找到优化股票和期货基础文件配置的方法

Micro-sheep · Jun 15, 2021 · cd4cc13 · cd4cc13
1 parent 732d0ca
commit cd4cc13
Show file tree

Hide file tree

Showing 16 changed files with 355 additions and 134 deletions.
diff --git a/.gitignore b/.gitignore
@@ -1,6 +1,6 @@
 # Folders
 */__pycache__/*
-efinance.egg-info
+*.egg-info*
 build
 dist
 
@@ -9,4 +9,5 @@ dist
 *.csv
 *.xlsx
 *.zip
-*.ipynb
+
+
diff --git a/.vscode/settings.json b/.vscode/settings.json
@@ -0,0 +1,3 @@
+{
+    "python.pythonPath": "D:\\Scoop\\shims\\python.exe"
+}
diff --git a/efinance/api/__init__.py b/efinance/api/__init__.py
@@ -2,4 +2,3 @@
 import efinance.fund as fund
 import efinance.futures as futures
 
-
diff --git a/efinance/fund/__init__.py b/efinance/fund/__init__.py
@@ -6,4 +6,4 @@
                      get_period_change,
                      get_public_dates,
                      get_industry_distributing,
-                     get_qoute_history)
+                     get_quote_history)
diff --git a/efinance/fund/getter.py b/efinance/fund/getter.py
@@ -5,7 +5,7 @@
 from .config import EastmoneyFundHeaders
 
 
-def get_qoute_history(fund_code: str, pz: int = 40000) -> pd.DataFrame:
+def get_quote_history(fund_code: str, pz: int = 40000) -> pd.DataFrame:
     '''
     根据基金代码和要获取的页码抓取基金净值信息
 
@@ -64,9 +64,6 @@ def get_qoute_history(fund_code: str, pz: int = 40000) -> pd.DataFrame:
     return df
 
 
-
-
-
 def get_realtime_increase_rate(fund_codes: Union[List[str], str]) -> pd.DataFrame:
     '''
     获取基金实时预期涨跌幅度
@@ -176,46 +173,46 @@ def get_inverst_postion(fund_code: str, dates: Union[str, List[str]] = None) ->
     DataFrame : 包含指定基金特定日期的公开持仓信息
     '''
     columns = {
-            'GPDM': '股票代码',
-            'GPJC': '股票简称',
-            'JZBL': '持仓占比',
-            'PCTNVCHG': '较上期变化',
-        }
+        'GPDM': '股票代码',
+        'GPJC': '股票简称',
+        'JZBL': '持仓占比',
+        'PCTNVCHG': '较上期变化',
+    }
     df = pd.DataFrame(columns=columns.values())
-    if not isinstance(dates,List):
+    if not isinstance(dates, List):
         dates = [dates]
-    
+
     for date in dates:
         params = [
-        ('FCODE', fund_code),
-        ('MobileKey', '3EA024C2-7F22-408B-95E4-383D38160FB3'),
-        ('OSVersion', '14.3'),
-        ('appType', 'ttjj'),
-        ('appVersion', '6.2.8'),
-        ('deviceid', '3EA024C2-7F22-408B-95E4-383D38160FB3'),
-        ('passportid', '3061335960830820'),
-        ('plat', 'Iphone'),
-        ('product', 'EFund'),
-        ('serverVersion', '6.2.8'),
-        ('uToken', '6cfr1qdanf8nfhd6uc6u-hdj86f1f8kfe9f8k108.6'),
-        ('userId', 'f8d95b2330d84d9e804e7f28a802d809'),
-        ('version', '6.2.8'),
-    ]
+            ('FCODE', fund_code),
+            ('MobileKey', '3EA024C2-7F22-408B-95E4-383D38160FB3'),
+            ('OSVersion', '14.3'),
+            ('appType', 'ttjj'),
+            ('appVersion', '6.2.8'),
+            ('deviceid', '3EA024C2-7F22-408B-95E4-383D38160FB3'),
+            ('passportid', '3061335960830820'),
+            ('plat', 'Iphone'),
+            ('product', 'EFund'),
+            ('serverVersion', '6.2.8'),
+            ('uToken', '6cfr1qdanf8nfhd6uc6u-hdj86f1f8kfe9f8k108.6'),
+            ('userId', 'f8d95b2330d84d9e804e7f28a802d809'),
+            ('version', '6.2.8'),
+        ]
         if date is not None:
-            params.append(('DATE',date))
+            params.append(('DATE', date))
         params = tuple(params)
         response = requests.get('https://fundmobapi.eastmoney.com/FundMNewApi/FundMNInverstPosition',
                                 headers=EastmoneyFundHeaders, params=params)
         stocks = response.json()['Datas']['fundStocks']
-        
+
         if stocks is None or len(stocks) == 0:
             continue
-        
+
         _df = pd.DataFrame(stocks)
         _df = _df[list(columns.keys())].rename(columns=columns)
-        _df['公开日期'] = [date for _ in range(len(_df))] 
-        df = pd.concat([df,_df],axis=0)
-    df.insert(0,'基金代码',[fund_code for _ in range(len(df))])
+        _df['公开日期'] = [date for _ in range(len(_df))]
+        df = pd.concat([df, _df], axis=0)
+    df.insert(0, '基金代码', [fund_code for _ in range(len(df))])
     return df
 
