feat: Add multi-source weather data collection module and clarify Meteoblue coverage in documentation.

README.md

@@ -42,7 +42,7 @@ The bot aggregates data from multiple authoritative sources, layered by reliabil
 | Source             | Role                    | Coverage        | Strength                                                                           |
 | :----------------- | :---------------------- | :-------------- | :--------------------------------------------------------------------------------- |
 | **Open-Meteo**     | Base Forecast           | Global          | Provides detailed 72-hour temperature curves for all cities.                       |
-| **Meteoblue (MB)** | **Precision Consensus** | Global          | **Traders' choice**. Aggregates multiple models; excellent for microclimates.      |
+| **Meteoblue (MB)** | **Precision Consensus** | London Only     | **Traders' choice**. Aggregates multiple models; excellent for microclimates.      |
 | **METAR**          | **Settlement Standard** | Global Airports | The absolute truth for Polymarket settlement; real-time station data.              |
 | **NWS**            | Official (US)           | US Only         | High-fidelity forecasts for US cities, critical for extreme weather events.        |
 | **MGM**            | Official (Turkey)       | Ankara          | Direct access to Turkish State Meteorological Service for local official accuracy. |
@@ -102,5 +102,5 @@ graph TD
 
 1. **Check Consensus**: Compare Open-Meteo and Meteoblue (MB). Consensus usually implies higher probability.
 2. **Watch the Peak**: Use `/city` frequently during predicted peak windows to catch momentum.
-3. **Weighting Hierarchy**: Settlement is **METAR**; high-accuracy trend is **MB**; Official (NWS/MGM) is the "anchor."
+3. **Weighting Hierarchy**: Settlement is **METAR**; high-accuracy trend is **MB** (London); Official (NWS/MGM) is the "anchor."
 4. **Geographic Risk**: Pay close attention to cities where "Bias will significantly amplify."

README_ZH.md

@@ -48,7 +48,7 @@ _注意：系统当前处于 **天气查询模式**。主动市场监控和自
 | 数据源             | 数据角色       | 覆盖范围   | 优势                                             |
 | :----------------- | :------------- | :--------- | :----------------------------------------------- |
 | **Open-Meteo**     | 基础预测       | 全球       | 提供所有城市的 72 小时精细化温度曲线             |
-| **Meteoblue (MB)** | **高精度共识** | 全球       | **交易员首选**。聚合多家模型，对微气候处理极佳   |
+| **Meteoblue (MB)** | **高精度共识** | 仅限伦敦   | **交易员首选**。聚合多家模型，对微气候处理极佳   |
 | **METAR**          | **结算标准**   | 全球机场   | Polymarket 结算参考的绝对真理，实时机场观测      |
 | **NWS**            | 官方预测(美)   | 仅限美国   | 美国国家气象局，对美国城市的极端天气预判准确     |
 | **MGM**            | 官方预测(土)   | 仅限安卡拉 | 土耳其气象局，提供安卡拉 Esenboğa 机场的官方数据 |
@@ -108,5 +108,5 @@ graph TD
 
 1. **检查模型共识**：查看 Open-Meteo 和 Meteoblue (MB) 是否达成共识。
 2. **关注峰值窗口**：在预测的峰值时段多次使用 `/city` 刷新。
-3. **数据权重优先级**：结算以 **METAR** 为准，趋势预测以 **MB** 为准。
+3. **数据权重优先级**：结算以 **METAR** 为准，趋势预测以 **MB** 为准（仅限伦敦）。
 4. **地理风险评估**：重点关注提示中的“偏差会显著放大”警告（如安卡拉、伦敦）。

src/data_collection/weather_sources.py

@@ -791,14 +791,15 @@ class WeatherDataCollector:
                     if mgm_data:
                         results["mgm"] = mgm_data
                 
-                # 获取 Meteoblue 预测 (公认最准)
-                mb_data = self.fetch_from_meteoblue(
-                    lat, lon, 
-                    timezone_name=open_meteo.get("timezone", "UTC"),
-                    use_fahrenheit=use_fahrenheit
-                )
-                if mb_data:
-                    results["meteoblue"] = mb_data
+                # 对伦敦，获取 Meteoblue 预测 (公认最准)
+                if city_lower == "london":
+                    mb_data = self.fetch_from_meteoblue(
+                        lat, lon, 
+                        timezone_name=open_meteo.get("timezone", "UTC"),
+                        use_fahrenheit=use_fahrenheit
+                    )
+                    if mb_data:
+                        results["meteoblue"] = mb_data
 
                 # 对美国城市，额外获取 NWS 高精预报
                 if use_fahrenheit: