def custom_view(self):
url = self.request.params.get('url')
if url is None:
url = self.wizard_state.get('wizard_threddsservice')['url']
# TODO: back url handling needs to be changed
back_url = None
prev = self.request.params.get('prev')
back_links = self.wizard_state.get('wizard_threddsservice').get('back_links', [])
if prev:
back_links.append(prev)
elif len(back_links) > 0:
back_links.pop()
self.wizard_state.get('wizard_threddsservice')['back_links'] = back_links
self.session.changed()
if len(back_links) > 0:
back_url = self.request.route_path('wizard_threddsbrowser', _query=[('url', back_links[-1])])
logger.debug("wizard state: %s", self.wizard_state.get('wizard_threddsservice'))
catalog = threddsclient.read_url(url)
items = []
items.extend( catalog.flat_references() )
items.extend( catalog.flat_datasets() )
fields = ['name', 'size', 'modified']
grid = Grid(self.request, items, fields, )
return dict(title=catalog.url, grid=grid, back_url=back_url)
def custom_view(self):
url = self.request.params.get('url')
if url is None:
url = self.wizard_state.get('wizard_threddsservice')['url']
# TODO: back url handling needs to be changed
back_url = None
prev = self.request.params.get('prev')
back_links = self.wizard_state.get('wizard_threddsservice').get(
'back_links', [])
if prev:
back_links.append(prev)
elif len(back_links) > 0:
back_links.pop()
self.wizard_state.get(
'wizard_threddsservice')['back_links'] = back_links
self.session.changed()
if len(back_links) > 0:
back_url = self.request.route_path('wizard_threddsbrowser',
_query=[('url', back_links[-1])
])
LOGGER.debug("wizard state: %s",
self.wizard_state.get('wizard_threddsservice'))
catalog = threddsclient.read_url(url)
items = []
items.extend(catalog.flat_references())
items.extend(catalog.flat_datasets())
fields = ['name', 'size', 'modified']
grid = Grid(
self.request,
items,
fields,
)
return dict(title=catalog.url, grid=grid, back_url=back_url)
def test_noaa():
cat = read_url('http://www.esrl.noaa.gov/psd/thredds/catalog.xml')
assert cat.name == 'THREDDS PSD Test Catalog'
assert cat.url == 'http://www.esrl.noaa.gov/psd/thredds/catalog.xml'
assert len(cat.references) == 2
cat2 = cat.references[0].follow()
assert cat2.name == 'Datasets'
assert cat2.url == 'http://www.esrl.noaa.gov/psd/thredds/catalog/Datasets/catalog.xml'
def test_noaa():
cat = read_url('http://www.esrl.noaa.gov/psd/thredds/catalog.xml')
assert cat.name == 'THREDDS PSD Test Catalog'
assert cat.url == 'http://www.esrl.noaa.gov/psd/thredds/catalog.xml'
assert len(cat.references) == 2
cat2 = cat.references[0].follow()
assert cat2.name == 'Datasets'
assert cat2.url == 'http://www.esrl.noaa.gov/psd/thredds/catalog/Datasets/catalog.xml'
def _fetch_thredds_metadata(url, title=None):
"""Fetch capabilities metadata from thredds catalog service and return record dict."""
