import requests
from lxml import etree
import redis
r = redis.Redis(host="localhost", port=6379, db=0)


def get_page_content(url):
	# 获取指定网页中的标题和链接
    url_lists = []
    headers = {
        "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36"
    }
    response = requests.get(url, headers=headers, verify=False)
    if response.status_code == 200:
        html = etree.HTML(response.content.decode())
	    if html is not None:
	        a_urls = html.xpath("//a")
	        for a in a_urls:
	            title = "".join(a.xpath(".//text()")).strip(）
                a_urls = a.xpath("./@href")
                if len(a_urls) > 0:
                    a_url = a_urls[0]
                    url_lists.append({"url": a_url, "title": title})
        return url_lists
	

# 监控函数
def monitor_website(url, interval=7200):
    while True:
        time.sleep(interval)  # 休眠指定的时间
        new_content = get_page_content(url) 
        changes = []
        if new_content:
            for item in new_content:
                # 检查 URL 是否已经存在
                if r.sismember("myset", item["url"]):
                    print("URL 已经存在，跳过")
                else:
                    # 添加到 Set 中并进行爬取
                    r.sadd("myset", item["url"])
                    changes.append(item)
            if len(changes) > 0:
                print(f"{url}网站已更新,新增数据为{changes}")
                bot(f"{url}网站已更新,新增数据为{changes}")


def bot(text):
    # 构建消息内容
    message_data = {
        "msgtype": "text",
        "text": {
            "content": text,
            "mentioned_list": ["@all"]
        }
    }
    robot_webhook = 'https://qyapi.weixin.qq.com/cgi-bin/webhook/send?key=你的key'
    # 发送请求
    response = requests.post(robot_webhook, headers={"Content-Type": "application/json"}, data=json.dumps(message_data))

    # 检查响应状态码
    if response.status_code == 200:
        print("消息发送成功")
    else:
        print(f"消息发送失败，状态码：{response.status_code}")