Added xlsx and xls

packages/markitdown/pyproject.toml

@@ -28,9 +28,6 @@ dependencies = [
   "requests",
   "markdownify~=0.14.1",
   "numpy",
-  "pandas",
-  "openpyxl",
-  "xlrd",
   "pdfminer.six",
   "puremagic",
   "pydub",
@@ -47,10 +44,15 @@ dependencies = [
 [project.optional-dependencies]
 all = [
   "python-pptx",
-  "mammoth"
+  "mammoth",
+  "pandas",
+  "openpyxl",
+  "xlrd"
 ]
 pptx = ["python-pptx"]
 docx = ["mammoth"]
+xlsx = ["pandas", "openpyxl"]
+xls = ["pandas", "xlrd"]
 
 [project.urls]
 Documentation = "https://github.com/microsoft/markitdown#readme"

packages/markitdown/src/markitdown/converters/_plain_text_converter.py

@@ -6,6 +6,13 @@ from typing import Any, Union
 from ._base import DocumentConverter, DocumentConverterResult
 
 
+# Mimetypes to ignore (commonly confused extensions)
+IGNORE_MIMETYPES = [
+    "text/vnd.in3d.spot",  # .spo wich is confused with xls, doc, etc.
+    "text/vnd.graphviz",  # .dot which is confused with xls, doc, etc.
+]
+
+
 class PlainTextConverter(DocumentConverter):
     """Anything with content type text/plain"""
 
@@ -22,6 +29,10 @@ class PlainTextConverter(DocumentConverter):
             "__placeholder" + kwargs.get("file_extension", "")
         )
 
+        # Ignore common false positives
+        if content_type in IGNORE_MIMETYPES:
+            content_type = None
+
         # Only accept text files
         if content_type is None:
             return None

packages/markitdown/src/markitdown/converters/_xlsx_converter.py

@@ -1,9 +1,26 @@
-from typing import Union
+import sys
 
-import pandas as pd
+from typing import Union
 
 from ._base import DocumentConverter, DocumentConverterResult
 from ._html_converter import HtmlConverter
+from .._exceptions import MissingDependencyException, MISSING_DEPENDENCY_MESSAGE
+
+# Try loading optional (but in this case, required) dependencies
+# Save reporting of any exceptions for later
+_xlsx_dependency_exc_info = None
+try:
+    import pandas as pd
+    import openpyxl
+except ImportError:
+    _xlsx_dependency_exc_info = sys.exc_info()
+
+_xls_dependency_exc_info = None
+try:
+    import pandas as pd
+    import xlrd
+except ImportError:
+    _xls_dependency_exc_info = sys.exc_info()
 
 
 class XlsxConverter(HtmlConverter):
@@ -22,6 +39,18 @@ class XlsxConverter(HtmlConverter):
         if extension.lower() != ".xlsx":
             return None
 
+        # Load the dependencies
+        if _xlsx_dependency_exc_info is not None:
+            raise MissingDependencyException(
+                MISSING_DEPENDENCY_MESSAGE.format(
+                    converter=type(self).__name__,
+                    extension=".xlsx",
+                    feature="xlsx",
+                )
+            ) from _xlsx_dependency_exc_info[1].with_traceback(
+                _xlsx_dependency_exc_info[2]
+            )  # Restore the original traceback
+
         sheets = pd.read_excel(local_path, sheet_name=None, engine="openpyxl")
         md_content = ""
         for s in sheets:
@@ -46,6 +75,18 @@ class XlsConverter(HtmlConverter):
         if extension.lower() != ".xls":
             return None
 
+        # Load the dependencies
+        if _xls_dependency_exc_info is not None:
+            raise MissingDependencyException(
+                MISSING_DEPENDENCY_MESSAGE.format(
+                    converter=type(self).__name__,
+                    extension=".xls",
+                    feature="xls",
+                )
+            ) from _xls_dependency_exc_info[1].with_traceback(
+                _xls_dependency_exc_info[2]
+            )  # Restore the original traceback
+
         sheets = pd.read_excel(local_path, sheet_name=None, engine="xlrd")
         md_content = ""
         for s in sheets: