Support opening password protected datasets over Opendap (Fixes #1068) (#1570)

* Use the PydapDataStore.open() classmethod

* Added test for pydap password support

* Added pydap password change to whats-new.rst

* Changed test_password to test_session

* Documented type of ds in PydapDataStore

* Fixed documentation

* Removed unused import

* Added docs for using sessions with pydap

* Fixed typo

* Fixed formatting after merge

Author: mrpgraae

doc/io.rst

@@ -388,6 +388,38 @@ over the network until we look at particular values:
 
 .. image:: _static/opendap-prism-tmax.png
 
+Some servers require authentication before we can access the data. For this
+purpose we can explicitly create a :py:class:`~xarray.backends.PydapDataStore`
+and pass in a `Requests`__ session object. For example for 
+HTTP Basic authentication::
+
+    import xarray as xr
+    import requests
+
+    session = requests.Session()
+    session.auth = ('username', 'password')
+
+    store = xr.backends.PydapDataStore.open('http://example.com/data',
+                                            session=session)
+    ds = xr.open_dataset(store)
+
+`Pydap's cas module`__ has functions that generate custom sessions for 
+servers that use CAS single sign-on. For example, to connect to servers
+that require NASA's URS authentication::
+
+  import xarray as xr
+  from pydata.cas.urs import setup_session
+
+  ds_url = 'https://gpm1.gesdisc.eosdis.nasa.gov/opendap/hyrax/example.nc'
+
+  session = setup_session('username', 'password', check_url=ds_url)
+  store = xr.backends.PydapDataStore.open(ds_url, session=session)
+
+  ds = xr.open_dataset(store)
+
+__ http://docs.python-requests.org
+__ http://pydap.readthedocs.io/en/latest/client.html#authentication
+
 .. _io.rasterio:
 
 Rasterio

doc/whats-new.rst

@@ -111,6 +111,13 @@ Enhancements
   By `Joe Hamman <https://github.com/jhamman>`_ and
   `Gerrit Holl <https://github.com/gerritholl>`_.
 
+- Changed :py:class:`~xarray.backends.PydapDataStore` to take a Pydap dataset.
+  This permits opening Opendap datasets that require authentication, by
+  instantiating a Pydap dataset with a session object. Also added
+  :py:meth:`xarray.backends.PydapDataStore.open` which takes a url and session
+  object (:issue:`1068`).
+  By `Philip Graae <https://github.com/mrpgraae>`_.
+
 - Support applying rolling window operations using bottleneck's moving window
   functions on data stored as dask arrays (:issue:`1279`).
   By `Joe Hamman <https://github.com/jhamman>`_.

xarray/backends/api.py

@@ -288,7 +288,7 @@ def maybe_decode_store(store, lock=False):
             store = backends.ScipyDataStore(filename_or_obj,
                                             autoclose=autoclose)
         elif engine == 'pydap':
-            store = backends.PydapDataStore(filename_or_obj)
+            store = backends.PydapDataStore.open(filename_or_obj)
         elif engine == 'h5netcdf':
             store = backends.H5NetCDFStore(filename_or_obj, group=group,
                                            autoclose=autoclose)

xarray/backends/pydap_.py

@@ -60,9 +60,19 @@ class PydapDataStore(AbstractDataStore):
     This store provides an alternative way to access OpenDAP datasets that may
     be useful if the netCDF4 library is not available.
     """
-    def __init__(self, url):
+    def __init__(self, ds):
+        """
+        Parameters
+        ----------
+        ds : pydap DatasetType
+        """
+        self.ds = ds
+
+    @classmethod
+    def open(cls, url, session=None):
         import pydap.client
-        self.ds = pydap.client.open_url(url)
+        ds = pydap.client.open_url(url, session=session)
+        return cls(ds)
 
     def open_store_variable(self, var):
         data = indexing.LazilyIndexedArray(PydapArrayWrapper(var))

xarray/tests/test_backends.py

@@ -31,6 +31,8 @@
                assert_identical)
 from .test_dataset import create_test_data
 
+from xarray.tests import mock
+
 try:
     import netCDF4 as nc4
 except ImportError:
@@ -1509,6 +1511,14 @@ def test_cmp_local_file(self):
             self.assertDatasetEqual(actual.isel(j=slice(1, 2)),
                                     expected.isel(j=slice(1, 2)))
 
+    def test_session(self):
+        from pydap.cas.urs import setup_session
+
+        session = setup_session('XarrayTestUser', 'Xarray2017')
+        with mock.patch('pydap.client.open_url') as mock_func:
+            xr.backends.PydapDataStore.open('http://test.url', session=session)
+        mock_func.assert_called_with('http://test.url', session=session)
+
     @requires_dask
     def test_dask(self):
         with self.create_datasets(chunks={'j': 2}) as (actual, expected):