按「数据类型」合并同类查询接口:一个数据类型 = 一个方法,跨市场自动选路。 - 28 个统一接口(get_universe/get_quotes/get_bars/get_indicators/get_ticks/ get_minutes/get_f10/get_file/get_boards/get_board_of/get_snapshot 等), 标的统一字符串写法(sz000001 / hk00700 / usAAPL / cffex:IFL0); 同名旧方法不再兼容 (market, code) 元组。 - 旧 51 个按通道/市场分裂的接口:33 个保留为 deprecated 别名(1.0 移除), 18 个同名升级为统一接口。公开方法共 63 个。 - 新增库层标的解析 pytdxdata.symbols;数据模型追加 symbol/name/fields 兜底字段。 - 修复:分页器连接泄漏、日期区间 K线返回 0 条(偏移方向探测)、池子全冷却死等。 - 文档/README/SKILL/llms.txt 全量同步;新增 docs/refactor-audit.md 审查报告。 - 测试 127 个用例全绿(含 tests/test_all_interfaces.py 全 63 方法回归)。
7.4 KiB
7.4 KiB
场景示例
每个片段都是完整可跑的。共同前提:
import asyncio
from pathlib import Path
from pytdxdata import TdxData
from pytdxdata.models import Adjust, KlinePeriod
全市场日线批量落库
连接池会把不同股票分配到不同服务器,这是 *_batch 存在的意义。
async def dump_all_daily():
async with TdxData(cache_dir=Path("./tdx_cache")) as td:
infos = await td.get_universe("sz") # 缓存 1 天
symbols = [i.symbol for i in infos] # ["sz000001", ...]
bars = await td.get_bars(
symbols,
KlinePeriod.DAY,
count=800,
adjust=Adjust.QFQ,
concurrency=12,
)
got = {b.symbol for b in bars}
print(f"{len(got)} / {len(symbols)} 只拿到数据")
# bars 是扁平 list[SecurityBar](按标的/时间排序),落库 / 写 parquet 都行
if bars:
print(bars[-1].symbol, bars[-1].datetime, bars[-1].close)
!!! tip "分页与并发的取舍"
concurrency 不是越大越好。单台服务器有连接上限,concurrency 超过 pool_max × 服务器数
之后只会排队。实践值:8~16。
分钟线增量更新
只拉「上次之后」的部分,用 get_bars(start_date=...) 省掉全量重拉。
async def update_minute(symbol: str, last_dt):
async with TdxData(cache_dir=Path("./tdx_cache")) as td:
rows = await td.get_bars(symbol, KlinePeriod.MIN_1, start_date=last_dt)
return [r for r in rows if r.datetime > last_dt]
!!! warning "1 分钟 K 线走 MAC 单连接串行分页"
这是刻意设计:并发分页会把不同页分到不同服务器,而各服务器历史深度不一致,
拼接后会出现非确定性数据空洞。所以 MIN_1 强制单连接串行(见 通道与数据源)。
报价轮询
async def poll_quotes(symbols, interval=5.0):
async with TdxData() as td:
while True:
quotes = await td.get_quotes(symbols) # >80 只自动切批;缓存 TTL 5s
for q in quotes:
print(q.code, q.price, q.bid[0], q.ask[0])
await asyncio.sleep(interval)
缓存 TTL 与轮询间隔对齐时,重复轮询几乎 0 网络开销。但注意通达信公开源本身是 15 分钟延时数据,别拿它做实时交易决策。
板块轮动 / 领涨股
async def sector_rotation():
async with TdxData() as td:
# 近 5 日概念板块涨幅排行
top = await td.get_board_change_ranking(kind="concept", days=5, top_n=10)
for row in top:
print(row)
# 拿第一名板块的成分股
symbol = top[0]["symbol"] if "symbol" in top[0] else "881001"
members = await td.get_board_members(symbol, count=20)
for m in members[:5]:
print(m.code, m.name, m.fields)
# 板块资金汇总
print(await td.get_board_summary(symbol))
个股所属板块(反向查询)
async def belong(symbol: str):
async with TdxData() as td:
for b in await td.get_board_of(symbol):
print(b)
逐笔复盘
async def review_transactions(symbol: str, ymd: int):
async with TdxData() as td:
rows = await td.get_ticks(symbol, date=ymd, count=2000)
total = sum(r.trade_count or 0 for r in rows)