 
@@ -271,7 +268,7 @@ def get_period_change(fund_code: str) -> pd.DataFrame:
 
     df = df[list(columns.keys())].rename(columns=columns)
     df['时间段'] = titles.values()
-    df.insert(0,'基金代码',[fund_code for _ in range(len(df))])
+    df.insert(0, '基金代码', [fund_code for _ in range(len(df))])
     return df
 
 
@@ -311,7 +308,7 @@ def get_public_dates(fund_code: str) -> List[str]:
     return json_response['Datas']
 
 
-def get_types_persentage(fund_code: str, dates:Union[List[str],str,None]=None) -> pd.DataFrame:
+def get_types_persentage(fund_code: str, dates: Union[List[str], str, None] = None) -> pd.DataFrame:
     '''
     获取指定基金不同类型占比信息
 
@@ -329,43 +326,43 @@ def get_types_persentage(fund_code: str, dates:Union[List[str],str,None]=None) -
     DataFrame : 指定基金的在不同日期的不同类型持仓占比信息
     '''
     columns = {
-            'GP': '股票比重',
-            'ZQ': '债券比重',
-            'HB': '现金比重',
-            'JZC': '总规模(亿元)',
-            'QT': '其他比重'
-        }
-    df = pd.DataFrame(columns = columns.values())
-    if not isinstance(dates,List):
+        'GP': '股票比重',
+        'ZQ': '债券比重',
+        'HB': '现金比重',
+        'JZC': '总规模(亿元)',
+        'QT': '其他比重'
+    }
+    df = pd.DataFrame(columns=columns.values())
+    if not isinstance(dates, List):
         dates = [dates]
     for date in dates:
         params = [
-        ('FCODE', fund_code),
-        ('MobileKey', '3EA024C2-7F22-408B-95E4-383D38160FB3'),
-        ('OSVersion', '14.3'),
-        ('appVersion', '6.3.8'),
-        ('cToken', 'a6hdhrfejje88ruaeduau1rdufna1e--.6'),
-        ('deviceid', '3EA024C2-7F22-408B-95E4-383D38160FB3'),
-        ('passportid', '3061335960830820'),
-        ('plat', 'Iphone'),
-        ('product', 'EFund'),
-        ('serverVersion', '6.3.6'),
-        ('uToken', 'a166hhqnrajucnfcjkfkeducanekj1dd1cc2a-e9.6'),
-        ('userId', 'f8d95b2330d84d9e804e7f28a802d809'),
-        ('version', '6.3.8'),
-    ]
+            ('FCODE', fund_code),
+            ('MobileKey', '3EA024C2-7F22-408B-95E4-383D38160FB3'),
+            ('OSVersion', '14.3'),
+            ('appVersion', '6.3.8'),
+            ('cToken', 'a6hdhrfejje88ruaeduau1rdufna1e--.6'),
+            ('deviceid', '3EA024C2-7F22-408B-95E4-383D38160FB3'),
+            ('passportid', '3061335960830820'),
+            ('plat', 'Iphone'),
+            ('product', 'EFund'),
+            ('serverVersion', '6.3.6'),
+            ('uToken', 'a166hhqnrajucnfcjkfkeducanekj1dd1cc2a-e9.6'),
+            ('userId', 'f8d95b2330d84d9e804e7f28a802d809'),
+            ('version', '6.3.8'),
+        ]
         if date is not None:
             params.append(('DATE', date))
         params = tuple(params)
         json_response = requests.get(
-        'https://fundmobapi.eastmoney.com/FundMNewApi/FundMNAssetAllocationNew',  params=params).json()
-    
+            'https://fundmobapi.eastmoney.com/FundMNewApi/FundMNAssetAllocationNew',  params=params).json()
+
         if len(json_response['Datas']) == 0:
             continue
         _df = pd.DataFrame(json_response['Datas'])[columns.keys()]
         _df = _df.rename(columns=columns)
-        df = pd.concat([df,_df],axis=0)
-    df.insert(0,'基金代码',[fund_code for _ in range(len(df))])
+        df = pd.concat([df, _df], axis=0)
+    df.insert(0, '基金代码', [fund_code for _ in range(len(df))])
     return df
 
