max_records = 2000
# <markdowncell>
# ### Is data available for the basic oceanography variables in the CSW endpoints for multiple locations?
#
# #### Check the CSW endpoints for each variable and location
# <markdowncell>
# <div class="warning"><strong>This next cell takes a long time to process!</strong> <br>Go grab a coffee</div>
# <codecell>
# Add a waitbar to monitor status
divid = insert_progress_bar(title='Searching catalogs. Please wait...',
color='red')
# Save all of the results in a list of Dataframes
results = {}
all_data = []
count = 0
# Loop through the csw endpoints
for endpoint in endpoints:
print '\n' + endpoint
csw = CatalogueServiceWeb(endpoint, timeout=60)
# loop through the variables
for var_name in names_dict:
# print '\n' + var_name.upper()
num_recs = []
# <div class="error"><strong>Processing long time series</strong> -
# The CO-OPS Server responds really slow (> 30 secs, for what should be
# a 5 sec request) to multiple requests, so getting long time series
# data is almost impossible.</div>
# <markdowncell>
# <div class="info">
# <strong>Use NDBC DAP endpoints to get time-series data</strong> -
# The DAP server for met data is available for NDBC, we use that
# to get long time series data.</div>
# <codecell>
divid = insert_progress_bar(title='Please wait...', color='red')
# Used to define the number of days allowable by the service.
coops_point_max_days = ndbc_point_max_days = 30
print("start & end dates: %s, %s\n" % (jd_start, jd_stop))
num_stations = len(st_list.keys())
count = 0
for station in st_list.keys():
count += 1
# Set it so we can use it later.
st = station.split(":")[-1]
print('[%s]: %s' % (st_list[station]['source'], st))
if st_list[station]['source'] == 'coops':
# Coops fails for large requests.
master_df = pd.DataFrame()
elif st_list[station]['source'] == 'ndbc':
# <div class="error"><strong>Processing long time series</strong> -
# The CO-OPS Server responds really slow (> 30 secs, for what should be
# a 5 sec request) to multiple requests, so getting long time series
# data is almost impossible.</div>
# <markdowncell>
# <div class="info">
# <strong>Use NDBC DAP endpoints to get time-series data</strong> -
# The DAP server for met data is available for NDBC, we use that
# to get long time series data.</div>
# <codecell>
divid = insert_progress_bar(title='Please wait...', color='red')
# Used to define the number of days allowable by the service.
coops_point_max_days = ndbc_point_max_days = 30
print("start & end dates: %s, %s\n" % (jd_start, jd_stop))
num_stations = len(st_list.keys())
count = 0
for station in st_list.keys():
count += 1
# Set it so we can use it later.
st = station.split(":")[-1]
print('[%s]: %s' % (st_list[station]['source'], st))
if st_list[station]['source'] == 'coops':
# Coops fails for large requests.
master_df = pd.DataFrame()
elif st_list[station]['source'] == 'ndbc':
max_records = 2000
# <markdowncell>
# ### Is data available for the basic oceanography variables in the CSW endpoints for multiple locations?
#
# #### Check the CSW endpoints for each variable and location
# <markdowncell>
# <div class="warning"><strong>This next cell takes a long time to process!</strong> <br>Go grab a coffee</div>
# <codecell>
# Add a waitbar to monitor status
divid = insert_progress_bar(title='Searching catalogs. Please wait...', color='red')
# Save all of the results in a list of Dataframes
results = {}
all_data = []
count = 0
# Loop through the csw endpoints
for endpoint in endpoints:
print '\n' + endpoint
csw = CatalogueServiceWeb(endpoint, timeout=60)
# loop through the variables
for var_name in names_dict:
# print '\n' + var_name.upper()
num_recs = []
