jack/Chan
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: multi-symbol support and per-tf start_time in data_provider

Browse Source
This commit is contained in:
jackyu66git
2026-05-13 18:34:39 +08:00
parent d8e3cdd9e9
commit 0dd8f8a585
2 changed files with 739 additions and 66 deletions
Download Patch File Download Diff File Expand all files Collapse all files
data_provider/main.py
+717 -57
View File
@@ -19,6 +19,7 @@ import ccxt # type: ignore
import pandas as pd # type: ignore
from fastapi import FastAPI, HTTPException, Query, WebSocket, WebSocketDisconnect
from fastapi.middleware.cors import CORSMiddleware
from fastapi.responses import HTMLResponse
import uvicorn
from technical.util import resample_to_interval
@@ -35,6 +36,10 @@ TIMEFRAME_TO_MS: Dict[str, int] = {
"1d": 86_400_000,
"1w": 604_800_000,
}
# 内存最大缓存的 K 线数量（超出部分从 CSV 按需读取，不限制则不限量）
MAX_CANDLES_IN_MEMORY: Dict[str, int] = {
"1m": 129_600, # 3 个月（3 * 30 * 24 * 60）
}
# 每个基础周期可派生出的合成周期列表（由该基础周期 K 线 resample 得到）
DERIVED_TIMEFRAME_PLAN: Dict[str, List[str]] = {
"1m": ["2m", "3m", "4m", "5m", "10m", "15m", "20m", "25m", "30m", "45m"],
@@ -213,6 +218,14 @@ class DataProvider:
if start is None:
raise ValueError("配置文件必须包含 start_time 字段")
self.start_time_ms: int = start
# 按周期独立 start_time（从 start_time_per_tf 字段读取），未配置则回退到全局 start_time
self.start_time_map: Dict[str, int] = {}
start_per_tf = self.config.get("start_time_per_tf", {})
if isinstance(start_per_tf, dict):
for tf, ts_str in start_per_tf.items():
tf_start = parse_timestamp(ts_str)
if tf_start is not None:
self.start_time_map[tf] = tf_start
self.exchange = self._init_exchange()
self.data: Dict[str, Dict[str, List[Dict[str, float]]]] = {
symbol: {tf: [] for tf in self.timeframes} for symbol in self.symbols
@@ -236,6 +249,8 @@ class DataProvider:
self._stop_event = threading.Event()
self._fetch_thread: Optional[threading.Thread] = None
self._persist_thread: Optional[threading.Thread] = None
self._backfill_thread: Optional[threading.Thread] = None
self._cold_start_done = False
# 记录断线后需要从哪个 since 重新拉取（symbol -> timeframe -> since_ms）
self._resume_since: Dict[str, Dict[str, int]] = {}
# 恢复点持久化文件
@@ -270,6 +285,10 @@ class DataProvider:
unique.append(item)
return unique
def _get_start_time(self, timeframe: str) -> int:
"""获取指定周期的 start_time（毫秒）。优先使用 start_time_per_tf，否则回退全局。"""
return self.start_time_map.get(timeframe, self.start_time_ms)
def _validate_timeframes(self, configured: Optional[Iterable[str]]) -> List[str]:
"""校验周期在允许集合内；未配置则默认 TIMEFRAME_ORDER 全部；顺序优先按 TIMEFRAME_ORDER。"""
if not configured:
@@ -348,6 +367,19 @@ class DataProvider:
logger.debug("时间周期 %s 合并后K线数量: %s", timeframe, len(ordered))
return ordered
def _trim(self, symbol: str, timeframe: str) -> None:
"""将内存缓存裁剪到 MAX_CANDLES_IN_MEMORY 上限（全量数据已在 CSV 中）。"""
max_count = MAX_CANDLES_IN_MEMORY.get(timeframe)
if max_count is None:
return
sym_data = self.data.get(symbol)
if sym_data is None:
return
candles = sym_data.get(timeframe)
if candles is None or len(candles) <= max_count:
return
sym_data[timeframe] = candles[-max_count:]
def _write_to_disk(self, symbol: str, timeframe: str, data: List[Dict[str, float]]) -> None:
"""先写临时文件再 replace，避免写入中断导致 CSV 损坏。"""
path = self._data_file_path(symbol, timeframe)
