Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Feature/ Add xls support #169

Merged
merged 6 commits into from
Jan 3, 2025
Merged
Show file tree
Hide file tree
Changes from 4 commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions pyproject.toml
Original file line number Diff line number Diff line change
Expand Up @@ -32,6 +32,7 @@ dependencies = [
"python-pptx",
"pandas",
"openpyxl",
"xlrd",
"pdfminer.six",
"puremagic",
"pydub",
Expand Down
26 changes: 25 additions & 1 deletion src/markitdown/_markitdown.py
Original file line number Diff line number Diff line change
Expand Up @@ -724,7 +724,30 @@ def convert(self, local_path, **kwargs) -> Union[None, DocumentConverterResult]:
if extension.lower() != ".xlsx":
return None

sheets = pd.read_excel(local_path, sheet_name=None)
sheets = pd.read_excel(local_path, sheet_name=None, engine="openpyxl")
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(
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"
Expand Down Expand Up @@ -1278,6 +1301,7 @@ def __init__(
self.register_page_converter(BingSerpConverter())
self.register_page_converter(DocxConverter())
self.register_page_converter(XlsxConverter())
self.register_page_converter(XlsConverter())
self.register_page_converter(PptxConverter())
self.register_page_converter(WavConverter())
self.register_page_converter(Mp3Converter())
Expand Down
Binary file added tests/test_files/test.xls
Binary file not shown.
12 changes: 12 additions & 0 deletions tests/test_markitdown.py
Original file line number Diff line number Diff line change
Expand Up @@ -54,6 +54,12 @@
"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",
Expand Down Expand Up @@ -176,6 +182,12 @@ def test_markitdown_local() -> None:
result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test.xlsx"))
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:
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"))
validate_strings(result, DOCX_TEST_STRINGS)
Expand Down