mirror of
https://github.com/hwchase17/langchain
synced 2024-10-29 17:07:25 +00:00
f7e3d97b19
- Remove unnecessary spaces from document object’s page_content of BiliBiliLoader - Fix BiliBiliLoader document and test file
21 lines
545 B
Python
21 lines
545 B
Python
from langchain.document_loaders import BiliBiliLoader
|
|
|
|
|
|
def test_bilibili_loader() -> None:
|
|
"""Test Bilibili Loader."""
|
|
loader = BiliBiliLoader(
|
|
[
|
|
"https://www.bilibili.com/video/BV1xt411o7Xu/",
|
|
"https://www.bilibili.com/video/av330407025/",
|
|
]
|
|
)
|
|
docs = loader.load()
|
|
|
|
assert len(docs) == 2
|
|
|
|
assert len(docs[0].page_content) > 0
|
|
assert docs[1].metadata["owner"]["mid"] == 398095160
|
|
|
|
assert docs[1].page_content == ""
|
|
assert docs[1].metadata["owner"]["mid"] == 398095160
|