move some goal parsing code into sharable module

The code for extracting data from a goal document can be reused.

Change-Id: I128e8bd1395713f1daa233751a25487cc0fff153
Signed-off-by: Doug Hellmann <doug@doughellmann.com>

goal_tools/goals.py

@@ -0,0 +1,38 @@
+#!/usr/bin/env python3
+
+# Licensed under the Apache License, Version 2.0 (the "License"); you may
+# not use this file except in compliance with the License. You may obtain
+# a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
+# WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
+# License for the specific language governing permissions and limitations
+# under the License.
+
+import bs4 as beautifulsoup
+import requests
+
+_SITE_TITLE = '— OpenStack Technical Committee Governance Documents'
+
+
+def _parse_goal_page(html):
+    data = {
+        'title': '',
+        'description': '',
+    }
+    bs = beautifulsoup.BeautifulSoup(html, 'html.parser')
+    data['title'] = bs.title.string or ''
+    if data['title'].endswith(_SITE_TITLE):
+        data['title'] = data['title'][:-len(_SITE_TITLE)].strip()
+    data['description'] = bs.p.text or bs.p.string or ''
+    return data
+
+
+def get_info(url):
+    html = requests.get(url)
+    data = _parse_goal_page(html.text)
+    data['url'] = url
+    return data

goal_tools/import_goal.py

@@ -19,11 +19,11 @@ import os.path
 import warnings
 
 import appdirs
-import bs4 as beautifulsoup
 import requests
 import yaml
 
 from goal_tools import storyboard
+from goal_tools import goals
 
 _GOVERNANCE_PROJECT_NAME = 'openstack/governance'
 _STORY_URL_TEMPLATE = 'https://storyboard.openstack.org/#!/story/{}'
@@ -57,29 +57,6 @@ def _get_worklist_settings(tag):
         }
 
 
-_SITE_TITLE = '— OpenStack Technical Committee Governance Documents'
-
-
-def _parse_goal_page(html):
-    data = {
-        'title': '',
-        'description': '',
-    }
-    bs = beautifulsoup.BeautifulSoup(html, 'html.parser')
-    data['title'] = bs.title.string or ''
-    if data['title'].endswith(_SITE_TITLE):
-        data['title'] = data['title'][:-len(_SITE_TITLE)].strip()
-    data['description'] = bs.p.text or bs.p.string or ''
-    return data
-
-
-def _get_goal_info(url):
-    html = requests.get(url)
-    data = _parse_goal_page(html.text)
-    data['url'] = url
-    return data
-
-
 def _get_project_info(url):
     response = requests.get(url)
     data = yaml.safe_load(response.text)
@@ -187,7 +164,7 @@ def main():
 
     try:
         LOG.debug('reading goal info from {}'.format(args.goal_url))
-        goal_info = _get_goal_info(args.goal_url)
+        goal_info = goals.get_info(args.goal_url)
     except Exception as err:
         parser.error(err)
     full_description = (goal_info['description'] +