buy = sum(r.vol for r in rows if r.bs_flag == 0) # 主动买
sell = sum(r.vol for r in rows if r.bs_flag == 1) # 主动卖
print(f"{ymd} 总成交笔数={total} 主动买={buy} 主动卖={sell}")
财务因子快照
async def finance_snapshot(symbols):
async with TdxData() as td:
for fin in await td.get_finance(symbols): # 标准通道,最新快照
print(fin.symbol, fin)
历史专业财报(gpcw*.zip,含多报告期)走文件接口:
async def history_financials(code: str):
async with TdxData(cache_dir=Path("./tdx_cache")) as td:
infos = await td.get_financial_file_infos() # 索引
records = await td.get_financial_records_parsed(infos[-1].filename)
row = next((r for r in records if r.code == code), None)
if row:
print(row.report_date, row.fields[:8])
行业分类映射
async def industry_lookup(codes):
async with TdxData(cache_dir=Path("./tdx_cache")) as td:
hy = await td.get_industry_map() # {6位代码: IndustryInfo}
for c in codes:
info = hy.get(c)
if info:
print(c, info.tdx_industry, info.sw_industry)
板块成分(离线解析)
get_block_parsed 拿到的是纯 dataclass,落成本地 JSON 后完全脱网可用——
适合做「板块成分快照」的定时任务。
import json
async def snapshot_blocks():
async with TdxData(cache_dir=Path("./tdx_cache")) as td:
all_blocks = []
for fn in ("block_zs.dat", "block_gn.dat", "block_fg.dat"):
for b in await td.get_block_parsed(fn):
all_blocks.append({
"name": b.name,
"category": b.category,
"codes": b.codes,
})
Path("blocks.json").write_text(
json.dumps(all_blocks, ensure_ascii=False), encoding="utf-8"
)
港股 / 美股 / 期货 / 期权
async def ex_markets():
async with TdxData() as td:
hk = await td.get_bars("hk00700", KlinePeriod.DAY, count=700)
us = await td.get_bars("usAAPL", KlinePeriod.DAY, count=700)
fut = await td.get_bars("cffex:IFL0", KlinePeriod.DAY, count=700)
opt = await td.get_bars("sh_stock_option:10010971", KlinePeriod.DAY, count=700)
print(len(hk), len(us), len(fut), len(opt))
# 港股全量逐笔(自动翻页,≤50 页 / 9 万条)
ticks = await td.get_ticks("hk00700", count=None)
print(len(ticks))
转成 pandas
包本身不带 pandas 依赖,但转换是一行的事:
import pandas as pd
async def to_dataframe(symbol: str):
async with TdxData() as td:
bars = await td.get_bars(symbol, KlinePeriod.DAY, count=800)
df = pd.DataFrame([{
"dt": b.datetime, "open": b.open, "high": b.high,
"low": b.low, "close": b.close, "vol": b.vol, "amount": b.amount,
} for b in bars])
return df.set_index("dt")
长驻服务(FastAPI)
!!! danger "不要每次请求都新建 TdxData" 池与缓存都挂在实例上,每请求新建 = 每请求重建连接池 + 缓存全部失效。
from contextlib import asynccontextmanager
from pathlib import Path
from fastapi import FastAPI, Request
@asynccontextmanager
async def lifespan(app: FastAPI):
async with TdxData(cache_dir=Path("./tdx_cache"), pool_min=4, pool_max=16) as td:
app.state.td = td
yield
app = FastAPI(lifespan=lifespan)
@app.get("/kline/{symbol}")
async def kline(symbol: str, request: Request):
td = request.app.state.td
bars = await td.get_bars(symbol, KlinePeriod.DAY, count=30)
return [{"dt": str(b.datetime), "close": b.close} for b in bars]