# TODO: maybe use thredds siphon
import threddsclient
tds = threddsclient.read_url(url)
title = title or tds.name or "Unknown"
record = dict(
type='service',
title=title,
abstract="",
source=url,
format=THREDDS_TYPE,
creator='',
keywords=['thredds'],
rights='',
# subjects = '',
references=[])
return record
def harvest_service(request, url, service_type, service_name=None):
if service_type == 'thredds_catalog':
import threddsclient
tds = threddsclient.read_url(url)
title = tds.name
if service_name and len(service_name.strip()) > 2:
title = service_name
elif len(title.strip()) == 0:
title = url
record = dict(
title = title,
abstract = "",
source = url,
format = "THREDDS",
creator = '',
keywords = 'thredds',
rights = '')
publish(request, record)
else: # ogc services
request.csw.harvest(source=url, resourcetype=service_type)
def thredds_get_resources(url, depth):
cat = threddsclient.read_url(url)
name = self._resource_id(cat)
if depth == self.max_depth:
name = self.service_name
resource_type = 'directory'
if cat.datasets and cat.datasets[
0].content_type != "application/directory":
resource_type = 'file'
tree_item = {
name: {
'children': {},
'resource_type': resource_type
}
}
if depth > 0:
for reference in cat.flat_references():
tree_item[name]['children'].update(
thredds_get_resources(reference.url, depth - 1))
return tree_item
def test_invalid_url():
with pytest.raises(requests.ConnectionError):
read_url('http://example.invalid')
def download_netcdf_file_from_met(data_source=DATA_SOURCE_NEW):
archive_url = None
if data_source == DATA_SOURCE_NEW:
print("Traversing operational archive")
archive_url = OPERATIONAL_ARCHIVE_URL
elif data_source == DATA_SOURCE_OLD:
print("Traversing historical archive")
archive_url = HISTORICAL_ARCHIVE_URL
else:
raise ValueError("Invalid data source provided")
data_catalog = threddsclient.read_url(archive_url)
# Newest YEAR = operational_data_catalog.flat_references()[0], FRA nyeste år er .flat_references()[0] NYESTE MÅNED
newest_catalog_ref = \
data_catalog.flat_references()[0].follow().flat_references()[0].follow().flat_references()[0] if data_source == DATA_SOURCE_NEW else \
data_catalog.flat_references()[1].follow().flat_references()[0].follow().flat_references()[0]
download_directory_data = threddsclient.read_url(newest_catalog_ref.url)
datasets = download_directory_data.datasets[0].datasets
configuration_file = json.load(open(CONFIG_FILE_NAME)) if isfile(CONFIG_FILE_NAME) else None
repository_root_path = configuration_file["windData"]["windDataRepositoryDirectory"]
variables_to_keep = configuration_file["windData"]["windDataVariablesToKeep"]
existing_files = read_added_files()
tmp_file_path = "{root_path}{filename}".format(root_path=repository_root_path, filename=TMP_NETCDF_FILE_NAME)
for year_idx, year in enumerate(data_catalog.flat_references()):
if year.name == "raw_grid":
continue
for month_idx, month in enumerate(data_catalog.flat_references()[year_idx].follow().flat_references()):
for day_idx, day in enumerate(data_catalog.flat_references()[year_idx].follow().flat_references()[
month_idx].follow().flat_references()):
date_time = year.name + "-" + month.name + "-" + day.name
if date_time in existing_files:
continue
datasets = \
data_catalog.flat_references()[year_idx].follow().flat_references()[
month_idx].follow().flat_references()[
day_idx].follow().flat_datasets()
if datasets:
file_index = 0 # Which file to download for that given day
distance_in_hours_from_12 = 9999
for idx, file in enumerate(datasets): # List of all files for that given day
if "forecast" in file.name or "latest" in file.name:
continue
timestamp = file.name[file.name.rindex("_") + 1:].replace(".nc", "")
# Get hours from timestamp
hours = timestamp[9:11]
current_distance = calculate_distance_to_number(12, int(hours))
if current_distance == 0:
file_index = idx
break
if current_distance < distance_in_hours_from_12:
distance_in_hours_from_12 = current_distance
file_index = idx
# Download!
download_url = datasets[file_index].download_url()
req = requests.get(download_url)
if req.status_code == 200:
# Store file
print("--\nWriting tmp file to disk with location: {root_path}{file_name}".format(root_path=repository_root_path,
file_name=TMP_NETCDF_FILE_NAME))
with open(tmp_file_path, "wb") as outfile:
outfile.write(req.content)
file_name = "{file_name}_reduced.nc".format(file_name=datasets[file_index].name[:-3])
drop_attributes_and_write_to_disk(data_file_path=tmp_file_path,
result_file_path="{root_path}{filename}".format(root_path=repository_root_path,
filename=file_name),
columns_to_keep=variables_to_keep)
with open("added_files", "a+") as myfile:
myfile.write(date_time + "\n")
existing_files.append(date_time)
if os.path.exists("{root_path}{file_name}".format(root_path=repository_root_path, file_name=TMP_NETCDF_FILE_NAME)):
os.remove("{root_path}{file_name}".format(root_path=repository_root_path, file_name=TMP_NETCDF_FILE_NAME))
