Get IBE's query_region_async function minimally working

astroquery/ibe/__init__.py

@@ -14,8 +14,9 @@ class Conf(_config.ConfigNamespace):
     Configuration parameters for `astroquery.ibe`.
     """
 
+    # For some reason the IBE in the URL is case sensitive
     server = _config.ConfigItem(
-        'http://irsa.ipac.caltech.edu/ibe/',
+        'http://irsa.ipac.caltech.edu/IBE/',
         'Name of the IBE server to use.')
     mission = _config.ConfigItem(
         'ptf',
@@ -24,12 +25,11 @@ class Conf(_config.ConfigNamespace):
 
     dataset = _config.ConfigItem(
         'images',
-        ('Default data set. See, for example, '
-         'http://irsa.ipac.caltech.edu/ibe/search/ptf for options.'))
+        ('This option is meaningless in the context of IRSA\'s ibe.'))
     table = _config.ConfigItem(
-        'level1',
-        ('Default table. See, for example, '
-         'http://irsa.ipac.caltech.edu/ibe/search/ptf/images for options.'))
+        'ptf.ptf_procimg',
+        ('Default table. Select the desired mission at '
+         'http://irsa.ipac.caltech.edu/ibe/search/ for options.'))
     timeout = _config.ConfigItem(
         60,
         'Time limit for connecting to the IRSA server.')

astroquery/ibe/core.py

@@ -10,11 +10,14 @@
 from __future__ import print_function, division
 
 import os
+import sys
+
 import webbrowser
 from bs4 import BeautifulSoup
 
 import astropy.coordinates as coord
 from astropy.table import Table
+from astropy.io.ascii.html import HTML
 import six
 
 from ..exceptions import InvalidQueryError
@@ -24,6 +27,14 @@
 
 __all__ = ['Ibe', 'IbeClass']
 
+if sys.version_info[0] >= 3:
+    decode = lambda x: x.decode()
+    encode = lambda x: bytes(x, "ascii")
+
+else:
+    decode = lambda x: x
+    encode = lambda x: x
+
 
 class IbeClass(BaseQuery):
     URL = conf.server
@@ -107,7 +118,8 @@ def query_region(
         # Raise exception, if request failed
         response.raise_for_status()
 
-        return Table.read(response.text, format='ipac', guess=False)
+        return commons.parse_votable(
+            encode(response.text)).get_first_table().to_table()
 
     def query_region_sia(self, coordinate=None, mission=None,
                          dataset=None, table=None, width=None,
@@ -156,8 +168,10 @@ def query_region_async(
             SQL-like query string. Required if ``coordinates`` is absent.
         mission : str
             The mission to be used (if not the default mission).
+            Note: this kwarg is not actually used here.
         dataset : str
             The dataset to be used (if not the default dataset).
+            Note: this option is meaningless to the ibe service.
         table : str
             The table to be queried (if not the default table).
         columns : str, list
@@ -195,7 +209,8 @@ def query_region_async(
             The action to perform at the server.  The default is ``'search'``,
             which returns a table of the available data.  ``'data'`` requires
             advanced path construction that is not yet supported. ``'sia'``
-            provides access to the 'simple image access' IVOA protocol
+            is here for legacy reasons. This function is built around IRSA's
+            VO TAP API. IRSA's SIA API is completely different.
 
         Returns
         -------
@@ -220,8 +235,16 @@ def query_region_async(
                 "The action='data' option is a placeholder for future " +
                 "functionality.")
 