@@ -368,75 +400,159 @@ class DataProvider:
logger.info("交易对 %s 时间周期 %s 已写入磁盘 (%s 根K线)", symbol, timeframe, len(data))
def _fetch_history(self, symbol: str, timeframe: str, since_ms: int) -> List[List[float]]:
"""从 since_ms 分页拉取直到接近当前时间；遇限频则 sleep 重试。"""
"""从 since_ms 分页拉取直到接近当前时间。
当 since_ms 早于交易所数据保留期时，先从最新数据往回探测有效起点，
再向后分页补齐。"""
results: List[List[float]] = []
limit = 1500
now_ms = self.exchange.milliseconds()
tf_ms = TIMEFRAME_TO_MS[timeframe]
fetch_since = since_ms
# 先尝试直接拉取
first_batch = self._fetch_ohlcv_retry(symbol, timeframe, since=since_ms, limit=limit)
# 若返回空，或首根时间远晚于 since（交易所忽略了过老的 since），启用反向探测
gap_ms = tf_ms * limit * 2
first_skipped = (
not first_batch
or (first_batch[0][0] - since_ms > gap_ms and first_batch[-1][0] >= now_ms - tf_ms * 10)
)
if first_skipped:
logger.info("since 过老被交易所跳过，启用反向探测 %s %s (since=%s)", symbol, timeframe, to_utc_iso(since_ms))
# 反向探测：从当前时间往前翻页，找到实际最早可用的 K 线
all_collected: List[List[float]] = []
search_since = max(0, now_ms - tf_ms * limit)
search_rounds = 0
max_search = 200
earliest_ts = None
while search_rounds < max_search:
search_rounds += 1
batch = self._fetch_ohlcv_retry(symbol, timeframe, since=search_since, limit=limit)
if not batch:
break
all_collected = batch + all_collected
first_ts = batch[0][0]
if first_ts == search_since or first_ts <= since_ms:
earliest_ts = first_ts
break
search_since = max(0, first_ts - tf_ms * limit)
time.sleep(self.exchange.rateLimit / 1000 if self.exchange.rateLimit else 0.2)
if earliest_ts is None and all_collected:
earliest_ts = all_collected[0][0]
if earliest_ts is not None:
logger.info("反向探测找到最早 %s: %s (%s)", symbol, to_utc_iso(earliest_ts), timeframe)
# 用收集到的数据作为起点，继续向前分页到 now
results = all_collected
if results:
last_ts = results[-1][0]
if last_ts < now_ms - tf_ms:
extra = self._fetch_ohlcv_paginate(symbol, timeframe, last_ts + tf_ms, now_ms, limit)
results.extend(extra)
logger.info("交易对 %s 时间周期 %s 拉取历史K线数量: %s", symbol, timeframe, len(results))
return results
# 直接拉取成功，正常向后分页
results = list(first_batch)
last_ts = results[-1][0]
if last_ts < now_ms - tf_ms:
extra = self._fetch_ohlcv_paginate(symbol, timeframe, last_ts + tf_ms, now_ms, limit)
results.extend(extra)
logger.info("交易对 %s 时间周期 %s 拉取历史K线数量: %s", symbol, timeframe, len(results))
return results
def _fetch_ohlcv_retry(self, symbol: str, timeframe: str, since: int, limit: int) -> List[List[float]]:
"""带重试的单次 fetch_ohlcv，限频/网络错误时等待重试。"""
max_attempts = 5
for attempt in range(max_attempts):
try:
return self.exchange.fetch_ohlcv(symbol, timeframe=timeframe, since=since, limit=limit)
except ccxt.RateLimitExceeded as exc:
wait_s = (self.exchange.rateLimit / 1000 if self.exchange.rateLimit else 1) * (attempt + 1)
logger.warning("触发频率限制，等待 %.1fs: %s", wait_s, exc)
time.sleep(wait_s)
except ccxt.BaseError as exc:
logger.error("拉取K线失败 (%s, %s, since=%s): %s (attempt %s/%s)",
timeframe, symbol, since, exc, attempt + 1, max_attempts)
time.sleep(3 * (attempt + 1))
logger.error("拉取K线失败，已达最大重试次数: %s %s", symbol, timeframe)
return []
def _fetch_ohlcv_paginate(self, symbol: str, timeframe: str, start_ms: int, end_ms: int, limit: int) -> List[List[float]]:
"""从 start_ms 向后分页拉取到 end_ms。"""
results: List[List[float]] = []
tf_ms = TIMEFRAME_TO_MS[timeframe]
