langchain-alterlab

LangChain integration for the AlterLab web scraping API.

Installation

pip install langchain-alterlab

Setup

Set your AlterLab API key:

export ALTERLAB_API_KEY="your-api-key"

Get your API key at alterlab.io/dashboard.

Document Loader

Load web pages as LangChain Document objects with structured metadata:

from langchain_alterlab import AlterLabLoader

# Single URL
loader = AlterLabLoader(url="https://example.com/article")
docs = loader.load()

print(docs[0].page_content[:200])
print(docs[0].metadata)
# {'source': 'https://example.com/article', 'title': '...', 'author': '...', ...}

Multiple URLs

loader = AlterLabLoader(
    urls=[
        "https://example.com/page1",
        "https://example.com/page2",
    ],
)
docs = loader.load()

Custom Parameters

loader = AlterLabLoader(
    url="https://example.com",
    params={
        "formats": ["markdown", "json"],
        "mode": "js",  # JavaScript rendering
        "extraction_profile": "article",
    },
)

Async Loading

docs = await loader.aload()

Agent Tool

Use AlterLabScrapeTool with LangChain agents to scrape pages on demand:

from langchain_alterlab import AlterLabScrapeTool

tool = AlterLabScrapeTool()

# Direct use
result = tool.invoke("https://example.com")
print(result)

With an Agent

from langchain_openai import ChatOpenAI
from langchain_alterlab import AlterLabScrapeTool

llm = ChatOpenAI()
tools = [AlterLabScrapeTool()]
agent = llm.bind_tools(tools)

With Metadata

tool = AlterLabScrapeTool(include_metadata=True)
result = tool.invoke("https://example.com")
# Output includes title, author, source before content

Metadata Fields

Documents and tool results include structured metadata:

API Reference

See docs.alterlab.io for the full AlterLab API documentation.

Search Tool

Use AlterLabSearchTool to let agents run web searches (numbered title, URL and snippet):

from langchain_alterlab import AlterLabSearchTool

tool = AlterLabSearchTool(num_results=5, params={"engine": "google"})
print(tool.invoke("web scraping api"))