Fix markdown conversion for headers and footers

docx2everything/converters/markdown_converter.py

@@ -511,6 +511,9 @@ def parse_body_to_markdown(root, numbering_info=None, hyperlinks=None, images=No
     markdown_parts = []
     body = root.find(qn('w:body'))
 
+    if body is None and root.tag in (qn('w:hdr'), qn('w:ftr')):
+        body = root
+
     if body is None:
         return ''
 

tests/test_markdown_header_footer.py

@@ -0,0 +1,48 @@
+import xml.etree.ElementTree as ET
+
+from docx2everything.converters.markdown_converter import parse_body_to_markdown
+
+
+W_NS = "http://schemas.openxmlformats.org/wordprocessingml/2006/main"
+
+
+def xml_root(xml):
+    return ET.fromstring(xml)
+
+
+def test_header_root_is_converted_to_markdown():
+    root = xml_root(f"""
+    <w:hdr xmlns:w="{W_NS}">
+      <w:p><w:r><w:t>Header text</w:t></w:r></w:p>
+    </w:hdr>
+    """)
+
+    markdown = parse_body_to_markdown(root)
+
+    assert markdown == "Header text"
+
+
+def test_footer_root_is_converted_to_markdown():
+    root = xml_root(f"""
+    <w:ftr xmlns:w="{W_NS}">
+      <w:p><w:r><w:t>Footer text</w:t></w:r></w:p>
+    </w:ftr>
+    """)
+
+    markdown = parse_body_to_markdown(root)
+
+    assert markdown == "Footer text"
+
+
+def test_document_body_root_still_converts_to_markdown():
+    root = xml_root(f"""
+    <w:document xmlns:w="{W_NS}">
+      <w:body>
+        <w:p><w:r><w:t>Body text</w:t></w:r></w:p>
+      </w:body>
+    </w:document>
+    """)
+
+    markdown = parse_body_to_markdown(root)
+
+    assert markdown == "Body text"