From 6560696a3734462ead1ad21ab32b30f829346368 Mon Sep 17 00:00:00 2001
From: "2569718930@qq.com" <2569718930@qq.com>
Date: Sun, 8 Feb 2026 19:57:44 +0800
Subject: [PATCH] feat: Implement multi-source weather data collection from
OpenWeatherMap, Visual Crossing, and NOAA METAR, and add NYC market-specific
data handling.
---
bot_listener.py | 24 ++++++++++------
save_nyc_mb.py | 17 +++++++++++
src/data_collection/weather_sources.py | 32 +++++++++++++++++----
test_nyc_mb.py | 39 ++++++++++++++++++++++++++
4 files changed, 98 insertions(+), 14 deletions(-)
create mode 100644 save_nyc_mb.py
create mode 100644 test_nyc_mb.py
diff --git a/bot_listener.py b/bot_listener.py
index 54114665..1f755f13 100644
--- a/bot_listener.py
+++ b/bot_listener.py
@@ -218,13 +218,13 @@ def start_bot():
"la": "los angeles", "洛杉矶": "los angeles",
}
- # 1. 尝试直接从映射表获取
+ # 1. 第一优先级：严格全字匹配
city_name = STANDARD_MAPPING.get(city_input)
- # 2. 如果没匹配到，尝试前缀匹配 (如输入 "seou")
- if not city_name:
+ # 2. 第二优先级：如果长度 >= 3，尝试前缀匹配
+ if not city_name and len(city_input) >= 3:
for k, v in STANDARD_MAPPING.items():
- if len(city_input) >= 3 and k.startswith(city_input[:3]):
+ if k.startswith(city_input):
city_name = v
break
@@ -278,19 +278,27 @@ def start_bot():
if mb_high is not None:
sources.append("MB")
- comp_parts.append(f"MB: {mb_high}")
+ comp_parts.append(f"MB: {mb_high:.1f}{temp_symbol}" if isinstance(mb_high, (int, float)) else f"MB: {mb_high}")
if nws_high is not None:
sources.append("NWS")
- comp_parts.append(f"NWS: {nws_high}")
+ comp_parts.append(f"NWS: {nws_high:.1f}{temp_symbol}" if isinstance(nws_high, (int, float)) else f"NWS: {nws_high}")
if mgm_high is not None:
sources.append("MGM")
- comp_parts.append(f"MGM: {mgm_high}")
+ comp_parts.append(f"MGM: {mgm_high:.1f}{temp_symbol}" if isinstance(mgm_high, (int, float)) else f"MGM: {mgm_high}")
+
+ # 检查是否有显著分歧 (超过 5°F 或 2.5°C)
+ divergence_warning = ""
+ if mb_high is not None and max_temps:
+ diff = abs(mb_high - max_temps[0])
+ threshold = 5.0 if temp_unit == "fahrenheit" else 2.5
+ if diff > threshold:
+ divergence_warning = f" ⚠️ 模型显著分歧 ({diff:.1f}{temp_symbol})"
comp_str = f" ({' | '.join(comp_parts)})" if comp_parts else ""
sources_str = " | ".join(sources)
msg_lines.append(f"\n📊 预报 ({sources_str})")
- msg_lines.append(f"👉 今天: {today_t}{temp_symbol}{comp_str}")
+ msg_lines.append(f"👉 今天: {today_t}{temp_symbol}{comp_str}{divergence_warning}")
# 明后天
if len(dates) > 1:
diff --git a/save_nyc_mb.py b/save_nyc_mb.py
new file mode 100644
index 00000000..36f8fd6f
--- /dev/null
+++ b/save_nyc_mb.py
@@ -0,0 +1,17 @@
+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()
diff --git a/src/data_collection/weather_sources.py b/src/data_collection/weather_sources.py
index 2ebd07c2..5accfbd6 100644
--- a/src/data_collection/weather_sources.py
+++ b/src/data_collection/weather_sources.py
@@ -535,27 +535,47 @@ class WeatherDataCollector:
从 Meteoblue 网页抓取多模型预测数据的“共识”最高温
"""
try:
+ # 1. 构造精确的方向后缀 URL
+ lat_dir = "N" if lat >= 0 else "S"
+ lon_dir = "E" if lon >= 0 else "W"
+ # Meteoblue 坐标 URL 习惯：保留 3 位小数，使用大写方向后缀
+ coord_str = f"{abs(lat):.3f}{lat_dir}{abs(lon):.3f}{lon_dir}"
tz_slug = timezone_name.replace("/", "%2F")
- url = f"https://www.meteoblue.com/en/weather/week/{lat}N{lon}E8_{tz_slug}"
+
+ # 使用 forecast/week 路径通常比直接 week 更稳定
+ url = f"https://www.meteoblue.com/en/weather/week/{coord_str}"
+ 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"
+ "Accept-Language": "en-US,en;q=0.9",
+ "Referer": "https://www.meteoblue.com/"
}
response = self.session.get(
url,
headers=headers,
- 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()
content = response.text
+
+ # 2. 检查是否重定向到了错误的地方 (例如大阪 Osaka)
+ # 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
+ if lon < 0 and "W" in coord_str:
+ 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+) °C', content, re.DOTALL | re.IGNORECASE)
result = {
"source": "meteoblue",
- "url": url,
+ "url": response.url,
"today_high": None,
"daily_highs": [],
"unit": "celsius"
@@ -568,7 +588,7 @@ class WeatherDataCollector:
val = float(match.group(1))
result["today_high"] = c_to_f(val) if use_fahrenheit else val
- # 同时提取接下来几天的最高温
+ # 同时提取接下来几天
all_highs = re.findall(r'tab-temp-max.*?(\d+) °C', content, re.DOTALL)
if all_highs:
if use_fahrenheit:
@@ -577,7 +597,7 @@ class WeatherDataCollector:
result["daily_highs"] = [float(h) for h in all_highs]
result["unit"] = "fahrenheit" if use_fahrenheit else "celsius"
- logger.info(f"✅ Meteoblue 抓取成功: 今天 {result['today_high']}{result['unit']}")
+ logger.info(f"✅ Meteoblue 抓取成功 ({coord_str}): 今天 {result['today_high']}{result['unit']}")
return result
except Exception as e:
logger.error(f"Meteoblue fetch failed: {e}")
diff --git a/test_nyc_mb.py b/test_nyc_mb.py
new file mode 100644
index 00000000..543d6834
--- /dev/null
+++ b/test_nyc_mb.py
@@ -0,0 +1,39 @@
+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+) °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+) °C', content, re.DOTALL)
+ print(f"All Highs Found: {all_highs}")
+ except Exception as e:
+ print(f"Error: {e}")
+
+test_mb_nyc()