Match direct-child <br> and <em> in _stringify

legistar/base.py

@@ -232,9 +232,9 @@ def _parse_detail(self, key, field_1, field_2):
         return None
 
     def _stringify(self, field):
-        for br in field.xpath("*//br"):
+        for br in field.xpath(".//br"):
             br.tail = "\n" + br.tail if br.tail else "\n"
-        for em in field.xpath("*//em"):
+        for em in field.xpath(".//em"):
             if em.text:
                 em.text = "--em--" + em.text + "--em--"
         return field.text_content().replace(' ', ' ').strip()

tests/test_parsing.py

@@ -1,13 +1,24 @@
 import os
 
 import lxml
+import lxml.html
 import pytest
 
+from legistar.base import LegistarScraper
 from legistar.bills import LegistarBillScraper
 from legistar.events import LegistarEventsScraper
 from legistar.people import LegistarPersonScraper
 
 
+@pytest.mark.parametrize('markup, expected', [
+    ('<td>Line1<br/>Line2</td>', 'Line1\nLine2'),        # <br> is a direct child of the cell
+    ('<td><font>Line1<br/>Line2</font></td>', 'Line1\nLine2'),  # <br> nested in a child element
+])
+def test_stringify_br_becomes_newline(markup, expected):
+    scraper = LegistarScraper()
+    assert scraper._stringify(lxml.html.fromstring(markup)) == expected
+
+
 @pytest.mark.parametrize('jurisdiction', ['chicago', 'metro', 'nyc'])
 def test_parse_bills(project_directory, jurisdiction):
     bills_fixture = os.path.join(project_directory, 'tests', 'fixtures', jurisdiction, 'bills.html')