mirror of
https://github.com/hwchase17/langchain.git
synced 2025-04-29 12:25:37 +00:00
## Description Add `__init__` for `UnstructuredHTMLLoader` to restrict the input type to `str` or `Path`, and transfer the `self.file_path` to `str` just like `UnstructuredXMLLoader` does. ## Issue Fix #29090 ## Dependencies No changes.
52 lines
1.7 KiB
Python
52 lines
1.7 KiB
Python
from pathlib import Path
|
|
from typing import Any, List, Union
|
|
|
|
from langchain_community.document_loaders.unstructured import UnstructuredFileLoader
|
|
|
|
|
|
class UnstructuredHTMLLoader(UnstructuredFileLoader):
|
|
"""Load `HTML` files using `Unstructured`.
|
|
|
|
You can run the loader in one of two modes: "single" and "elements".
|
|
If you use "single" mode, the document will be returned as a single
|
|
langchain Document object. If you use "elements" mode, the unstructured
|
|
library will split the document into elements such as Title and NarrativeText.
|
|
You can pass in additional unstructured kwargs after mode to apply
|
|
different unstructured settings.
|
|
|
|
Examples
|
|
--------
|
|
from langchain_community.document_loaders import UnstructuredHTMLLoader
|
|
|
|
loader = UnstructuredHTMLLoader(
|
|
"example.html", mode="elements", strategy="fast",
|
|
)
|
|
docs = loader.load()
|
|
|
|
References
|
|
----------
|
|
https://unstructured-io.github.io/unstructured/bricks.html#partition-html
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
file_path: Union[str, Path],
|
|
mode: str = "single",
|
|
**unstructured_kwargs: Any,
|
|
):
|
|
"""
|
|
|
|
Args:
|
|
file_path: The path to the HTML file to load.
|
|
mode: The mode to use when loading the file. Can be one of "single",
|
|
"multi", or "all". Default is "single".
|
|
**unstructured_kwargs: Any kwargs to pass to the unstructured.
|
|
"""
|
|
file_path = str(file_path)
|
|
super().__init__(file_path=file_path, mode=mode, **unstructured_kwargs)
|
|
|
|
def _get_elements(self) -> List:
|
|
from unstructured.partition.html import partition_html
|
|
|
|
return partition_html(filename=self.file_path, **self.unstructured_kwargs) # type: ignore[arg-type]
|