Implementation:CrewAIInc CrewAI Oxylabs Google Search Tool

Knowledge Sources	CrewAI
Domains	Tools, Web_Scraping, Search
Last Updated	2026-02-11 00:00 GMT

Overview

OxylabsGoogleSearchScraperTool scrapes Google search results using the Oxylabs web scraper API.

Description

The module follows the standard Oxylabs tool family pattern with three classes: OxylabsGoogleSearchScraperArgs (a Pydantic input schema accepting a search query string), OxylabsGoogleSearchScraperConfig (a configuration model with options including domain, start_page, pages, limit, geo_location, user_agent_type, render, callback_url, context, parse, and parsing_instructions -- notably including a limit field for controlling the number of results per page that is unique to this Google variant), and OxylabsGoogleSearchScraperTool (the main tool extending BaseTool). Initialization handles credential resolution from constructor parameters or OXYLABS_USERNAME/OXYLABS_PASSWORD environment variables and creates an Oxylabs RealtimeClient with the standard version metadata SDK type string. The _run method calls self.oxylabs_api.google.scrape_search(query, **config) and returns the first result's content as a string or JSON-serialized dict. Geo-targeting and device emulation capabilities enable location-specific and device-specific search result retrieval.

Usage

Use this tool when a CrewAI agent needs to perform Google searches programmatically for web research, competitor analysis, SEO monitoring, or general information gathering tasks.

Code Reference

Source Location

• Repository: CrewAI
• File: lib/crewai-tools/src/crewai_tools/tools/oxylabs_google_search_scraper_tool/oxylabs_google_search_scraper_tool.py
• Lines: 1-172

Signature

class OxylabsGoogleSearchScraperArgs(BaseModel):
    query: str = Field(description="Search query")

class OxylabsGoogleSearchScraperConfig(BaseModel):
    domain: str | None = None
    start_page: int | None = None
    pages: int | None = None
    limit: int | None = None
    geo_location: str | None = None
    user_agent_type: str | None = None
    render: str | None = None
    callback_url: str | None = None
    context: list | None = None
    parse: bool | None = None
    parsing_instructions: dict | None = None

class OxylabsGoogleSearchScraperTool(BaseTool):
    name: str = "Oxylabs Google Search Scraper tool"
    description: str = "Scrape Google Search results with Oxylabs Google Search Scraper"
    args_schema: type[BaseModel] = OxylabsGoogleSearchScraperArgs
    oxylabs_api: RealtimeClient
    config: OxylabsGoogleSearchScraperConfig

    def __init__(
        self,
        username: str | None = None,
        password: str | None = None,
        config: OxylabsGoogleSearchScraperConfig | dict | None = None,
        **kwargs,
    ): ...

    def _run(self, query: str, **kwargs) -> str: ...

Import

from crewai_tools import OxylabsGoogleSearchScraperTool

I/O Contract

Inputs

Name	Type	Required	Description
username	str or None	No	Oxylabs username; falls back to OXYLABS_USERNAME environment variable
password	str or None	No	Oxylabs password; falls back to OXYLABS_PASSWORD environment variable
config	OxylabsGoogleSearchScraperConfig or dict or None	No	Configuration options including pagination and result limits; defaults to empty config
query	str	Yes	Google search query to execute

Outputs

Name	Type	Description
_run() returns	str	Search results content as string or JSON-serialized dict if structured parsing is enabled

Usage Examples

Basic Usage

from crewai_tools import OxylabsGoogleSearchScraperTool

tool = OxylabsGoogleSearchScraperTool(
    username="your_username",
    password="your_password",
)
result = tool._run(query="CrewAI multi-agent framework")

With Geo-targeting and Pagination

from crewai_tools import OxylabsGoogleSearchScraperTool
from crewai_tools.tools.oxylabs_google_search_scraper_tool.oxylabs_google_search_scraper_tool import (
    OxylabsGoogleSearchScraperConfig,
)

config = OxylabsGoogleSearchScraperConfig(
    domain="co.uk",
    geo_location="United Kingdom",
    start_page=1,
    pages=2,
    limit=10,
    parse=True,
)
tool = OxylabsGoogleSearchScraperTool(config=config)
result = tool._run(query="best AI frameworks 2025")

Related Pages

• Principle:CrewAIInc_CrewAI_Built_In_Tool_Selection