 
@@ -427,7 +424,7 @@ def get_industry_distributing(fund_code: str, dates: Union[str, List[str]] = Non
     Return
     ------
     DataFrame : 包含指定基金行业持仓信息的表格
-    
+
     '''
     columns = {
         'HYMC': '行业名称',
@@ -458,13 +455,13 @@ def get_industry_distributing(fund_code: str, dates: Union[str, List[str]] = Non
         ]
         if date is not None:
             params.append(('DATE', date))
-        
+
         response = requests.get('https://fundmobapi.eastmoney.com/FundMNewApi/FundMNSectorAllocation',
                                 headers=EastmoneyFundHeaders, params=params)
         datas = response.json()['Datas']
         _df = pd.DataFrame(datas)
         _df = _df.rename(columns=columns)
-        df = pd.concat([df, _df],axis=0)
-    df.insert(0,'基金代码',[fund_code for _ in range(len(df))])
+        df = pd.concat([df, _df], axis=0)
+    df.insert(0, '基金代码', [fund_code for _ in range(len(df))])
     df = df.drop_duplicates()
     return df
diff --git a/efinance/futures/__init__.py b/efinance/futures/__init__.py
@@ -1,3 +1,3 @@
-from .getter import (get_futures_base_info,
-                                     get_qoute_history)
-
+from .getter import (
+    get_futures_base_info,
+    get_quote_history)
diff --git a/efinance/futures/config.py b/efinance/futures/config.py
@@ -1,3 +1,8 @@
+
+from pathlib import Path
+HERE = Path(__file__).parent
+FUTURES_BASE_INFO_SAVE_PATH = HERE/'futures_info.csv'
+
 EastmoneyKlines = {
     'f51': '日期',
     'f52': '开盘',

diff --git a/efinance/futures/getter.py b/efinance/futures/getter.py
@@ -1,8 +1,12 @@
+from .utils import update_local_futures_info
+from typing import Dict, List, Union
 import pandas as pd
 import requests
 from urllib.parse import urlencode
-
+import multitasking
+from tqdm import tqdm
 from .config import EastmoneyHeaders, EastmoneyKlines
+from retry import retry
 
 
 def get_futures_base_info() -> pd.DataFrame:
@@ -42,7 +46,11 @@ def get_futures_base_info() -> pd.DataFrame:
     return df
 
