处理指数和基金映射

index_downloader.py

@@ -1,5 +1,5 @@
 import os
-
+import re
 import akshare as ak
 import pandas as pd
 from loguru import logger
@@ -25,27 +25,56 @@ def get_all_stock_index():
     return df
 
 
+def get_index_fund_info():
+    # 读取指数数据和基金数据
+    index_df = pd.read_csv(
+        "/Users/aszer/Documents/vscode/etf/data/index_all_stock.csv",
+        encoding="utf-8-sig",
+    )
+    fund_df = pd.read_csv(
+        "/Users/aszer/Documents/vscode/etf/data/fund_info.csv", encoding="utf-8-sig"
+    )
+
+    # 构建指数名称集合去重，加快后续匹配
+    index_name_set = set(index_df["名称"].astype(str).unique())
+
+    # 对每个基金名称，查找其是否包含某一指数名称，允许多对多匹配
+    records = []
+    for fund_idx, fund_row in fund_df.iterrows():
+        fund_name = str(fund_row["基金名称"])
+        fund_code = str(fund_row["基金代码"])
+        funf_fee = fund_row["手续费"]
+        matched_index_list = [
+            idx_name
+            for idx_name in index_name_set
+            if idx_name.lower() in fund_name.lower()
+        ]
+        for idx_name in matched_index_list:
+            # 找到指数的相关代码
+            index_row = index_df[index_df["名称"] == idx_name]
+            index_code = None
+            if not index_row.empty:
+                index_code = str(index_row.iloc[0]["代码"])
+            records.append(
+                {
+                    "指数代码": index_code,
+                    "指数名称": idx_name,
+                    "基金代码": fund_code,
+                    "基金名称": fund_name,
+                    "手续费": funf_fee,
+                }
+            )
+    index_fund_df = pd.DataFrame(records)
+    index_fund_df = index_fund_df.sort_values("指数代码").reset_index(drop=True)
+    return index_fund_df
+
+
 if __name__ == "__main__":
     # df = get_all_stock_index()
     # df.to_csv("index_all_stock.csv", index=False, encoding="utf-8-sig")
 
-    df = pd.read_csv("index_all_stock.csv", encoding="utf-8-sig")
+    # res = ak.fund_etf_spot_em()
-    for index, row in df.iterrows():
+    # print(res)
-        print(f"正在获取 {index} {row['代码']} ...")
-        file_path = f"data/{row['代码']}.csv"
-        if os.path.exists(file_path):
-            print(f"{row['代码']} 存在")
-            continue
-        index_hist_df = ak.index_zh_a_hist(
-            symbol=row["代码"],  # 指数代码,如上证指数
-            period="daily",  # K线周期: daily(日K)
-            start_date="19700101",  # 开始日期
-            end_date="22220101",  # 结束日期
-        )
-        index_hist_df.to_csv(
-            f"data/{row['代码']}.csv", index=False, encoding="utf-8-sig"
-        )
-        # time.sleep(15)
-    # print(index_hist_df)
 
-    ...
+    df = get_index_fund_info()
+    df.to_csv("index_fund_info.csv", index=False, encoding="utf-8-sig")