Add CBOE Optionable list

.idea/misc.xml

@@ -54,7 +54,7 @@
     <ConfirmationsSetting value="0" id="Add" />
     <ConfirmationsSetting value="0" id="Remove" />
   </component>
-  <component name="ProjectRootManager" version="2" languageLevel="JDK_1_3" default="false" assert-keyword="false" jdk-15="false" project-jdk-name="Python 3.5.1 virtualenv at C:\Users\Bradlee Speice\Development\metrik\metrik-virtual" project-jdk-type="Python SDK">
+  <component name="ProjectRootManager" version="2" languageLevel="JDK_1_3" default="false" assert-keyword="false" jdk-15="false" project-jdk-name="Python 3.5.1 (C:\Users\Bradlee Speice\Anaconda3\python.exe)" project-jdk-type="Python SDK">
     <output url="file://$PROJECT_DIR$/out" />
   </component>
   <component name="PythonCompatibilityInspectionAdvertiser">

metrik/tasks/cboe.py

@@ -0,0 +1,32 @@
+import requests
+import pandas as pd
+from six import StringIO
+
+from metrik.tasks.base import MongoNoBackCreateTask
+
+
+class CboeOptionableList(MongoNoBackCreateTask):
+    def get_collection_name(self):
+        return 'cboe_optionable_list'
+
+    @staticmethod
+    def retrieve_data(*args, **kwargs):
+        # Explicitly use requests to make mocking easy
+        csv_bytes = requests.get('http://www.cboe.com/publish/scheduledtask/'
+                                 'mktdata/cboesymboldir2.csv').content
+        csv_str = csv_bytes.decode('ascii')
+
+        # Because some of the fields include extra commas, we need to
+        # pre-process them out
+        old_sep = ','
+        new_sep = '|'
+        csv_rows = csv_str.split('\r\n')
+        csv_header = csv_rows[1]
+        num_cols = len(csv_header.split(old_sep))
+        csv_content = [r.replace(old_sep, new_sep, num_cols - 1)
+                       for r in csv_rows[1:]]
+        content_str = '\n'.join(csv_content)
+        csv_filelike = StringIO(content_str)
+
+        company_csv = pd.read_csv(csv_filelike, sep=new_sep)
+        return {'companies': company_csv.to_dict(orient='records')}

test/tasks/test_cboe.py

@@ -0,0 +1,12 @@
+from unittest import TestCase
+
+from metrik.tasks.cboe import CboeOptionableList
+
+
+class CboeTest(TestCase):
+
+    def test_optionable_list(self):
+        companies = CboeOptionableList.retrieve_data()['companies']
+        assert len(companies) > 2000
+        # TODO: Get lists of companies from ETF holdings and verify that they
+        # can be found here as well - this should be a superset