mirror of
https://github.com/Mintplex-Labs/langchain-python.git
synced 2026-07-19 13:26:32 -04:00
qued
e4224a396b
# Unstructured XML Loader
Adds an `UnstructuredXMLLoader` class for .xml files. Works with
unstructured>=0.6.7. A plain text representation of the text with the
XML tags will be available under the `page_content` attribute in the
doc.
### Testing
```python
from langchain.document_loaders import UnstructuredXMLLoader
loader = UnstructuredXMLLoader(
"example_data/factbook.xml",
)
docs = loader.load()
```
## Who can review?
@hwchase17
@eyurtsev
23 lines
749 B
Python
23 lines
749 B
Python
"""Loader that loads Microsoft Excel files."""
|
|
from typing import Any, List
|
|
|
|
from langchain.document_loaders.unstructured import (
|
|
UnstructuredFileLoader,
|
|
validate_unstructured_version,
|
|
)
|
|
|
|
|
|
class UnstructuredXMLLoader(UnstructuredFileLoader):
|
|
"""Loader that uses unstructured to load XML files."""
|
|
|
|
def __init__(
|
|
self, file_path: str, mode: str = "single", **unstructured_kwargs: Any
|
|
):
|
|
validate_unstructured_version(min_unstructured_version="0.6.7")
|
|
super().__init__(file_path=file_path, mode=mode, **unstructured_kwargs)
|
|
|
|
def _get_elements(self) -> List:
|
|
from unstructured.partition.xml import partition_xml
|
|
|
|
return partition_xml(filename=self.file_path, **self.unstructured_kwargs)
|