+
+ 
+
diff --git a/docs/assets/browserbase_logo.png b/docs/assets/browserbase_logo.png
new file mode 100644
index 00000000..bd16f2e1
Binary files /dev/null and b/docs/assets/browserbase_logo.png differ
diff --git a/docs/source/introduction/overview.rst b/docs/source/introduction/overview.rst
index 00a76d5d..506770a5 100644
--- a/docs/source/introduction/overview.rst
+++ b/docs/source/introduction/overview.rst
@@ -82,6 +82,11 @@ FAQ
Sponsors
========
+.. image:: ../../assets/browserbase_logo.png
+ :width: 10%
+ :alt: Browserbase
+ :target: https://www.browserbase.com/
+
.. image:: ../../assets/serp_api_logo.png
:width: 10%
:alt: Serp API
diff --git a/scrapegraphai/docloaders/browser_base.py b/scrapegraphai/docloaders/browser_base.py
index 318c9f38..c9413d68 100644
--- a/scrapegraphai/docloaders/browser_base.py
+++ b/scrapegraphai/docloaders/browser_base.py
@@ -3,7 +3,7 @@
"""
from typing import List
-def browser_base_fetch(api_key: str, project_id: str, link: List[str]) -> List[str]:
+def browser_base_fetch(api_key: str, project_id: str, link: List[str], text_content: bool = True, async_mode: bool = False) -> List[str]:
"""
BrowserBase Fetch
@@ -13,6 +13,8 @@ def browser_base_fetch(api_key: str, project_id: str, link: List[str]) -> List[s
- `api_key`: The API key provided by BrowserBase.
- `project_id`: The ID of the project on BrowserBase where you want to fetch data from.
- `link`: The URL or link that you want to fetch data from.
+ - `text_content`: A boolean flag to specify whether to return only the text content (True) or the full HTML (False).
+ - `async_mode`: A boolean flag that determines whether the function runs asynchronously (True) or synchronously (False, default).
It initializes a Browserbase object with the given API key and project ID,
then uses this object to load the specified link.
@@ -35,6 +37,8 @@ def browser_base_fetch(api_key: str, project_id: str, link: List[str]) -> List[s
api_key (str): The API key provided by BrowserBase.
project_id (str): The ID of the project on BrowserBase where you want to fetch data from.
link (str): The URL or link that you want to fetch data from.
+ text_content (bool): Whether to return only the text content (True) or the full HTML (False). Defaults to True.
+ async_mode (bool): Whether to run the function asynchronously (True) or synchronously (False). Defaults to False.
Returns:
object: The result of the loading operation.
@@ -49,7 +53,19 @@ def browser_base_fetch(api_key: str, project_id: str, link: List[str]) -> List[s
browserbase = Browserbase(api_key=api_key, project_id=project_id)
result = []
- for l in link:
- result.append(browserbase.load(l, text_content=True))
+ async def _async_fetch_link(l):
+ return await asyncio.to_thread(browserbase.load, l, text_content=text_content)
+
+ if async_mode:
+ async def _async_browser_base_fetch():
+ for l in link:
+ result.append(await _async_fetch_link(l))
+ return result
+
+ result = asyncio.run(_async_browser_base_fetch())
+ else:
+ for l in link:
+ result.append(browserbase.load(l, text_content=text_content))
+
return result