SuperAPI AI Directory
Partner中文AI newsFavorites
Skillstushare

tushare

General & other

View repository

Updated 10-16 01:49

About this skill

Tushare Data Retrieval

Task Objective

  • This Skill is used to: obtain A-share market data, financial indicators, and macroeconomic data through the Tushare data interface
  • Capabilities include: real-time quotes, historical K-lines, financial data, indicator data, stock information, macroeconomic data, index data
  • Trigger conditions: when users mention Tushare or need to obtain A-share data, financial information, or macroeconomic data

Prerequisites

  • Dependency description: install the tushare library (already included in dependency)
  • Credential configuration: Tushare Token must be configured (credential name: TUSHARE_TOKEN, environment variable: TUSHARE_TOKEN)
  • Account application: visit https://tushare.pro/ register an account and obtain an API Token (see references/tushare_quickstart.md for details)

Operation Steps

  • Standard process:
    1. Determine data requirements — the agent understands the user's intent (quotes/K-lines/financials/macroeconomic/index, etc.)
    2. Call the corresponding script — select the script according to the data type
    3. Parse results — the agent analyzes the returned JSON-format data
  • Script call mapping:
    • Quotes/K-lines/adjusted data → python scripts/market_data.py --type daily --ts_code 000001.SZ --start_date 20240101 --end_date 20240131
    • Financial data/income statement/balance sheet → python scripts/financial_data.py --type financial --ts_code 000001.SZ --period 2023
    • Stock list/trading calendar → python scripts/stock_info.py --type stock_basic
    • Index data/macroeconomic data → python scripts/macro_index_data.py --type index_daily --ts_code 000001.SH --start_date 20240101 --end_date 20240131
  • Optional branches:
    • When data for multiple stocks is needed: use the --ts_code parameter separated by commas
    • When adjusted data is needed: use --type adj_factor to obtain adjustment factors
    • When a reporting period needs to be specified: use the --period parameter (YYYY or YYYYMM)

Usage Examples

  • Example 1: Obtain daily K-line data for a stock
    • Scenario/Input: the user says "view the K-line data for Ping An Bank over the last month"
    • Expected output: return OHLCV data such as date, opening price, highest price, lowest price, closing price, and trading volume
    • Key point: call python scripts/market_data.py --type daily --ts_code 000001.SZ --start_date 20240301 --end_date 20240331
  • Example 2: Query financial data
    • Scenario/Input: the user says "obtain China Merchants Bank's 2023 financial indicators"
    • Expected output: return financial indicators such as ROE, ROA, gross margin, and net margin
    • Key point: call python scripts/financial_data.py --type fina_indicator --ts_code 600036.SH --period 2023
  • Example 3: Obtain index data
    • Scenario/Input: the user says "query the recent trend of the Shanghai Composite Index"
    • Expected output: return data such as the date, closing price, and trading volume of the Shanghai Composite Index
    • Key point: call python scripts/macro_index_data.py --type index_daily --ts_code 000001.SH --start_date 20240301 --end_date 20240331

Quick Reference

Common Code Examples

import tushare as ts
import pandas as pd

# 设置 Token（需先设置环境变量 TUSHARE_TOKEN）
ts.set_token(os.environ.get('TUSHARE_TOKEN', ''))
pro = ts.pro_api()

# 获取日K线数据
df = pro.daily(ts_code='000001.SZ', start_date='20240101', end_date='20241231')

# 获取财务指标
df = pro.fina_indicator(ts_code='600036.SH', period='2023')

# 获取指数数据
df = pro.index_daily(ts_code='000001.SH', start_date='20240101', end_date='20241231')

Comparison with Other Data Sources

Feature tushare jqdatasdk baostock akshare
Cost Free/Paid Requires registration points Free Free
Registration requirement ✅ Required ✅ Required ❌ Not required ❌ Not required
Data scope Comprehensive (including macroeconomic) A-shares + factors Mainly A-shares Comprehensive
Macro data ✅ Rich ❌ ❌ ✅
Call frequency Free with limits Yes Unlimited Unlimited

Resource index

  • Scripts:
    • scripts/market_data.py (Purpose and parameters: retrieve market quotes/K-line/adjusted data, supports --type/--ts_code/--start_date/--end_date)
    • scripts/financial_data.py (Purpose and parameters: retrieve financial data/income statement/balance sheet/cash flow statement/indicators, supports --type/--ts_code/--period)
    • scripts/stock_info.py (Purpose and parameters: retrieve stock list/trading calendar/name changes, supports --type/--ts_code/--start_date/--end_date)
    • scripts/macro_index_data.py (Purpose and parameters: retrieve index data/macro data/Shibor, supports --type/--ts_code/--start_date/--end_date)
  • References:

Notes

  • Script execution requires configuring a Tushare Token; credential configuration must be completed before first use
  • Tushare stock code format: Shanghai market is XXXXXX.SH, Shenzhen market is XXXXXX.SZ
  • Some data (such as financial data) may be delayed; it is recommended to retrieve it outside trading hours 9:30-15:00
  • The script returns data in JSON format; the agent is responsible for parsing and converting it into a user-friendly presentation
  • There is a call frequency limit; free accounts can make at most 120 calls per minute (see the official Tushare documentation for details)
  • For first use, it is recommended to first read tushare_quickstart.md to complete authentication configuration