added bs4 import in the split_file_function and removed it from top l…

…evel. The class can be imported without bs4 depedency and once the split function is called, the bs4 will be imported. This makes bs4 optional depedency.

libs/text-splitters/langchain_text_splitters/html.py

@@ -19,10 +19,8 @@
 )
 
 import requests
-from bs4 import BeautifulSoup
-from langchain.docstore.document import Document as DocstoreDocument
 from langchain_core._api import beta
-from langchain_core.documents import BaseDocumentTransformer, Document as CoreDocument
+from langchain_core.documents import BaseDocumentTransformer, Document
 
 from langchain_text_splitters.character import RecursiveCharacterTextSplitter
 
@@ -297,6 +295,14 @@ def split_text_from_file(self, file: Any) -> List[Document]:
         Returns:
             A list of split Document objects.
         """
+        try:
+            from bs4 import BeautifulSoup  # type: ignore[import-untyped]
+        except ImportError as e:
+            raise ImportError(
+                "Unable to import BeautifulSoup/PageElement, \
+                    please install with `pip install \
+                    bs4`."
+            ) from e
         if isinstance(file, str):
             with open(file, 'r', encoding='utf-8') as f:
                 html_content = f.read()