fetch_since = start_ms
max_rounds = 5000
rounds = 0
while fetch_since < now_ms and rounds < max_rounds:
while fetch_since < end_ms and rounds < max_rounds:
rounds += 1
try:
candles = self.exchange.fetch_ohlcv(
symbol,
timeframe=timeframe,
since=fetch_since,
limit=limit,
)
except ccxt.RateLimitExceeded as exc:
logger.warning("触发频率限制，等待: %s", exc)
time.sleep(self.exchange.rateLimit / 1000 if self.exchange.rateLimit else 1)
continue
except ccxt.BaseError as exc:
logger.error("拉取历史K线失败 (%s, %s): %s", timeframe, fetch_since, exc)
time.sleep(5)
continue
candles = self._fetch_ohlcv_retry(symbol, timeframe, since=fetch_since, limit=limit)
if not candles:
break
results.extend(candles)
last_ts = candles[-1][0]
fetch_since = last_ts + tf_ms
if last_ts >= now_ms - tf_ms:
if last_ts >= end_ms - tf_ms:
break
time.sleep(self.exchange.rateLimit / 1000 if self.exchange.rateLimit else 0.2)
logger.info("交易对 %s 时间周期 %s 拉取历史K线数量: %s", symbol, timeframe, len(results))
return results
def initialize(self) -> None:
"""阻塞式启动：加载本地、从倒数第二根或配置起点补历史、写盘并 set _ready。"""
logger.info("开始初始化数据提供商")
"""快速启动：仅加载本地 CSV 到内存，立即设 _ready 让服务可用。后台再补拉交易所数据。"""
logger.info("开始初始化数据提供商（仅加载本地数据）")
for symbol in self.symbols:
for timeframe in self.timeframes:
existing = self._load_local(symbol, timeframe)
with self._lock:
self.data.setdefault(symbol, {})[timeframe] = existing
self._trim(symbol, timeframe)
logger.info("交易对 %s 时间周期 %s 已加载本地K线: %s 根", symbol, timeframe, len(existing))
self._ready.set()
logger.info("数据初始化完成，服务已就绪（后台将补拉交易所数据）")
def _cold_start_backfill(self) -> None:
"""后台一次性回填：从交易所拉取每个 symbol/timeframe 的缺失历史，合并后写盘。"""
logger.info("开始后台回填交易所数据")
for symbol in self.symbols:
for timeframe in self.timeframes:
if self._stop_event.is_set():
return
with self._lock:
existing = list(self.data.get(symbol, {}).get(timeframe, []))
tf_ms = TIMEFRAME_TO_MS[timeframe]
last_ts = existing[-1]["timestamp"] if existing else None
# 计算 fetch_since：优先从数据末尾补，但若数据量极少
#（刷新线程抢先写入的少量近期数据），则回退到 start_time 做全量回填
if last_ts is not None:
if len(existing) >= 2:
# 从倒数第二根起拉，避免最后一根未收盘重复/缺口
fetch_since = existing[-2]["timestamp"]
if len(existing) > RECENT_CANDLE_LIMIT * 3:
# 已有足够历史数据，仅增量补拉
fetch_since = (existing[-2]["timestamp"] if len(existing) >= 2
else max(0, existing[-1]["timestamp"] - tf_ms))
else:
fetch_since = max(0, last_ts - tf_ms)
# 只有刷新线程抢先写入的少量数据，从 start_time 全量回填
fetch_since = self._get_start_time(timeframe)
logger.info("数据量不足 (%s 根)，从 start_time 回填 %s %s",
len(existing), symbol, timeframe)
else:
fetch_since = self.start_time_ms
logger.debug(
"初始化拉取参数",
extra={
"symbol": symbol,
"timeframe": timeframe,
"existing_last": last_ts,
"fetch_since": fetch_since,
"tf_ms": tf_ms,
},
)
history = self._fetch_history(symbol, timeframe, fetch_since)
merged = self._merge_candles(timeframe, existing, history)
with self._lock:
self.data.setdefault(symbol, {})[timeframe] = merged
self._write_to_disk(symbol, timeframe, merged)
self._ready.set()
logger.info("数据初始化完成")
fetch_since = self._get_start_time(timeframe)
try:
history = self._fetch_history(symbol, timeframe, fetch_since)
# 再次读取最新数据后合并，避免覆盖并发刷新线程写入的更新
with self._lock:
current = list(self.data.get(symbol, {}).get(timeframe, []))
merged = self._merge_candles(timeframe, current, history)