 
-def get_qoute_history(secid: str, beg: str = '19000101', end: str = '20500101', klt: int = 101, fqt: int = 1) -> pd.DataFrame:
+def get_quote_history_single(secid: str,
+                             beg: str = '19000101',
+                             end: str = '20500101',
+                             klt: int = 101,
+                             fqt: int = 1) -> pd.DataFrame:
     '''
     获取k线数据
 
@@ -67,11 +75,10 @@ def get_qoute_history(secid: str, beg: str = '19000101', end: str = '20500101',
     DateFrame : 包含股票k线数据
 
     '''
-    
+
     fields = list(EastmoneyKlines.keys())
     columns = list(EastmoneyKlines.values())
     fields2 = ",".join(fields)
-
 
     params = (
         ('fields1', 'f1,f2,f3,f4,f5,f6,f7,f8,f9,f10,f11,f12,f13'),
@@ -93,7 +100,6 @@ def get_qoute_history(secid: str, beg: str = '19000101', end: str = '20500101',
         print(secid, '无数据')
         return None
     # code = data['code']
-    # name
     # name = data['name']
     klines = data['klines']
 
@@ -106,3 +112,92 @@ def get_qoute_history(secid: str, beg: str = '19000101', end: str = '20500101',
     df = pd.DataFrame(rows, columns=columns)
 
     return df
+
+
+def get_quote_history_multi(secids: List[str],
+                            beg: str = '19000101',
+                            end: str = '20500101',
+                            klt: int = 101,
+                            fqt: int = 1,
+                            tries: int = 3) -> Dict[str, pd.DataFrame]:
+    '''
+    获取多只股票历史行情信息
+
+    Parameters
+    ----------
+    secids : 多个 期货 secid 列表
+    beg : 开始日期 例如 20200101
+    end : 结束日期 例如 20200201
+    klt : k线间距 默认为 101 即日k
+            klt : 1 1 分钟
+            klt : 5 5 分钟
+            klt : 101 日
+            klt : 102 周
+    fqt: 复权方式
+            不复权 : 0
+            前复权 : 1
+            后复权 : 2 
+
+    Return
+    ------
+    DateFrame : 包含股票k线数据
+    '''
+    dfs: Dict[str, pd.DataFrame] = {}
+    total = len(secids)
+    if total != 0:
+        update_local_futures_info()
+
+    @retry(tries=tries)
+    @multitasking.task
+    def start(stock_code: str):
+        _df = get_quote_history_single(
+            stock_code, beg=beg, end=end, klt=klt, fqt=fqt)
+        dfs[stock_code] = _df
+        pbar.update(1)
+        pbar.set_description_str(f'Processing: {stock_code}')
+
+    pbar = tqdm(total=total)
+    for stock_code in secids:
+        start(stock_code)
+    multitasking.wait_for_tasks()
+    pbar.close()
+    return dfs
+
+
+def get_quote_history(secids: Union[str, List[str]],
+                      beg: str = '19000101',
+                      end: str = '20500101',
+                      klt: int = 101,
+                      fqt: int = 1) -> pd.DataFrame:
+    '''
+    获取k线数据
+
+    Parameters
+    ----------
+    secids : 6 位股票代码 或者 6 位股票代码构成的列表
+    beg : 开始日期 例如 20200101
+    end : 结束日期 例如 20200201
+    klt : k线间距 默认为 101 即日k
+            klt : 1 1 分钟
+            klt : 5 5 分钟
+            klt : 101 日
+            klt : 102 周
+    fqt: 复权方式
+            不复权 : 0
+            前复权 : 1
+            后复权 : 2 
+
+    Return
+    ------
+    DateFrame : 包含股票k线数据
+
+    '''
+    if isinstance(secids, str):
+        return get_quote_history_single(secids, beg=beg, end=end, klt=klt, fqt=fqt)
+    elif hasattr(secids, '__iter__'):
+        secids = list(secids)
+        return get_quote_history_multi(secids, beg=beg, end=end, klt=klt, fqt=fqt)
+    else:
+        raise TypeError(
+            '期货 secid 类型输入不正确！'
+        )