forked from Archives/langchain
You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
18 lines
460 B
Python
18 lines
460 B
Python
from pathlib import Path
|
|
|
|
from langchain.document_loaders.html_bs import BSHTMLLoader
|
|
|
|
|
|
def test_bs_html_loader() -> None:
|
|
"""Test unstructured loader."""
|
|
file_path = Path(__file__).parent.parent / "examples/example.html"
|
|
loader = BSHTMLLoader(str(file_path))
|
|
docs = loader.load()
|
|
|
|
assert len(docs) == 1
|
|
|
|
metadata = docs[0].metadata
|
|
|
|
assert metadata["title"] == "Chew dad's slippers"
|
|
assert metadata["source"] == str(file_path)
|