self.data[symbol][timeframe] = merged
self._write_to_disk(symbol, timeframe, merged)
self._trim(symbol, timeframe)
self._notify_update(symbol, timeframe)
logger.info("回填完成 %s %s: +%s 根新K线", symbol, timeframe, len(history))
except Exception as exc:
logger.error("回填失败 %s %s: %s", symbol, timeframe, exc)
self._set_resume_since(symbol, timeframe, fetch_since)
logger.info("后台回填全部完成")
self._cold_start_done = True
def resample_df(self, df: pd.DataFrame, interval: int) -> pd.DataFrame:
"""将基础周期 DataFrame 聚合为 interval 分钟周期（freqtrade technical.util）。"""
@@ -549,23 +665,28 @@ class DataProvider:
logger.error("数据更新回调异常: %s", exc)
def start_background_workers(self) -> None:
"""启动增量刷新线程与周期性落盘线程。"""
if self._fetch_thread and self._fetch_thread.is_alive():
return
"""启动后台线程：冷启动回填、增量刷新、周期性落盘。"""
self._stop_event.clear()
self._backfill_thread = threading.Thread(target=self._cold_start_backfill, name="backfill-loop", daemon=True)
self._fetch_thread = threading.Thread(target=self._refresh_loop, name="refresh-loop", daemon=True)
self._persist_thread = threading.Thread(target=self._persist_loop, name="persist-loop", daemon=True)
self._backfill_thread.start()
self._fetch_thread.start()
self._persist_thread.start()
logger.info("后台线程已启动")
logger.info("后台线程已启动（回填 + 增量刷新 + 落盘）")
def stop(self) -> None:
"""停止后台线程（应用关闭时 lifespan finally 调用）。"""
self._stop_event.set()
if self._fetch_thread:
self._fetch_thread.join(timeout=5)
if self._persist_thread:
self._persist_thread.join(timeout=5)
for thread, name in [
(self._backfill_thread, "backfill"),
(self._fetch_thread, "fetch"),
(self._persist_thread, "persist"),
]:
if thread:
thread.join(timeout=5)
if thread.is_alive():
logger.warning("后台线程 %s 未能在 5s 内结束", name)
logger.info("数据提供商已停止")
def _refresh_loop(self) -> None:
@@ -591,6 +712,7 @@ class DataProvider:
self.data[symbol][timeframe] = merged
self._notify_update(symbol, timeframe)
self._clear_resume_since(symbol, timeframe)
self._trim(symbol, timeframe)
else:
# 正常增量获取最近若干根K线
candles = self.exchange.fetch_ohlcv(
@@ -605,6 +727,7 @@ class DataProvider:
merged = self._merge_candles(timeframe, current, candles)
self.data[symbol][timeframe] = merged
self._notify_update(symbol, timeframe)
self._trim(symbol, timeframe)
except ccxt.BaseError as exc:
logger.error("更新最新K线失败 (%s %s): %s", symbol, timeframe, exc)
# 记录应当从何时恢复拉取，避免重连后从当前时间开始导致丢K
@@ -613,10 +736,10 @@ class DataProvider:
if current:
last_ts = int(current[-1]["timestamp"])
else:
last_ts = self.start_time_ms
last_ts = self._get_start_time(timeframe)
tf_ms = TIMEFRAME_TO_MS[timeframe]
# 回退一个周期，确保包含可能未完全收盘的K线，去重由 _merge_candles 处理
since_ms = max(self.start_time_ms, last_ts - tf_ms)
since_ms = max(self._get_start_time(timeframe), last_ts - tf_ms)
self._set_resume_since(symbol, timeframe, since_ms)
time.sleep(2)
continue
@@ -629,7 +752,7 @@ class DataProvider:
self._persist_all()
def _persist_all(self) -> None:
"""在锁内复制 data 后落盘，避免长时间持锁。"""
"""在锁内复制 data 后落盘，避免长时间持锁。有限制的时间周期跳过不写（CSV 已有全量历史）。"""
if not self._ready.is_set():
return
with self._lock:
@@ -639,6 +762,8 @@ class DataProvider:
}
for symbol, tf_map in snapshot.items():
for timeframe, data in tf_map.items():
if timeframe in MAX_CANDLES_IN_MEMORY:
continue # 内存只有尾部 N 根，不覆盖 CSV 全量
self._write_to_disk(symbol, timeframe, data)
