Merge 1c0362f375 into 73ba69d8cd

pyproject.toml

@@ -30,9 +30,8 @@ dependencies = [
   "markdownify",
   "numpy",
   "python-pptx",
-  "pandas",
+  "python-calamine",
-  "openpyxl",
+  "tabulate",
-  "xlrd",
   "pdfminer.six",
   "puremagic",
   "pydub",

src/markitdown/_markitdown.py

@@ -22,10 +22,11 @@ from warnings import warn, resetwarnings, catch_warnings
 import mammoth
 import markdownify
 import olefile
-import pandas as pd
 import pdfminer
 import pdfminer.high_level
 import pptx
+from python_calamine import load_workbook
+from tabulate import tabulate
 
 # File-format detection
 import puremagic
@@ -737,46 +738,24 @@ class DocxConverter(HtmlConverter):
         return result
 
 
-class XlsxConverter(HtmlConverter):
+class ExcelConverter(HtmlConverter):
     """
-    Converts XLSX files to Markdown, with each sheet presented as a separate Markdown table.
+    Converts Excel (XLSX, XLS, XLSM or XLSB) files to Markdown, with each sheet presented as a separate Markdown table.
     """
 
     def convert(self, local_path, **kwargs) -> Union[None, DocumentConverterResult]:
-        # Bail if not a XLSX
+        # Bail if not a XLSX, XLS, XLSM or XLSB
         extension = kwargs.get("file_extension", "")
-        if extension.lower() != ".xlsx":
+        if extension.lower() not in [".xlsx", ".xls", ".xlsb", ".xlsm"]:
             return None
 
-        sheets = pd.read_excel(local_path, sheet_name=None, engine="openpyxl")
+        workbook = load_workbook(local_path)
         md_content = ""
-        for s in sheets:
+        for s in workbook.sheet_names:
+            sheet = workbook.get_sheet_by_name(s)
+            tabular_data = sheet.to_python(skip_empty_area=False)
             md_content += f"## {s}\n"
-            html_content = sheets[s].to_html(index=False)
+            html_content = tabulate(tabular_data, tablefmt="html")
-            md_content += self._convert(html_content).text_content.strip() + "\n\n"
-
-        return DocumentConverterResult(
-            title=None,
-            text_content=md_content.strip(),
-        )
-
-
-class XlsConverter(HtmlConverter):
-    """
-    Converts XLS files to Markdown, with each sheet presented as a separate Markdown table.
-    """
-
-    def convert(self, local_path, **kwargs) -> Union[None, DocumentConverterResult]:
-        # Bail if not a XLS
-        extension = kwargs.get("file_extension", "")
-        if extension.lower() != ".xls":
-            return None
-
-        sheets = pd.read_excel(local_path, sheet_name=None, engine="xlrd")
-        md_content = ""
-        for s in sheets:
-            md_content += f"## {s}\n"
-            html_content = sheets[s].to_html(index=False)
             md_content += self._convert(html_content).text_content.strip() + "\n\n"
 
         return DocumentConverterResult(
@@ -1533,8 +1512,7 @@ class MarkItDown:
         self.register_page_converter(YouTubeConverter())
         self.register_page_converter(BingSerpConverter())
         self.register_page_converter(DocxConverter())
-        self.register_page_converter(XlsxConverter())
+        self.register_page_converter(ExcelConverter())
-        self.register_page_converter(XlsConverter())
         self.register_page_converter(PptxConverter())
         self.register_page_converter(WavConverter())
         self.register_page_converter(Mp3Converter())

tests/test_markitdown.py

@@ -54,12 +54,6 @@ XLSX_TEST_STRINGS = [
     "affc7dad-52dc-4b98-9b5d-51e65d8a8ad0",
 ]
 
-XLS_TEST_STRINGS = [
-    "## 09060124-b5e7-4717-9d07-3c046eb",
-    "6ff4173b-42a5-4784-9b19-f49caff4d93d",
-    "affc7dad-52dc-4b98-9b5d-51e65d8a8ad0",
-]
-
 DOCX_TEST_STRINGS = [
     "314b0a30-5b04-470b-b9f7-eed2c2bec74a",
     "49e168b7-d2ae-407f-a055-2167576f39a1",
@@ -196,11 +190,17 @@ def test_markitdown_local() -> None:
     result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test.xlsx"))
     validate_strings(result, XLSX_TEST_STRINGS)
 
+    # Test XLSB processing
+    result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test.xlsb"))
+    validate_strings(result, XLSX_TEST_STRINGS)
+
+    # Test XLSM processing
+    result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test.xlsm"))
+    validate_strings(result, XLSX_TEST_STRINGS)
+
     # Test XLS processing
     result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test.xls"))
-    for test_string in XLS_TEST_STRINGS:
+    validate_strings(result, XLSX_TEST_STRINGS)
-        text_content = result.text_content.replace("\\", "")
-        assert test_string in text_content
 
     # Test DOCX processing
     result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test.docx"))