Skip to content

Python tool for converting files and office documents to Markdown.

Add HTML support to DocumentIntelligenceConverter (#1352)

safen0sea1a3dfb60fd
diff --git a/packages/markitdown/src/markitdown/converters/_doc_intel_converter.py b/packages/markitdown/src/markitdown/converters/_doc_intel_converter.py
index ba66b5b5..fd843f23 100644
--- a/packages/markitdown/src/markitdown/converters/_doc_intel_converter.py
+++ b/packages/markitdown/src/markitdown/converters/_doc_intel_converter.py
@@ -84,6 +84,9 @@ def _get_mime_type_prefixes(types: List[DocumentIntelligenceFileType]) -> List[s
prefixes.append(
"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
)
+ elif type_ == DocumentIntelligenceFileType.HTML:
+ prefixes.append("text/html")
+ prefixes.append("application/xhtml+xml")
elif type_ == DocumentIntelligenceFileType.PDF:
prefixes.append("application/pdf")
prefixes.append("application/x-pdf")
@@ -119,6 +122,8 @@ def _get_file_extensions(types: List[DocumentIntelligenceFileType]) -> List[str]
extensions.append(".bmp")
elif type_ == DocumentIntelligenceFileType.TIFF:
extensions.append(".tiff")
+ elif type_ == DocumentIntelligenceFileType.HTML:
+ extensions.append(".html")
return extensions
diff --git a/packages/markitdown/tests/test_docintel_html.py b/packages/markitdown/tests/test_docintel_html.py
new file mode 100644
index 00000000..d0b4caa3
--- /dev/null
+++ b/packages/markitdown/tests/test_docintel_html.py
@@ -0,0 +1,26 @@
+import io
+from markitdown.converters._doc_intel_converter import (
+ DocumentIntelligenceConverter,
+ DocumentIntelligenceFileType,
+)
+from markitdown._stream_info import StreamInfo
+
+
+def _make_converter(file_types):
+ conv = DocumentIntelligenceConverter.__new__(DocumentIntelligenceConverter)
+ conv._file_types = file_types
+ return conv
+
+
+def test_docintel_accepts_html_extension():
+ conv = _make_converter([DocumentIntelligenceFileType.HTML])
+ stream_info = StreamInfo(mimetype=None, extension=".html")
+ assert conv.accepts(io.BytesIO(b""), stream_info)
+
+
+def test_docintel_accepts_html_mimetype():
+ conv = _make_converter([DocumentIntelligenceFileType.HTML])
+ stream_info = StreamInfo(mimetype="text/html", extension=None)
+ assert conv.accepts(io.BytesIO(b""), stream_info)
+ stream_info = StreamInfo(mimetype="application/xhtml+xml", extension=None)
+ assert conv.accepts(io.BytesIO(b""), stream_info)