# 周期性也保存一次恢复点，保证一致性
self._save_resume_since()
@@ -663,9 +788,18 @@ class DataProvider:
end_ms: Optional[int],
limit: Optional[int],
) -> List[Dict[str, float]]:
"""从内存读取已缓存的基础周期 K 线并按时间/limit 裁剪。"""
"""从内存读取已缓存的基础周期 K 线并按时间/limit 裁剪；内存不足时从 CSV 补充。"""
with self._lock:
candles = list(self.data.get(symbol, {}).get(timeframe, []))
# 有限制的时间周期，若内存不够老则从 CSV 补充历史
if timeframe in MAX_CANDLES_IN_MEMORY and candles and start_ms is not None:
if start_ms < candles[0]["timestamp"]:
csv_candles = self._load_local(symbol, timeframe)
if csv_candles:
merged = {c["timestamp"]: c for c in csv_candles}
for c in candles:
merged[c["timestamp"]] = c
candles = sorted(merged.values(), key=lambda x: x["timestamp"])
if start_ms is not None:
candles = [row for row in candles if row["timestamp"] >= start_ms]
if end_ms is not None:
@@ -853,6 +987,532 @@ def create_app(provider: DataProvider) -> FastAPI:
"ready": provider.is_ready(),
}
@app.get("/api-manual", response_class=HTMLResponse)
async def api_manual():
"""数据服务 API 使用手册页面。"""
derived_plan = DERIVED_TIMEFRAME_PLAN
timeframe_ms = TIMEFRAME_TO_MS
memory_limits = MAX_CANDLES_IN_MEMORY
base_tfs = provider.timeframes
derived_tfs = provider.get_derived_timeframes()
all_tfs = provider.get_available_timeframes()
symbols = provider.symbols
# Build derived timeframe table rows
derived_rows = ""
for base, derived_list in derived_plan.items():
present = "✓" if base in base_tfs else "✗"
derived_rows += f"<tr><td><code>{base}</code></td><td>{present}</td><td>{', '.join(f'<code>{d}</code>' for d in derived_list)}</td></tr>"
# Build memory limits table rows
memory_rows = ""
for tf in base_tfs:
limit = memory_limits.get(tf)
if limit is None:
span = "unlimited"
elif tf == "1m":
span = f"{limit:,} candles (~3 months)"
elif tf == "1h":
span = f"{limit:,} candles (~1 year)"
else:
span = f"{limit:,} candles"
memory_rows += f"<tr><td><code>{tf}</code></td><td>{span}</td></tr>"
# Pre-build config JSON example to avoid f-string escaping issues
import json as _json
_config_obj = {
"exchange": "binance",
"symbols": ["BTC/USDT:USDT", "ETH/USDT:USDT"],
"start_time": "2024-01-01T00:00:00Z",
"start_time_per_tf": {"1m": "2026-01-01T00:00:00Z"},
"timeframes": ["1m", "1h", "1d", "1w"],
"data_dir": "./data",
}
config_example = _json.dumps(_config_obj, indent=2, ensure_ascii=False)
return f"""<!DOCTYPE html>
<html lang="zh-CN">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Data Provider — API Manual</title>
<link href="https://cdn.jsdelivr.net/npm/bootstrap@5.1.3/dist/css/bootstrap.min.css" rel="stylesheet">
<link href="https://cdn.jsdelivr.net/npm/bootstrap-icons@1.8.1/font/bootstrap-icons.css" rel="stylesheet">
<style>
body {{
font-family: "Helvetica Neue", Arial, "PingFang SC", "Microsoft YaHei", sans-serif;
background: #f8f9fa; color: #333; padding: 0;
}}
.hero {{
background: linear-gradient(135deg, #1a1a2e 0%, #16213e 50%, #0f3460 100%);
color: #fff; padding: 48px 0 40px; margin-bottom: 32px;
}}
.hero h1 {{ font-size: 2rem; font-weight: 700; margin: 0; }}
.hero .badge {{ font-size: 0.8rem; vertical-align: middle; margin-left: 10px; }}
.hero p {{ opacity: 0.85; margin: 8px 0 0; font-size: 0.95rem; }}
.nav-pills .nav-link {{ color: #495057; border-radius: 6px; padding: 6px 16px; font-size: 0.9rem; }}
