OxyLabs AI Studio Python SDK

这是一个简洁的 Python SDK，用于与 Oxylabs AI Studio API 服务进行无缝交互，包括 AI-Scraper、AI-Crawler、AI-Browser-Agent 以及其他数据提取工具。

环境要求

• python 3.10 及以上版本
• API KEY

安装

pip install oxylabs-ai-studio

使用方法

爬取 (AiCrawler.crawl)

from oxylabs_ai_studio.apps.ai_crawler import AiCrawler

crawler = AiCrawler(api_key="")

url = "https://oxylabs.io"
result = crawler.crawl(
    url=url,
    user_prompt="Find all pages with proxy products pricing",
    output_format="markdown",
    render_javascript=False,
    return_sources_limit=3,
    geo_location="United States",
)
print("Results:")
for item in result.data:
    print(item, "\n")

参数说明:

• url (str): 开始爬取的 URL (必填)
• user_prompt (str): 指导提取的自然语言提示词 (必填)
• output_format (Literal["json", "markdown", "csv", "toon"]): 输出格式 (默认: "markdown")
• schema (dict | None): 用于结构化提取的 JSON Schema (若 output_format 为 "json", "csv" 或 "toon" 时必填)
• render_javascript (bool): 是否渲染 JavaScript (默认: False)
• return_sources_limit (int): 返回的最大源数量 (默认: 25)
• geo_location (str): ISO2 格式的代理位置或国家标准名称。详见 文档
• max_credits (int | None): 可使用的最大积分 (可选)

抓取 (AiScraper.scrape)

from oxylabs_ai_studio.apps.ai_scraper import AiScraper

scraper = AiScraper(api_key="")

schema = scraper.generate_schema(prompt="want to parse developer, platform, type, price game title, genre (array) and description")
print(f"Generated schema: {schema}")

url = "https://sandbox.oxylabs.io/products/3"
result = scraper.scrape(
    url=url,
    output_format="json",
    schema=schema,
    render_javascript=False,
)
print(result)

参数说明:

• url (str): 目标抓取 URL (必填)
• output_format (Literal["json", "markdown", "csv", "screenshot", "toon"]): 输出格式 (默认: "markdown")
• schema (dict | None): 用于结构化提取的 JSON Schema (若 output_format 为 "json", "csv" 或 "toon" 时必填)
• render_javascript (bool | string): 是否渲染 JavaScript。可设置为 "auto"，此时服务会自动检测是否需要渲染 (默认: False)
• geo_location (str): ISO2 格式的代理位置或国家标准名称。详见 文档
• user_agent (str): User-Agent 请求头。详情请参考 https://developers.oxylabs.io/scraping-solutions/web-scraper-api/features/http-context-and-job-management/user-agent-type

浏览器代理 (BrowserAgent.run)

from oxylabs_ai_studio.apps.browser_agent import BrowserAgent

browser_agent = BrowserAgent(api_key="")

schema = browser_agent.generate_schema(
    prompt="game name, platform, review stars and price"
)
print("schema: ", schema)

prompt = "Find if there is game 'super mario odyssey' in the store. If there is, find the price. Use search bar to find the game."
url = "https://sandbox.oxylabs.io/"
result = browser_agent.run(
    url=url,
    user_prompt=prompt,
    output_format="json",
    schema=schema,
)
print(result.data)

参数说明:

• url (str): 开始浏览的 URL (必填)
• user_prompt (str): 用于提取的自然语言提示词 (必填)
• output_format (Literal["json", "markdown", "html", "screenshot", "csv", "toon"]): 输出格式 (默认: "markdown")
• schema (dict | None): 用于结构化提取的 JSON Schema (若 output_format 为 "json", "csv" 或 "toon" 时必填)
• geo_location (str): ISO2 格式的代理位置或国家标准名称。例如 'Germany' (首字母大写)

搜索 (AiSearch.search)

from oxylabs_ai_studio.apps.ai_search import AiSearch


search = AiSearch(api_key="")

query = "lasagna recipe"
result = search.search(
    query=query,
    limit=5,
    render_javascript=False,
    return_content=True,
)
print(result.data)

# 或者使用快速搜索
result = search.instant_search(
    query=query,
    limit=10,
)
print(result.data)