18.1 监控重要页面在生成式摘要中的出现率

import requests
import json
import time
from datetime import datetime

# 配置
PERPLEXITY_API_KEY = "your_perplexity_api_key"
MONITORED_PAGES = {
    "https://yourdomain.com/product/ai-assistant": [
        "What is the best AI assistant for developers?",
        "How to use an AI coding tool?",
        "Top AI assistant features in 2024"
    ],
    "https://yourdomain.com/faq": [
        "How to reset your password?",
        "What are the supported languages?",
        "Is there a free trial?"
    ]
}

def query_perplexity(question):
    """向Perplexity API发送查询并返回响应文本"""
    url = "https://api.perplexity.ai/chat/completions"
    headers = {
        "Authorization": f"Bearer {PERPLEXITY_API_KEY}",
        "Content-Type": "application/json"
    }
    payload = {
        "model": "llama-3-sonar-large-32k-online",
        "messages": [
            {"role": "system", "content": "You are a helpful assistant. Provide accurate and concise answers."},
            {"role": "user", "content": question}
        ],
        "max_tokens": 500,
        "temperature": 0.1  # 低温度以获得更一致的输出
    }
    try:
        response = requests.post(url, headers=headers, json=payload, timeout=30)
        response.raise_for_status()
        data = response.json()
        return data['choices'][0]['message']['content']
    except Exception as e:
        print(f"Error querying Perplexity: {e}")
        return ""

def check_mention(url, response_text):
    """检查响应文本中是否包含目标URL"""
    return url in response_text

def run_monitoring_cycle():
    """执行一轮监控"""
    results = []
    for page_url, questions in MONITORED_PAGES.items():
        for question in questions:
            print(f"[{datetime.now()}] Checking: {page_url} with question: '{question}'")
            response = query_perplexity(question)
            is_mentioned = check_mention(page_url, response)
            results.append({
                "timestamp": datetime.now().isoformat(),
                "page_url": page_url,
                "question": question,
                "is_mentioned": is_mentioned,
                "response_snippet": response[:200]  # 保存前200字符用于调试
            })
            # 避免API限流
            time.sleep(2)
    return results

def export_results(results):
    """将结果导出为JSON或发送到监控系统"""
    with open("geo_monitor_results.json", "a") as f:
        for result in results:
            f.write(json.dumps(result) + "\n")
    print(f"Exported {len(results)} results.")

if __name__ == "__main__":
    # 设置定时执行（例如：每4小时执行一次）
    # 实际部署时，应使用cron job或调度器
    results = run_monitoring_cycle()
    export_results(results)