In [1]:
from owslib.csw import CatalogueServiceWeb
from owslib import fes
In [2]:
# simple query for text only
val='gamssa'
filter_list = [fes.PropertyIsLike(propertyname='apiso:AnyText',literal=('*%s*' % val),
escapeChar='\\',wildCard='*',singleChar='?')]
In [3]:
def service_urls(records,service_string='urn:x-esri:specification:ServiceType:odp:url'):
"""
Get all URLs matching a specific ServiceType
Unfortunately these seem to differ between different CSW-ISO services.
For example, OpenDAP is specified:
NODC geoportal: 'urn:x-esri:specification:ServiceType:OPeNDAP'
NGDC geoportal: 'urn:x-esri:specification:ServiceType:odp:url'
"""
urls=[]
for key,rec in records.iteritems():
#create a generator object, and iterate through it until the match is found
#if not found, gets the default value (here "none")
url = next((d['url'] for d in rec.references if d['scheme'] == service_string), None)
if url is not None:
urls.append(url)
return urls
In [4]:
endpoint = 'http://data.nodc.noaa.gov/geoportal/csw'
csw = CatalogueServiceWeb(endpoint,timeout=60)
print csw.version
In [5]:
for oper in csw.operations:
if oper.name == 'GetRecords':
print '\nISO Queryables:\n',oper.constraints['SupportedISOQueryables']['values']
In [6]:
csw.getrecords2(constraints=filter_list,maxrecords=10000,esn='full')
len(csw.records.keys())
Out[6]:
In [7]:
choice=random.choice(list(csw.records.keys()))
print choice
csw.records[choice].references
Out[7]:
In [8]:
#find all WMS URLs
wms_urls = service_urls(csw.records,service_string='urn:x-esri:specification:ServiceType:WMS')
len(wms_urls)
Out[8]:
In [9]:
endpoint = 'http://www.nodc.noaa.gov/geoportal/csw'
csw = CatalogueServiceWeb(endpoint,timeout=60)
csw.version
Out[9]:
In [10]:
for oper in csw.operations:
if oper.name == 'GetRecords':
print '\nISO Queryables:\n',oper.constraints['SupportedISOQueryables']['values']
In [11]:
csw.getrecords2(constraints=filter_list,maxrecords=10000,esn='full')
len(csw.records.keys())
Out[11]:
In [12]:
choice=random.choice(list(csw.records.keys()))
print choice
csw.records[choice].references
Out[12]:
In [13]:
#find all WMS URLs
wms_urls = service_urls(csw.records,service_string='urn:x-esri:specification:ServiceType:WMS')
len(wms_urls)
Out[13]:
In [14]:
endpoint = 'http://catalog.data.gov/csw' # catalog.data.gov CSW
csw = CatalogueServiceWeb(endpoint,timeout=60)
csw.version
Out[14]:
In [15]:
for oper in csw.operations:
if oper.name == 'GetRecords':
print '\nISO Queryables:\n',oper.constraints['SupportedISOQueryables']['values']
In [16]:
csw.getrecords2(constraints=filter_list,maxrecords=10000,esn='full')
len(csw.records.keys())
Out[16]:
In [17]:
choice=random.choice(list(csw.records.keys()))
print choice
csw.records[choice].references
Out[17]:
From the above, we can see that because the 'scheme' is 'None' on all the references, we can't extract the different service types, like OPeNDAP, WCS, etc.
In [18]:
#find all WMS URLs
wms_urls = service_urls(csw.records,service_string='urn:x-esri:specification:ServiceType:WMS')
len(wms_urls)
Out[18]:
In [19]:
endpoint = 'http://catalog.data.gov/csw-all'
csw = CatalogueServiceWeb(endpoint,timeout=60)
print csw.version
In [20]:
for oper in csw.operations:
if oper.name == 'GetRecords':
print '\nISO Queryables:\n',oper.constraints['SupportedISOQueryables']['values']
In [21]:
csw.getrecords2(constraints=filter_list,maxrecords=10000,esn='full')
len(csw.records.keys())
Out[21]:
In [22]:
choice=random.choice(list(csw.records.keys()))
print choice
csw.records[choice].references
Out[22]:
In [23]:
#find all WMS URLs
wms_urls = service_urls(csw.records,service_string='urn:x-esri:specification:ServiceType:WMS')
len(wms_urls)
Out[23]:
In [23]: