Implementation:CrewAIInc CrewAI Oxylabs Amazon Search Tool

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

Overview

OxylabsAmazonSearchScraperTool scrapes Amazon search results by keyword using the Oxylabs web scraper API.

Description

The module follows the standard Oxylabs tool family pattern with three classes: OxylabsAmazonSearchScraperArgs (a Pydantic input schema accepting an Amazon search term string), OxylabsAmazonSearchScraperConfig (a configuration model with options including domain, start_page, pages, geo_location, user_agent_type, render, callback_url, context, parse, and parsing_instructions), and OxylabsAmazonSearchScraperTool (the main tool extending BaseTool). Initialization resolves credentials from constructor parameters or OXYLABS_USERNAME/OXYLABS_PASSWORD environment variables, creates an Oxylabs RealtimeClient with version metadata, and handles missing package installation interactively. The _run method calls self.oxylabs_api.amazon.scrape_search(query, **config) and returns the first result's content as a string or JSON-serialized dict. The pagination support via start_page and pages configuration makes it suitable for large-scale market research tasks.

Usage

Use this tool when a CrewAI agent needs to search Amazon's catalog and retrieve search result listings for product discovery, market research, or competitive analysis workflows.

Code Reference

Source Location

• Repository: CrewAI
• File: lib/crewai-tools/src/crewai_tools/tools/oxylabs_amazon_search_scraper_tool/oxylabs_amazon_search_scraper_tool.py
• Lines: 1-169

Signature

class OxylabsAmazonSearchScraperArgs(BaseModel):
    query: str = Field(description="Amazon search term")

class OxylabsAmazonSearchScraperConfig(BaseModel):
    domain: str | None = None
    start_page: int | None = None
    pages: 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 OxylabsAmazonSearchScraperTool(BaseTool):
    name: str = "Oxylabs Amazon Search Scraper tool"
    description: str = "Scrape Amazon search results with Oxylabs Amazon Search Scraper"
    args_schema: type[BaseModel] = OxylabsAmazonSearchScraperArgs
    oxylabs_api: RealtimeClient
    config: OxylabsAmazonSearchScraperConfig

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

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

Import

from crewai_tools import OxylabsAmazonSearchScraperTool

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	OxylabsAmazonSearchScraperConfig or dict or None	No	Configuration options including pagination; defaults to empty config
query	str	Yes	Amazon search term to scrape results for

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 OxylabsAmazonSearchScraperTool

tool = OxylabsAmazonSearchScraperTool(
    username="your_username",
    password="your_password",
)
result = tool._run(query="wireless headphones")

With Pagination

from crewai_tools import OxylabsAmazonSearchScraperTool
from crewai_tools.tools.oxylabs_amazon_search_scraper_tool.oxylabs_amazon_search_scraper_tool import (
    OxylabsAmazonSearchScraperConfig,
)

config = OxylabsAmazonSearchScraperConfig(
    domain="com",
    start_page=1,
    pages=3,
    parse=True,
)
tool = OxylabsAmazonSearchScraperTool(config=config)
result = tool._run(query="bluetooth speakers")

Related Pages

• Principle:CrewAIInc_CrewAI_Built_In_Tool_Selection