fix: list spacing in TXT output (#598)

adbar · May 16, 2024 · 1ce0e76 · 1ce0e76
1 parent 9307d90
commit 1ce0e76
Show file tree

Hide file tree

Showing 2 changed files with 7 additions and 1 deletion.
diff --git a/tests/unit_tests.py b/tests/unit_tests.py
@@ -1085,6 +1085,10 @@ def test_table_processing():
 
 def test_list_processing():
     options = DEFAULT_OPTIONS
+    # basic lists
+    my_doc = "<html><body><article><p>P 1</p><ul><li>Item 1</li><li>Item 2</li></ul><p>P 2</p></article></body></html>"
+    my_result = extract(my_doc, no_fallback=True, output_format='txt', config=ZERO_CONFIG)
+    assert my_result == "P 1\n- Item 1\n- Item 2\nP 2"
     # malformed lists (common error)
     result = etree.tostring(handle_lists(etree.fromstring('<list>Description of the list:<item>List item 1</item><item>List item 2</item><item>List item 3</item></list>'), options))
     assert result.count(b'List item') == 3

diff --git a/trafilatura/xml.py b/trafilatura/xml.py
@@ -39,7 +39,6 @@
 CONTROL_PARSER = XMLParser(remove_blank_text=True)
 
 NEWLINE_ELEMS = {
-    'item': '\n- ',
     **{tag: '\n' for tag in ['code', 'graphic', 'head', 'lb', 'list', 'p', 'quote', 'row', 'table']}
 }
 SPECIAL_FORMATTING = {'del', 'head', 'hi', 'ref'}
@@ -248,6 +247,9 @@ def replace_element_text(element, include_formatting):
                 elem_text = link_text
         else:
             LOGGER.warning("empty link: %s %s", elem_text, element.attrib)
+    # lists
+    elif element.tag == "item" and elem_text:
+        elem_text = f"- {elem_text}\n"
     return elem_text