fix: node pruning raising an AttributeError in certain cases (#761)

Fixes #760
adbar · Dec 4, 2024 · 76200b7 · 76200b7
1 parent c6e8340
commit 76200b7
Show file tree

Hide file tree

Showing 2 changed files with 7 additions and 1 deletion.
diff --git a/tests/filters_tests.py b/tests/filters_tests.py
@@ -100,15 +100,21 @@ def doc3():
         my_h2 = '<h2>42</h2>'
         return html.fromstring('<html><body>' + my_h1 + my_h2 + my_p*50 + '</body></html>')
 
+    def doc4():
+        my_p = '<p>abc</p>'
+        return html.fromstring('<html><body>' + my_p + '</body></html><!-- comment -->')
+
     #test xpath pruning
     assert extract(doc(), prune_xpath='//p') == ''
     assert extract(doc2(), prune_xpath='//p') == 'ABC'
     assert extract(doc2(), prune_xpath=['//p', '//h1']) == ''
     assert extract(doc3(), prune_xpath=['//p', '//h1']) == '42'
+    assert extract(doc4(), prune_xpath=['//comment()']) == 'abc'
     # sanity check
     assert extract(doc()) != ''
     assert extract(doc2()) != ''
     assert extract(doc3()) != ''
+    assert extract(doc4()) != ''
 
 
 if __name__ == '__main__':

diff --git a/trafilatura/htmlprocessing.py b/trafilatura/htmlprocessing.py
@@ -109,7 +109,7 @@ def prune_unwanted_nodes(
                     # There is a previous node, append text to its tail
                     prev.tail = (prev.tail or "") + " " + subtree.tail
             # remove the node
-            subtree.getparent().remove(subtree)
+            delete_element(subtree)
 
     if with_backup:
         new_len = len(tree.text_content())