.nav-pills .nav-link.active {{ background: #0d6efd; }}
.section {{ display: none; }}
.section.active {{ display: block; }}
.card {{ border: 1px solid #e9ecef; box-shadow: 0 1px 3px rgba(0,0,0,0.04); margin-bottom: 20px; }}
.card-header {{ background: #fff; border-bottom: 1px solid #e9ecef; font-weight: 600; font-size: 0.95rem; padding: 12px 18px; }}
pre {{ background: #1e1e2e; color: #cdd6f4; border-radius: 8px; padding: 16px; font-size: 0.85rem; line-height: 1.6; overflow-x: auto; }}
pre code {{ color: inherit; }}
.method-badge {{ display: inline-block; padding: 2px 8px; border-radius: 4px; font-size: 0.75rem; font-weight: 700; margin-right: 8px; width: 52px; text-align: center; }}
.method-GET {{ background: #d1fae5; color: #065f46; }}
.method-WS {{ background: #ede9fe; color: #5b21b6; }}
.endpoint-path {{ font-family: monospace; font-size: 0.9rem; }}
.table {{ font-size: 0.875rem; }}
.table code {{ background: #f1f3f5; padding: 1px 5px; border-radius: 3px; font-size: 0.82rem; }}
.status-ready {{ color: #198754; }}
.status-notready {{ color: #dc3545; }}
.param-required {{ color: #dc3545; font-weight: 600; }}
.toc-item {{ cursor: pointer; }}
footer {{ border-top: 1px solid #dee2e6; margin-top: 48px; padding: 20px 0; color: #868e96; font-size: 0.85rem; text-align: center; }}
.endpoint-card {{ border-left: 3px solid #0d6efd; }}
.endpoint-card.ws {{ border-left-color: #7c3aed; }}
</style>
</head>
<body>
<div class="hero">
<div class="container">
<h1>Data Provider <span class="badge bg-success">v1.0.0</span></h1>
<p>Cryptocurrency OHLCV data microservice — REST + WebSocket API for candlestick (K-line) data</p>
<p style="font-size:0.82rem; opacity:0.7;">Exchange: {provider.exchange_name} &middot; Symbols: {len(symbols)} &middot; Timeframes: {len(all_tfs)} &middot; Status: <span class="{'status-ready' if provider.is_ready() else 'status-notready'}">{'Ready' if provider.is_ready() else 'Initializing…'}</span></p>
</div>
</div>
<div class="container" style="max-width: 960px;">
<!-- Tabs -->
<ul class="nav nav-pills mb-4" id="manualTabs" role="tablist">
<li class="nav-item"><button class="nav-link active" data-section="overview">Overview</button></li>
<li class="nav-item"><button class="nav-link" data-section="rest">REST API</button></li>
<li class="nav-item"><button class="nav-link" data-section="ws">WebSocket</button></li>
<li class="nav-item"><button class="nav-link" data-section="timeframes">Timeframes</button></li>
<li class="nav-item"><button class="nav-link" data-section="config">Configuration</button></li>
<li class="nav-item"><button class="nav-link" data-section="examples">Code Examples</button></li>
</ul>
<!-- ==================== OVERVIEW ==================== -->
<div class="section active" id="section-overview">
<div class="card">
<div class="card-header">What is Data Provider?</div>
<div class="card-body">
<p><strong>Data Provider</strong> is a standalone microservice that fetches, caches, and serves cryptocurrency OHLCV (Open/High/Low/Close/Volume) candlestick data from the Binance Futures exchange via CCXT.</p>
<p>It decouples data acquisition from analysis — consumers request historical or real-time market data through a simple REST or WebSocket API instead of talking to exchange APIs directly.</p>
