by passing `force=True`.'
)
continue
# Download the dataset.
logger.info(
'Downloading knowledge dataset from {0}'.format(dataset_url))
filepath = gullet.download(dataset_url, '/tmp/')
logger.info('Downloaded to {0}'.format(filepath))
# Decompress the files.
logger.info('Extracting to {0}'.format(dc_filepath))
with open(dc_filepath, 'wb+') as dc_file, bz2.BZ2File(filepath,
'rb') as file:
for data in iter(lambda: file.read(100 * 1024), b''):
dc_file.write(data)
# Clean up.
os.remove(filepath)
logger.info('Downloading and extraction complete.')
