mirror of
https://github.com/Mintplex-Labs/langchain-python.git
synced 2026-07-22 17:25:22 -04:00
Harrison Chase
14 lines
408 B
Python
14 lines
408 B
Python
"""Loader that loads PDF files."""
|
|
from typing import List
|
|
|
|
from langchain.document_loaders.unstructured import UnstructuredFileLoader
|
|
|
|
|
|
class UnstructuredHTMLLoader(UnstructuredFileLoader):
|
|
"""Loader that uses unstructured to load HTML files."""
|
|
|
|
def _get_elements(self) -> List:
|
|
from unstructured.partition.html import partition_html
|
|
|
|
return partition_html(filename=self.file_path)
|