Files
ZDXX/1.1/test1.py

315 lines
11 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

import os
import json
import threading
import requests
import logging
from datetime import datetime
from flask import Flask, jsonify
from flask_sqlalchemy import SQLAlchemy
from flask_cors import CORS
from flask_apscheduler import APScheduler
from lxml import etree
# --- 配置日志 ---
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
app = Flask(__name__)
CORS(app)
# --- 数据库配置 ---
app.config['SQLALCHEMY_DATABASE_URI'] = 'sqlite:///monitor_data.db'
app.config['SQLALCHEMY_TRACK_MODIFICATIONS'] = False
app.config['SCHEDULER_API_ENABLED'] = True # 允许通过API查看调度任务
db = SQLAlchemy(app)
scheduler = APScheduler()
# --- 模型定义 ---
class MonitorRecord(db.Model):
id = db.Column(db.Integer, primary_key=True)
source = db.Column(db.String(50))
name = db.Column(db.String(100))
status = db.Column(db.String(50)) # 正常 / 离线 / 异常
reason = db.Column(db.String(255))
offset = db.Column(db.String(50))
latest_time = db.Column(db.String(50)) # 数据时间
check_time = db.Column(db.String(50)) # 爬取时间
content = db.Column(db.Text, nullable=True)
with app.app_context():
db.create_all()
# --- 爬虫配置 ---
CONFIG = {
"106": {
"base_url": "http://106.75.72.40:7500/api/proxy/tcp",
"primary_auth": "Basic YWRtaW46bGljYWhr",
"login_payload": {"username": "admin", "password": "licahk", "recaptcha": ""}
},
"82": {
"base_url": "http://82.156.1.111/weather/php",
"login": {'username': 'renlixin', 'password': 'licahk', 'login': '123'}
}
}
is_running = False
# --- 核心辅助函数 ---
def calculate_offset(latest_time_str):
if not latest_time_str or latest_time_str == "N/A":
return "从未同步"
try:
clean_date_str = str(latest_time_str).split()[0].replace('_', '-')
target_date = datetime.strptime(clean_date_str, "%Y-%m-%d").date()
diff = (datetime.now().date() - target_date).days
if diff == 0: return "当天已同步"
return f"滞后 {diff}"
except:
return "时间解析失败"
def save_record(source, name, status, reason, latest_time="N/A", content=None):
"""
Upsert 逻辑: 有则更新,无则插入
"""
record = MonitorRecord.query.filter_by(source=source, name=name).first()
now_str = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
current_offset = calculate_offset(latest_time)
if record:
if content is not None: record.content = content
if latest_time != "N/A": record.latest_time = latest_time
record.status = status
record.reason = reason
record.check_time = now_str
# 使用当前库里的时间重新计算 offset
time_base = latest_time if latest_time != "N/A" else record.latest_time
record.offset = calculate_offset(time_base)
else:
new_record = MonitorRecord(
source=source, name=name, status=status, reason=reason,
offset=current_offset, latest_time=latest_time,
check_time=now_str, content=content
)
db.session.add(new_record)
try:
db.session.commit()
except Exception as e:
db.session.rollback()
logging.error(f"DB Error: {e}")
return f"{source}_{name}"
# --- 106 逻辑 ---
def get_106_dynamic_token(port):
try:
login_url = f"http://106.75.72.40:{port}/api/login"
resp = requests.post(login_url, json=CONFIG["106"]["login_payload"], timeout=10)
return resp.text.strip().replace('"', '') if resp.status_code == 200 else None
except:
return None
def find_closest_item(items, is_date_level=True):
if not items or not isinstance(items, list): return None
today = datetime.now()
scored_items = []
for item in items:
name_val = item.get('name', '')
path_val = item.get('path', '')
target_str = name_val if name_val else path_val.split('/')[-1]
try:
if is_date_level:
current_date = datetime.strptime(target_str, "%Y_%m_%d")
else:
mod_str = item.get('modified', '')
current_date = datetime.fromisoformat(mod_str.replace('Z', '+00:00'))
diff = abs((today - current_date.replace(tzinfo=None)).total_seconds())
scored_items.append((diff, item, target_str))
except:
continue
if not scored_items: return None
scored_items.sort(key=lambda x: x[0])
return scored_items[0]
def run_106_logic(active_set):
c = CONFIG["106"]
today_str = datetime.now().strftime("%Y_%m_%d")
main_headers = {"Authorization": c["primary_auth"], "User-Agent": "Mozilla/5.0"}
try:
resp = requests.get(c["base_url"], headers=main_headers, timeout=20)
proxies = resp.json().get('proxies', [])
for item in proxies:
name = item.get('name', '')
if not name.lower().endswith('_data'): continue
if "TOWER" not in name.upper(): continue
if str(item.get('status')).lower() != 'online':
key = save_record("106网站", name, "离线", f"设备状态: {item.get('status')}")
active_set.add(key)
continue
try:
port = item.get('conf', {}).get('remote_port')
