allignment

Author: VinciGit00

pyproject.toml

@@ -36,6 +36,7 @@ dependencies = [
     "langchain-fireworks>=0.1.3",
     "langchain-community>=0.2.9",
     "langchain-huggingface>=0.0.3",
+    "browserbase==0.3.0"
 ]
 
 license = "MIT"

requirements-dev.lock

@@ -54,6 +54,8 @@ boto3==1.34.146
 botocore==1.34.146
     # via boto3
     # via s3transfer
+browserbase==0.3.0
+    # via scrapegraphai
 burr==0.22.1
     # via scrapegraphai
 cachetools==5.4.0
@@ -208,6 +210,7 @@ httptools==0.6.1
     # via uvicorn
 httpx==0.27.0
     # via anthropic
+    # via browserbase
     # via fastapi
     # via fireworks-ai
     # via groq
@@ -383,6 +386,7 @@ pillow==10.4.0
 platformdirs==4.2.2
     # via pylint
 playwright==1.45.0
+    # via browserbase
     # via scrapegraphai
     # via undetected-playwright
 pluggy==1.5.0
@@ -412,6 +416,7 @@ pyasn1-modules==0.4.0
     # via google-auth
 pydantic==2.8.2
     # via anthropic
+    # via browserbase
     # via burr
     # via fastapi
     # via fastapi-pagination

requirements.lock

@@ -37,6 +37,8 @@ boto3==1.34.146
 botocore==1.34.146
     # via boto3
     # via s3transfer
+browserbase==0.3.0
+    # via scrapegraphai
 cachetools==5.4.0
     # via google-auth
 certifi==2024.7.4
@@ -153,6 +155,7 @@ httplib2==0.22.0
     # via google-auth-httplib2
 httpx==0.27.0
     # via anthropic
+    # via browserbase
     # via fireworks-ai
     # via groq
     # via openai
@@ -275,6 +278,7 @@ pillow==10.4.0
     # via langchain-nvidia-ai-endpoints
     # via sentence-transformers
 playwright==1.45.0
+    # via browserbase
     # via scrapegraphai
     # via undetected-playwright
 proto-plus==1.24.0
@@ -299,6 +303,7 @@ pyasn1-modules==0.4.0
     # via google-auth
 pydantic==2.8.2
     # via anthropic
+    # via browserbase
     # via fireworks-ai
     # via google-cloud-aiplatform
     # via google-generativeai

scrapegraphai/docloaders/__init__.py

@@ -1,3 +1,4 @@
 """__init__.py file for docloaders folder"""
 
 from .chromium import ChromiumLoader
+from .broswer_base import browser_base_fetch

scrapegraphai/docloaders/browser_base.py

@@ -0,0 +1,38 @@
+"""
+browserbase integration module 
+"""
+from browserbase import Browserbase
+
+def browser_base_fetch(api_key: str, project_id: str, link: str) -> object:
+    """
+    BrowserBase Fetch
+    This module provides an interface to the BrowserBase API.
+    The `browser_base_fetch` function takes three arguments:
+    - `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.
+    It initializes a Browserbase object with the given API key and project ID, 
+    then uses this object to load the specified link. 
+    It returns the result of the loading operation.
+    Example usage:
+    ```
+    from browser_base_fetch import browser_base_fetch
+    result = browser_base_fetch(api_key="your_api_key", 
+    project_id="your_project_id", link="https://example.com")
+    print(result)
+    ```
+    Please note that you need to replace "your_api_key" and "your_project_id" 
+    with your actual BrowserBase API key and project ID.
+    Args:
+        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.
+    Returns:
+        object: The result of the loading operation.
+    """
+
+    browserbase = Browserbase(api_key=api_key, project_id=project_id)
+
+    result = browserbase.load(link)
+
+    return result