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.
langchain/tests/integration_tests/document_loaders/test_sitemap.py

21 lines
639 B
Python

from langchain.document_loaders import SitemapLoader
def test_sitemap() -> None:
"""Test sitemap loader."""
loader = SitemapLoader("https://langchain.readthedocs.io/sitemap.xml")
documents = loader.load()
assert len(documents) > 1
assert "🦜🔗" in documents[0].page_content
def test_filter_sitemap() -> None:
"""Test sitemap loader."""
loader = SitemapLoader(
"https://langchain.readthedocs.io/sitemap.xml",
filter_urls=["https://langchain.readthedocs.io/en/stable/"],
)
documents = loader.load()
assert len(documents) == 1
assert "🦜🔗" in documents[0].page_content