Fixes eager doctype regex matching when doctype is not followed by a …

…newline.
adbar · Dec 7, 2024 · 7671f3d · 7671f3d
1 parent 7067937
commit 7671f3d
Show file tree

Hide file tree

Showing 2 changed files with 8 additions and 1 deletion.
diff --git a/tests/unit_tests.py b/tests/unit_tests.py
@@ -140,6 +140,13 @@ def test_input():
         == '<!DOCTYPE html>\n<html lang="en-US">\n<head/>\n<body/>\n</html>'
     )
 
+    htmlstring = '<!DOCTYPE html><html><head></head><body>Foo <br/> Bar</body></html>'
+    beginning = htmlstring[:50].lower()
+    assert (
+        repair_faulty_html(htmlstring, beginning)
+        == '<!DOCTYPE html><html><head></head><body>Foo <br/> Bar</body></html>\n'
+    )
+
     with pytest.raises(TypeError) as err:
         assert load_html(123) is None
     assert 'incompatible' in str(err.value)

diff --git a/trafilatura/utils.py b/trafilatura/utils.py
@@ -61,7 +61,7 @@
 
 UNICODE_ALIASES = {'utf-8', 'utf_8'}
 
-DOCTYPE_TAG = re.compile("^< ?! ?DOCTYPE.+?/ ?>", re.I)
+DOCTYPE_TAG = re.compile("^< ?! ?DOCTYPE[^>]*/[^<]*>", re.I)
 FAULTY_HTML = re.compile(r"(<html.*?)\s*/>", re.I)
 HTML_STRIP_TAGS = re.compile(r'(<!--.*?-->|<[^>]*>)')