github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-04 12:39:32 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #18423

Browse Source 
* Implement lazy_load() for BSHTMLLoader
This commit is contained in:
Christophe Bornet
2024-03-06 19:25:01 +01:00
committed by GitHub
parent b3a0c44838
commit 9a6f7e213b
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
libs/community/langchain_community/document_loaders/html_bs.py
View File

@@ -1,5 +1,5 @@
import logging import logging
from typing import Dict, List, Union from typing import Dict, Iterator, Union
from langchain_core.documents import Document from langchain_core.documents import Document
@@ -42,7 +42,7 @@ class BSHTMLLoader(BaseLoader):
self.bs_kwargs = bs_kwargs self.bs_kwargs = bs_kwargs
self.get_text_separator = get_text_separator self.get_text_separator = get_text_separator
def load(self) -> List[Document]: def lazy_load(self) -> Iterator[Document]:
"""Load HTML document into document objects.""" """Load HTML document into document objects."""
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
@@ -60,4 +60,4 @@ class BSHTMLLoader(BaseLoader):
"source": self.file_path, "source": self.file_path,
"title": title, "title": title,
} }
return [Document(page_content=text, metadata=metadata)] yield Document(page_content=text, metadata=metadata)