<hr>
<h6>Key Features</h6>
<div class="row">
<div class="col-md-6">
<ul class="small">
<li>Fetches base OHLCV at <b>1m, 1h, 1d, 1w</b> from Binance</li>
<li>Synthesizes <b>{len(derived_tfs)} derived timeframes</b> by resampling</li>
<li>Dual storage: in-memory cache + CSV persistence</li>
<li>Background refresh every <b>{RECENT_FETCH_INTERVAL}s</b></li>
</ul>
</div>
<div class="col-md-6">
<ul class="small">
<li>REST endpoint at <code>/api/candles</code></li>
<li>WebSocket real-time push at <code>/ws</code></li>
<li>Automatic disconnect recovery</li>
<li>Fully Dockerized, single JSON config file</li>
</ul>
</div>
</div>
</div>
</div>
<div class="card">
<div class="card-header">Architecture</div>
<div class="card-body">
<pre style="background:#f8f9fa; color:#333; text-align:center; font-size:0.8rem; line-height:1.4;">
┌───────────────────────┐
│ Binance Futures │
│ (ccxt driver) │
└──────────┬────────────┘
│ fetch_ohlcv()
┌──────────┴────────────┐
│ DataProvider │
│ │
│ · In-memory cache │
│ · CSV persistence │
│ · Background refresh │
│ · Derived timeframe │
│ resample engine │
└──────┬────────┬────────┘
│ │
REST │ │ WebSocket
│ │
┌──────┴────────┴────────┐
│ Consumers (Flask app, │
│ browser, scripts…) │
└────────────────────────┘</pre>
</div>
</div>
<div class="card">
<div class="card-header">Endpoints at a Glance</div>
<div class="card-body p-0">
<table class="table table-hover mb-0">
<thead class="table-light"><tr><th>Method</th><th>Path</th><th>Description</th></tr></thead>
<tbody>
<tr><td><span class="method-badge method-GET">GET</span></td><td class="endpoint-path">/</td><td>Service info &amp; health summary</td></tr>
<tr><td><span class="method-badge method-GET">GET</span></td><td class="endpoint-path">/health</td><td>Structured health check (JSON)</td></tr>
<tr><td><span class="method-badge method-GET">GET</span></td><td class="endpoint-path">/timeframes</td><td>List available base &amp; derived timeframes</td></tr>
<tr><td><span class="method-badge method-GET">GET</span></td><td class="endpoint-path">/api/candles</td><td>Fetch OHLCV candles</td></tr>
<tr><td><span class="method-badge method-WS">WS</span></td><td class="endpoint-path">/ws</td><td>Real-time K-line streaming</td></tr>
<tr><td><span class="method-badge method-GET">GET</span></td><td class="endpoint-path">/api-manual</td><td>This page</td></tr>
</tbody>
</table>
</div>
</div>
<div class="card">
<div class="card-header">Data Model</div>
<div class="card-body">
<p class="small">Every candle object (REST response, WebSocket payload) has this structure:</p>
<table class="table table-bordered table-sm">
<thead class="table-light"><tr><th>Field</th><th>Type</th><th>Example</th></tr></thead>
<tbody>
<tr><td><code>timestamp</code></td><td>int</td><td><code>1704067200000</code></td></tr>
<tr><td><code>datetime</code></td><td>string</td><td><code>"2024-01-01T00:00:00Z"</code></td></tr>
<tr><td><code>open</code></td><td>float</td><td><code>42314.0</code></td></tr>
<tr><td><code>high</code></td><td>float</td><td><code>44266.0</code></td></tr>
<tr><td><code>low</code></td><td>float</td><td><code>42207.9</code></td></tr>
