refactor: Implement structured data collection and configuration modules, replacing legacy city-specific files and updating documentation.

This commit is contained in:
2569718930@qq.com
2026-02-08 20:30:17 +08:00
parent c97265c4e5
commit 694b2f87c4
6 changed files with 50 additions and 111 deletions
+2 -1
View File
@@ -8,6 +8,7 @@ An intelligent weather information bot designed to provide ultra-fast, live mete
- **Python 3.11+** - **Python 3.11+**
- Dependencies: `pip install -r requirements.txt` - Dependencies: `pip install -r requirements.txt`
- **Environment**: Configure `METEOBLUE_API_KEY` in `.env` to enable high-precision London forecasts.
### Running Locally (Windows/Linux) ### Running Locally (Windows/Linux)
@@ -82,7 +83,7 @@ graph TD
subgraph "Data Engine" subgraph "Data Engine"
Collector --> OM[Open-Meteo API] Collector --> OM[Open-Meteo API]
Collector --> MB[Meteoblue Scraper] Collector --> MB[Meteoblue Weather API]
Collector --> NOAA[METAR Data Center] Collector --> NOAA[METAR Data Center]
Collector --> MGM[Turkish MGM API] Collector --> MGM[Turkish MGM API]
Collector --> NWS[US NWS API] Collector --> NWS[US NWS API]
+2 -1
View File
@@ -8,6 +8,7 @@
- **Python 3.11+** - **Python 3.11+**
- 依赖安装: `pip install -r requirements.txt` - 依赖安装: `pip install -r requirements.txt`
- **环境变量**: 需在 `.env` 中配置 `METEOBLUE_API_KEY` 以激活伦敦高精度预报。
### 本地运行 (Windows/Linux) ### 本地运行 (Windows/Linux)
@@ -88,7 +89,7 @@ graph TD
subgraph "Data Engine" subgraph "Data Engine"
Collector --> OM[Open-Meteo API] Collector --> OM[Open-Meteo API]
Collector --> MB[Meteoblue Scraper] Collector --> MB[Meteoblue Weather API]
Collector --> NOAA[METAR Data Center] Collector --> NOAA[METAR Data Center]
Collector --> MGM[Turkish MGM API] Collector --> MGM[Turkish MGM API]
Collector --> NWS[US NWS API] Collector --> NWS[US NWS API]
-17
View File
@@ -1,17 +0,0 @@
import requests
def save_nyc_mb():
url = "https://www.meteoblue.com/en/weather/week/40.713N74.006W"
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
}
proxies = {"http": "http://127.0.0.1:7890", "https": "http://127.0.0.1:7890"}
try:
resp = requests.get(url, headers=headers, proxies=proxies, timeout=10)
with open("nyc_mb.html", "w", encoding="utf-8") as f:
f.write(resp.text)
print("Saved nyc_mb.html")
except Exception as e:
print(f"Error: {e}")
save_nyc_mb()
+44 -52
View File
@@ -37,7 +37,9 @@ class WeatherDataCollector:
def __init__(self, config: dict): def __init__(self, config: dict):
self.config = config self.config = config
self.wunderground_key = config.get("wunderground_api_key") weather_cfg = config.get("weather", {})
self.wunderground_key = weather_cfg.get("wunderground_api_key")
self.meteoblue_key = weather_cfg.get("meteoblue_api_key")
self.timeout = 30 # 增加超时以支持高延迟 VPS self.timeout = 30 # 增加超时以支持高延迟 VPS
self.session = requests.Session() self.session = requests.Session()
@@ -532,75 +534,65 @@ class WeatherDataCollector:
use_fahrenheit: bool = False, use_fahrenheit: bool = False,
) -> Optional[Dict]: ) -> Optional[Dict]:
""" """
Meteoblue 网页抓取多模型预测数据的“共识”最高温 通过 Meteoblue 官方 API 获取高精度预测数据
""" """
if not self.meteoblue_key:
logger.warning("Meteoblue API Key 未配置,跳过抓取。")
return None
try: try:
# 1. 构造精确的方向后缀 URL # 1. 调用官方 API (使用 basic-day 包,它是多模型 ML 融合结果)
lat_dir = "N" if lat >= 0 else "S" # 格式: https://my.meteoblue.com/packages/basic-day?apikey=KEY&lat=LAT&lon=LON&format=json
lon_dir = "E" if lon >= 0 else "W" url = "https://my.meteoblue.com/packages/basic-day"
# Meteoblue 坐标 URL 习惯:保留 3 位小数,使用大写方向后缀 params = {
coord_str = f"{abs(lat):.3f}{lat_dir}{abs(lon):.3f}{lon_dir}" "apikey": self.meteoblue_key,
tz_slug = timezone_name.replace("/", "%2F") "lat": lat,
"lon": lon,
# 使用 forecast/week 路径通常比直接 week 更稳定 "format": "json",
url = f"https://www.meteoblue.com/en/weather/week/{coord_str}" "as_daylight": "true"
if tz_slug:
url += f"_{tz_slug}"
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
"Accept-Language": "en-US,en;q=0.9",
"Referer": "https://www.meteoblue.com/"
} }
response = self.session.get( response = self.session.get(
url, url,
headers=headers, params=params,
