community[minor]: added Browserbase loader (#20478)

libs/community/langchain_community/document_loaders/__init__.py

@@ -95,6 +95,9 @@ if TYPE_CHECKING:
     from langchain_community.document_loaders.brave_search import (
         BraveSearchLoader,  # noqa: F401
     )
+    from langchain_community.document_loaders.browserbase import (
+        BrowserbaseLoader,  # noqa: F401
+    )
     from langchain_community.document_loaders.browserless import (
         BrowserlessLoader,  # noqa: F401
     )
@@ -541,6 +544,7 @@ __all__ = [
     "BlobLoader",
     "BlockchainDocumentLoader",
     "BraveSearchLoader",
+    "BrowserbaseLoader",
     "BrowserlessLoader",
     "CSVLoader",
     "CassandraLoader",
@@ -727,6 +731,7 @@ _module_lookup = {
     "BlobLoader": "langchain_community.document_loaders.blob_loaders",
     "BlockchainDocumentLoader": "langchain_community.document_loaders.blockchain",
     "BraveSearchLoader": "langchain_community.document_loaders.brave_search",
+    "BrowserbaseLoader": "langchain_community.document_loaders.browserbase",
     "BrowserlessLoader": "langchain_community.document_loaders.browserless",
     "CSVLoader": "langchain_community.document_loaders.csv_loader",
     "CassandraLoader": "langchain_community.document_loaders.cassandra",

libs/community/langchain_community/document_loaders/browserbase.py

@@ -0,0 +1,47 @@
+from typing import Iterator, List, Optional, Tuple, Union
+
+from langchain_core.documents import Document
+
+from langchain_community.document_loaders.base import BaseLoader
+
+
+class BrowserbaseLoader(BaseLoader):
+    """Load pre-rendered web pages using a headless browser hosted on Browserbase.
+
+    Depends on `browserbase` package.
+    Get your API key from https://browserbase.com
+    """
+
+    def __init__(
+        self,
+        urls: Union[List[str], Tuple[str, ...]],
+        *,
+        api_key: Optional[str] = None,
+        text_content: bool = False,
+    ):
+        self.urls = urls
+        self.text_content = text_content
+
+        try:
+            from browserbase import Browserbase
+        except ImportError:
+            raise ImportError(
+                "You must run "
+                "`pip install --upgrade "
+                "browserbase` "
+                "to use the Browserbase loader."
+            )
+
+        self.browserbase = Browserbase(api_key=api_key)
+
+    def lazy_load(self) -> Iterator[Document]:
+        """Load pages from URLs"""
+        pages = self.browserbase.load_urls(self.urls, self.text_content)
+
+        for i, page in enumerate(pages):
+            yield Document(
+                page_content=page,
+                metadata={
+                    "url": self.urls[i],
+                },
+            )

libs/community/tests/unit_tests/document_loaders/test_imports.py

@@ -38,6 +38,7 @@ EXPECTED_ALL = [
     "BlobLoader",
     "BlockchainDocumentLoader",
     "BraveSearchLoader",
+    "BrowserbaseLoader",
     "BrowserlessLoader",
     "CassandraLoader",
     "CSVLoader",