+        if action == "sia":
+            raise ValueError(
+                "The action='sia' is not implemented for IRSA's IBE "
+                "interface because IRSA's SIA interface is radically "
+                "different.")
+
         args = {
-            'INTERSECT': intersect
+            'INTERSECT': intersect,
+            'TABLE': table or self.TABLE,
+            'RESPONSEFORMAT': "VOTABLE"
         }
 
         # Note: in IBE, if 'mcen' argument is present, it is true.
@@ -247,14 +270,11 @@ def query_region_async(
                 columns = columns.split()
             args['columns'] = ','.join(columns)
 
-        url = "{URL}{action}/{mission}/{dataset}/{table}".format(
-                URL=self.URL,
-                action=action,
-                mission=mission or self.MISSION,
-                dataset=dataset or self.DATASET,
-                table=table or self.TABLE)
+        url = self.URL.rstrip("/")
+
+        response = self._request('GET', url, args, timeout=self.TIMEOUT)
 
-        return self._request('GET', url, args, timeout=self.TIMEOUT)
+        return response
 
     def list_missions(self, cache=True):
         """
@@ -276,14 +296,17 @@ def list_missions(self, cache=True):
 
             root = BeautifulSoup(response.text)
             links = root.findAll('a')
-            missions = [os.path.basename(a.attrs['href']) for a in links]
+
+            missions = [os.path.basename(a.attrs['href'].rstrip('/'))
+                            for a in links]
             self._missions = missions
 
         return missions
 
     def list_datasets(self, mission=None, cache=True):
         """
-        For a given mission, list the available datasets
+        For a given mission, list the available datasets.
+        This level has no meaning in IRSA's ibe service.
 
         Parameters
         ----------
@@ -299,24 +322,8 @@ def list_datasets(self, mission=None, cache=True):
         datasets : list
             A list of dataset names
         """
-        if mission is None:
-            mission = self.MISSION
-        if mission not in self.list_missions():
-            raise ValueError("Invalid mission specified: {0}."
-                             "Must be one of: {1}"
-                             .format(mission, self.list_missions()))
 
-        url = "{URL}search/{mission}/".format(URL=self.URL, mission=mission)
-        response = self._request('GET', url, timeout=self.TIMEOUT,
-                                 cache=cache)
-
-        root = BeautifulSoup(response.text)
-        links = root.findAll('a')
-        datasets = [a.text for a in links
-                    if a.attrs['href'].count('/') >= 4  # shown as '..'; ignore
-                    ]
-
-        return datasets
+        return ["images"]
 
     def list_tables(self, mission=None, dataset=None, cache=True):
         """
@@ -358,9 +365,7 @@ def list_tables(self, mission=None, dataset=None, cache=True):
                              .format(dataset, mission,
                                      self.list_datasets(mission, cache=True)))
 
-        url = "{URL}search/{mission}/{dataset}/".format(URL=self.URL,
-                                                        mission=mission,
-                                                        dataset=dataset)
+        url = "{URL}search/{mission}/".format(URL=self.URL, mission=mission)
         response = self._request('GET', url, timeout=self.TIMEOUT,
                                  cache=cache)
 
@@ -386,10 +391,9 @@ def show_docs(self, mission=None, dataset=None, table=None):
             The table to be queried (if not the default table).
         """
 
-        url = "{URL}docs/{mission}/{dataset}/{table}".format(
+        url = "{URL}docs/{mission}/{table}".format(
                 URL=self.URL,
                 mission=mission or self.MISSION,
-                dataset=dataset or self.DATASET,
                 table=table or self.TABLE)
 
         return webbrowser.open(url)
@@ -413,19 +417,20 @@ def get_columns(self, mission=None, dataset=None, table=None):
             A table containing a description of the columns
         """
 
-        url = "{URL}search/{mission}/{dataset}/{table}".format(
+        url = "{URL}search/{mission}/{table}/".format(
                 URL=self.URL,
                 mission=mission or self.MISSION,
-                dataset=dataset or self.DATASET,
                 table=table or self.TABLE)
 
         response = self._request(
-            'GET', url, {'FORMAT': 'METADATA'}, timeout=self.TIMEOUT)
+            'GET', url, {'FORMAT': 'METADATA'},
+            timeout=self.TIMEOUT)
 
         # Raise exception, if request failed
         response.raise_for_status()
+        HTMLtoTable = HTML()
 
-        return Table.read(response.text, format='ipac', guess=False)
+        return HTMLtoTable.read(response.text)
 
 
 Ibe = IbeClass()