招标公告数据提取自动化：代理代码指南

pip install "capsolver-core[playwright] @ git+https://github.com/capsolver-ai/capsolver-core.git"
pip install git+https://github.com/capsolver-ai/capsolver-agent.git
pip install "capsolver-mcp[browser] @ git+https://github.com/capsolver-ai/capsolver-mcp.git"
playwright install chromium
export CAPSOLVER_API_KEY="your-capsolver-api-key"

states = [
    "discover_notice_list",
    "open_notice_detail",
    "challenge_detected",
    "resume_after_solution",
    "extract_public_fields",
    "review_or_stop",
]

required_fields = ["notice_id", "buyer", "deadline", "source_url"]

import asyncio
from capsolver_core import create_capsolver
from playwright.async_api import async_playwright

TARGET_URL = "https://example.gov/tenders/search"

async def run_agent_step():
    async with async_playwright() as pw:
        browser = await pw.chromium.launch()
        page = await browser.new_page()
        await page.goto(TARGET_URL, wait_until="domcontentloaded")

        async with create_capsolver(api_key="YOUR_CAPSOLVER_KEY") as cap:
            captcha_types = await cap.detect(page)
            if not captcha_types:
                return "continue_without_challenge"

            results = await cap.solve_on_page(page)
            solved = [r for r in results if r.solution and not r.error]
            if not solved:
                return "stop_for_review"

        return "resume_original_authorized_task"

asyncio.run(run_agent_step())

import json
from openai import OpenAI
from capsolver_agent.schema import create_executor, get_all_tools

client = OpenAI()
executor = create_executor(api_key="YOUR_CAPSOLVER_KEY", default_timeout=120)
tools = [tool.to_openai_function() for tool in get_all_tools()]

messages = [{
    "role": "user",
    "content": "继续批准的浏览器任务。如果出现CAPTCHA，请调用CapSolver工具一次并报告结果。"
}]

async def run_one_turn():
    response = client.chat.completions.create(
        model="gpt-4o",
        messages=messages,
        tools=tools,
    )

    for call in response.choices[0].message.tool_calls or []:
        args = json.loads(call.function.arguments)
        result = await executor.execute(call.function.name, args)
        messages.append({
            "role": "tool",
            "tool_call_id": call.id,
            "content": json.dumps(result),
        })