update-csi500

scripts/data_collector/cn_index/collector.py

@@ -5,7 +5,6 @@ import re
 import abc
 import sys
 import importlib
-from tqdm import tqdm
 from io import BytesIO
 from typing import List, Iterable
 from pathlib import Path
@@ -14,7 +13,7 @@ import fire
 import requests
 import pandas as pd
 import baostock as bs
-from lxml import etree
+from tqdm import tqdm
 from loguru import logger
 
 CUR_DIR = Path(__file__).resolve().parent
@@ -47,7 +46,6 @@ def retry_request(url: str, method: str = "get", exclude_status: List = None):
 
 
 class CSIIndex(IndexBase):
-
     @property
     def calendar_list(self) -> List[pd.Timestamp]:
         """get history trading date
@@ -318,7 +316,6 @@ class CSIIndex(IndexBase):
 
 
 class CSI300(CSIIndex):
-
     @property
     def index_code(self):
         return "000300"
@@ -329,11 +326,10 @@ class CSI300(CSIIndex):
 
     @property
     def html_table_index(self):
-        return 0
+        return 1
 
 
 class CSI100(CSIIndex):
-
     @property
     def index_code(self):
         return "000903"
@@ -344,11 +340,10 @@ class CSI100(CSIIndex):
 
     @property
     def html_table_index(self):
-        return 1
+        return 2
 
 
 class CSI500(CSIIndex):
-
     @property
     def index_code(self):
         return "000905"
@@ -366,7 +361,7 @@ class CSI500(CSIIndex):
 
     def get_history_companies(self):
         """
-		Data source：http://baostock.com/baostock/index.php/%E4%B8%AD%E8%AF%81500%E6%88%90%E5%88%86%E8%82%A1
+        Data source: http://baostock.com/baostock/index.php/%E4%B8%AD%E8%AF%81500%E6%88%90%E5%88%86%E8%82%A1
                 Avoid a large number of parallel data acquisition,
                 such as 1000 times of concurrent data acquisition, because IP will be blocked
         Returns
@@ -391,7 +386,12 @@ class CSI500(CSIIndex):
 
 
 def get_instruments(
-    qlib_dir: str, index_name: str, method: str = "parse_instruments", request_retry: int = 5, retry_sleep: int = 3
+    qlib_dir: str,
+    index_name: str,
+    method: str = "parse_instruments",
+    freq: str = "day",
+    request_retry: int = 5,
+    retry_sleep: int = 3,
 ):
     """
 

scripts/data_collector/utils.py

@@ -34,6 +34,7 @@ CALENDAR_BENCH_URL_MAP = {
     "ALL": CALENDAR_URL_BASE.format(market=1, bench_code="000905"),
     # NOTE: Use the time series of ^GSPC(SP500) as the sequence of all stocks
     "US_ALL": "^GSPC",
+    "IN_ALL": "^NSEI",
 }
 
 _BENCH_CALENDAR_LIST = None
@@ -452,9 +453,7 @@ def symbol_prefix_to_sufix(symbol: str, capital: bool = True) -> str:
 
 
 def deco_retry(retry: int = 5, retry_sleep: int = 3):
-
     def deco_func(func):
-
         @functools.wraps(func)
         def wrapper(*args, **kwargs):
             _retry = 5 if callable(retry) else retry