mirror of
https://github.com/hwchase17/langchain.git
synced 2025-11-13 17:19:37 +00:00
a97e4252e3
# Unstructured Excel Loader
Adds an `UnstructuredExcelLoader` class for `.xlsx` and `.xls` files.
Works with `unstructured>=0.6.7`. A plain text representation of the
Excel file will be available under the `page_content` attribute in the
doc. If you use the loader in `"elements"` mode, an HTML representation
of the Excel file will be available under the `text_as_html` metadata
key. Each sheet in the Excel document is its own document.
### Testing
```python
from langchain.document_loaders import UnstructuredExcelLoader
loader = UnstructuredExcelLoader(
"example_data/stanley-cups.xlsx",
mode="elements"
)
docs = loader.load()
```
## Who can review?
@hwchase17
@eyurtsev
16 lines
432 B
Python
16 lines
432 B
Python
import os
|
|
from pathlib import Path
|
|
|
|
from langchain.document_loaders import UnstructuredExcelLoader
|
|
|
|
EXAMPLE_DIRECTORY = file_path = Path(__file__).parent.parent / "examples"
|
|
|
|
|
|
def test_unstructured_excel_loader() -> None:
|
|
"""Test unstructured loader."""
|
|
file_path = os.path.join(EXAMPLE_DIRECTORY, "stanley-cups.xlsx")
|
|
loader = UnstructuredExcelLoader(str(file_path))
|
|
docs = loader.load()
|
|
|
|
assert len(docs) == 1
|