token = get_106_dynamic_token(port)
if not token:
key = save_record("106网站", name, "异常", "Token获取失败")
active_set.add(key)
continue
headers = {"Authorization": c["primary_auth"], "x-auth": token}
api_root = "/api/resources/Data/" if "TOWER_" in name.upper() else "/api/resources/data/"
# 寻找日期
res1 = requests.get(f"http://106.75.72.40:{port}{api_root}", headers=headers, timeout=10)
best_date = find_closest_item(res1.json().get('items', []), True)
if not best_date or best_date[2] != today_str:
key = save_record("106网站", name, "正常", "未找到今日文件夹",
latest_time=best_date[2] if best_date else "N/A")
active_set.add(key)
continue
# 寻找文件
date_path = f"{api_root}{best_date[2]}/"
res2 = requests.get(f"http://106.75.72.40:{port}{date_path}", headers=headers, timeout=10)
best_file = find_closest_item(res2.json().get('items', []), False)
if not best_file:
key = save_record("106网站", name, "正常", "今日文件夹为空", latest_time=today_str)
active_set.add(key)
continue
# 获取内容
file_item = best_file[1]
full_path = file_item.get('path') or f"{date_path}{file_item.get('name')}"
# 判断下载方式
is_tower_i = "TOWER" in name.upper() and "TOWER_" not in name.upper()
if is_tower_i:
download_url = f"http://106.75.72.40:{port}/api/raw{full_path}"
res3 = requests.get(download_url, headers=headers, timeout=20)
final_content = f"Binary Data Size: {len(res3.content)}"
else:
file_api_url = f"http://106.75.72.40:{port}/api/resources{full_path}"
res3 = requests.get(file_api_url, headers=headers, timeout=20)
final_content = res3.json().get('content', '')
key = save_record("106网站", name, "正常", "同步成功", latest_time=today_str, content=final_content)
active_set.add(key)
except Exception as e:
key = save_record("106网站", name, "异常", f"采集错误: {str(e)[:50]}")
active_set.add(key)
except Exception as e:
logging.error(f"106 Global Error: {e}")
# --- 82 逻辑 ---
def run_82_logic(active_set):
c = CONFIG["82"]
session = requests.Session()
try:
session.post(f"{c['base_url']}/login.php", data=c["login"], timeout=10)
resp = session.post(f"{c['base_url']}/GetStationList.php", timeout=10)
stations = etree.HTML(resp.content).xpath('//option/@value')
for sid in [s for s in stations if s]:
try:
r = session.post(f"{c['base_url']}/getLastWeatherData.php", data=str(sid),
headers={'Content-Type': 'text/plain'}, timeout=10)
data = r.json()
if data:
d_list = data.get('date', [])
latest = str(d_list[-1]) if d_list else "N/A"
key = save_record("82网站", sid, "正常", "同步成功", latest_time=latest,
content=json.dumps(data, ensure_ascii=False))
active_set.add(key)
else:
key = save_record("82网站", sid, "异常", "返回空数据")
active_set.add(key)
except:
key = save_record("82网站", sid, "异常", "单个采集失败")
active_set.add(key)
except Exception as e:
logging.error(f"82 Global Error: {e}")
# --- 核心任务逻辑 ---
def execute_monitor_task():
global is_running
if is_running:
logging.warning("Task already running, skipping...")
return
is_running = True
logging.info("Starting monitor task...")
with app.app_context():
active_set = set()
run_106_logic(active_set)
run_82_logic(active_set)
# 掉线处理
all_records = MonitorRecord.query.all()
now_str = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
for record in all_records:
if f"{record.source}_{record.name}" not in active_set:
record.status = "已离线"
record.reason = "设备本次未出现"
record.check_time = now_str
record.offset = calculate_offset(record.latest_time)
try:
db.session.commit()
except:
db.session.rollback()
is_running = False
logging.info("Monitor task finished.")
# --- 路由 ---
@app.route('/api/run', methods=['POST'])
def manual_start():
if is_running: return jsonify({"status": "busy"}), 400
threading.Thread(target=execute_monitor_task).start()
return jsonify({"status": "started"})
@app.route('/api/status')
def status(): return jsonify({"is_running": is_running})
@app.route('/api/logs')
def logs():
data = MonitorRecord.query.all()
return jsonify([{
"source": l.source, "name": l.name, "status": l.status,
"reason": l.reason, "offset": l.offset, "latest_time": l.latest_time,
"check_time": l.check_time, "content": l.content
} for l in data])
# --- 调度器配置 ---
# id: 任务ID, func: 任务函数(字符串路径或引用), trigger: cron(定时), hour/minute: 时间
@scheduler.task('cron', id='daily_job', hour=10, minute=0)
def auto_run_task():
with app.app_context():
logging.info("Auto scheduler triggered.")
# 在新线程中运行,避免阻塞调度器主线程
threading.Thread(target=execute_monitor_task).start()
if __name__ == "__main__":
scheduler.init_app(app)
scheduler.start()
# 注意debug=True 可能会导致调度器在开发模式下运行两次,生产环境建议关闭 debug
app.run(debug=True, port=5000, use_reloader=False)