timeout=self.timeout, timeout=self.timeout
allow_redirects=True # 允许重定向,但我们要检查终点
) )
response.raise_for_status() response.raise_for_status()
data = response.json()
content = response.text day_data = data.get("data_day", {})
max_temps = day_data.get("temperature_max", [])
# 2. 检查是否重定向到了错误的地方 (例如大阪 Osaka) if not max_temps:
# 如果 URL 里有 W 但页面内容里全是 E 或者城市名完全对不上 logger.warning(f"Meteoblue API 返回数据中找不到最高温 (坐标: {lat},{lon})")
if lon < 0 and "W" in coord_str: return None
if "osaka" in response.url.lower():
logger.warning(f"⚠️ Meteoblue 重定向异常: 目标 {coord_str} 却返回了 {response.url}")
return None
# 3. 提取最高温
match = re.search(r'Today.*?tab-temp-max.*?(\d+)&nbsp;°C', content, re.DOTALL | re.IGNORECASE)
result = {
"source": "meteoblue",
"url": response.url,
"today_high": None,
"daily_highs": [],
"unit": "celsius"
}
# 2. 转换单位
def c_to_f(c): def c_to_f(c):
return round((c * 9/5) + 32, 1) return round((c * 9/5) + 32, 1)
if match: result = {
val = float(match.group(1)) "source": "meteoblue",
result["today_high"] = c_to_f(val) if use_fahrenheit else val "today_high": None,
"daily_highs": [],
"unit": "fahrenheit" if use_fahrenheit else "celsius",
"url": f"https://www.meteoblue.com/en/weather/week/{lat}N{lon}E" # 仅供参考
}
# 同时提取接下来几天 # 提取今日最高
all_highs = re.findall(r'tab-temp-max.*?(\d+)&nbsp;°C', content, re.DOTALL) mb_today_c = max_temps[0]
if all_highs: result["today_high"] = c_to_f(mb_today_c) if use_fahrenheit else mb_today_c
if use_fahrenheit:
result["daily_highs"] = [c_to_f(float(h)) for h in all_highs]
else:
result["daily_highs"] = [float(h) for h in all_highs]
result["unit"] = "fahrenheit" if use_fahrenheit else "celsius" # 提取接下来几天的最高温
logger.info(f"✅ Meteoblue 抓取成功 ({coord_str}): 今天 {result['today_high']}{result['unit']}") if use_fahrenheit:
result["daily_highs"] = [c_to_f(t) for t in max_temps]
else:
result["daily_highs"] = max_temps
logger.info(f"✅ Meteoblue API 获取成功 ({lat},{lon}): 今天 {result['today_high']}{result['unit']}")
return result return result
except Exception as e: except Exception as e:
logger.error(f"Meteoblue fetch failed: {e}") logger.error(f"Meteoblue API fetch failed: {e}")
return None return None
def extract_date_from_title(self, title: str) -> Optional[str]: def extract_date_from_title(self, title: str) -> Optional[str]:
+1
View File
@@ -25,6 +25,7 @@ def load_config():
"openweather_api_key": get_env_or_none("OPENWEATHER_API_KEY"), "openweather_api_key": get_env_or_none("OPENWEATHER_API_KEY"),
"wunderground_api_key": get_env_or_none("WUNDERGROUND_API_KEY"), "wunderground_api_key": get_env_or_none("WUNDERGROUND_API_KEY"),
"visualcrossing_api_key": get_env_or_none("VISUALCROSSING_API_KEY"), "visualcrossing_api_key": get_env_or_none("VISUALCROSSING_API_KEY"),
"meteoblue_api_key": get_env_or_none("METEOBLUE_API_KEY"),
"proxy": os.getenv("HTTPS_PROXY") or os.getenv("HTTP_PROXY"), "proxy": os.getenv("HTTPS_PROXY") or os.getenv("HTTP_PROXY"),
}, },
"telegram": { "telegram": {
-39
View File
@@ -1,39 +0,0 @@
import requests
import re
from datetime import datetime
def test_mb_nyc():
lat = 40.7128
lon = -74.0060
timezone_name = "America/New_York"
lat_dir = "N" if lat >= 0 else "S"
lon_dir = "E" if lon >= 0 else "W"
tz_slug = timezone_name.replace("/", "%2F")
# Try both ways
url1 = f"https://www.meteoblue.com/en/weather/week/{lat}N{lon}E8_{tz_slug}"
url2 = f"https://www.meteoblue.com/en/weather/week/{abs(lat)}{lat_dir}{abs(lon)}{lon_dir}8_{tz_slug}"
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
"Accept-Language": "en-US,en;q=0.9"
}
proxies = {"http": "http://127.0.0.1:7890", "https": "http://127.0.0.1:7890"}
for url in [url1, url2]:
print(f"\nTesting URL: {url}")
try:
resp = requests.get(url, headers=headers, proxies=proxies, timeout=10)
print(f"Status: {resp.status_code}")
content = resp.text
match = re.search(r'Today.*?tab-temp-max.*?(\d+)&nbsp;°C', content, re.DOTALL | re.IGNORECASE)
if match:
print(f"Captured High: {match.group(1)}°C")
else:
all_highs = re.findall(r'tab-temp-max.*?(\d+)&nbsp;°C', content, re.DOTALL)
print(f"All Highs Found: {all_highs}")
except Exception as e:
print(f"Error: {e}")
test_mb_nyc()