Strip img and a tags when checking phone numbers

findspam.py

@@ -155,6 +155,9 @@ def test_post(title, body, user_name, site, is_answer, body_is_summary):
             if rule['stripcodeblocks']:
                 body_to_check = regex.sub("<pre>.*?</pre>", "", body, flags=regex.DOTALL)
                 body_to_check = regex.sub("<code>.*?</code>", "", body_to_check, flags=regex.DOTALL)
+            if rule['reason'] == 'Phone number detected':
+                body_to_check = regex.sub("<img[^>]+>", "", body_to_check)
+                body_to_check = regex.sub("<a[^>]+>", "", body_to_check)
             if rule['all'] != (site in rule['sites']):
                 matched_title = regex.compile(rule['regex'], regex.UNICODE).findall(title)
                 matched_username = regex.compile(rule['regex'], regex.UNICODE).findall(user_name)

test/test_regexes.py

@@ -65,7 +65,10 @@
     (u'Как рандомно получать числа 1 и 2?', 'Body here', u'Сашка', 'ru.stackoverflow.com', False, False),
     ('Should not be caught: http://example.com', '', '', 'drupal.stackexchange.com', False, False),
     ('Should not be caught: https://www.example.com', '', '', 'drupal.stackexchange.com', False, False),
-    ('Should not be caught: something@example.com', '', '', 'drupal.stackexchange.com', False, False)
+    ('Should not be caught: something@example.com', '', '', 'drupal.stackexchange.com', False, False),
+    ('Title here', '<img src="http://example.com/11111111111.jpg" alt="my image">', '', 'stackoverflow.com', False, False),
+    ('Title here', '<img src="http://example.com/11111111111111.jpg" alt="my image" />', '', 'stackoverflow.com', False, False),
+    ('Title here', '<a href="http://example.com/11111111111111.html">page</a>', '', 'stackoverflow.com', False, False)
 ])
 def test_regexes(title, body, username, site, body_is_summary, match):
     # If we want to test answers separately, this should be changed