<tr><td><code>close</code></td><td>float</td><td><code>44230.2</code></td></tr>
<tr><td><code>volume</code></td><td>float</td><td><code>206424.144</code></td></tr>
</tbody>
</table>
</div>
</div>
</div>
<!-- ==================== REST API ==================== -->
<div class="section" id="section-rest">
<h5 class="mb-3"><span class="method-badge method-GET">GET</span> /health</h5>
<div class="card endpoint-card">
<div class="card-body">
<p class="small">Health check — use <code>ready</code> to determine if the service finished cold-start initialization.</p>
<p><strong>Response</strong> <span class="text-muted small">200 OK</span></p>
<pre><code>{{
"status": "ok",
"exchange": "binance",
"symbols": ["BTC/USDT:USDT", "ETH/USDT:USDT"],
"base_timeframes": ["1m", "1h", "1d", "1w"],
"derived_timeframes": ["2m","3m","4m","5m",...],
"timeframes": ["1m","2m","3m",...],
"ready": true
}}</code></pre>
<button class="btn btn-sm btn-outline-secondary" onclick="fetch('/health').then(r=>r.json()).then(d=>alert(JSON.stringify(d,null,2)))">Try it</button>
</div>
</div>
<h5 class="mb-3 mt-4"><span class="method-badge method-GET">GET</span> /api/candles</h5>
<div class="card endpoint-card">
<div class="card-body">
<p class="small">The primary data endpoint. Returns OHLCV candlestick data for a given symbol and timeframe.</p>
<p><strong>Query Parameters</strong></p>
<table class="table table-bordered table-sm">
<thead class="table-light"><tr><th>Param</th><th>Type</th><th>Required</th><th>Default</th><th>Description</th></tr></thead>
<tbody>
<tr><td><code>symbol</code></td><td>string</td><td><span class="param-required">Yes</span></td><td>—</td><td>Trading pair, e.g. <code>BTC/USDT:USDT</code></td></tr>
<tr><td><code>tf</code></td><td>string</td><td>No</td><td><code>1m</code></td><td>Timeframe — any base or derived</td></tr>
<tr><td><code>start</code></td><td>int</td><td>No</td><td>—</td><td>Start time, UTC milliseconds</td></tr>
<tr><td><code>end</code></td><td>int</td><td>No</td><td>—</td><td>End time, UTC milliseconds</td></tr>
<tr><td><code>limit</code></td><td>int</td><td>No</td><td>—</td><td>Max candles to return</td></tr>
</tbody>
</table>
<p><strong>Response</strong> <span class="text-muted small">200 OK — array of candle objects</span></p>
<pre><code>[
{{
"timestamp": 1704067200000,
"datetime": "2024-01-01T00:00:00Z",
"open": 42314.0,
"high": 44266.0,
"low": 42207.9,
"close": 44230.2,
"volume": 206424.144
}}
]</code></pre>
<p class="small text-muted">At least one of <code>start</code>/<code>end</code> or <code>limit</code> should be provided. If none given, all in-memory candles are returned (subject to memory limits).</p>
</div>
</div>
<h5 class="mb-3 mt-4"><span class="method-badge method-GET">GET</span> /timeframes</h5>
<div class="card endpoint-card">
<div class="card-body">
<p class="small">Lists all available timeframes: base (fetched from exchange) and derived (synthesized by resampling).</p>
<pre><code>{{
"base_timeframes": ["1m","1h","1d","1w"],
"derived_timeframes": ["2m","3m","4m","5m",...],
"timeframes": ["1m","2m","3m",...]
}}</code></pre>
</div>
</div>
<h5 class="mb-3 mt-4"><span class="method-badge method-GET">GET</span> /</h5>
<div class="card endpoint-card">
<div class="card-body">
<p class="small">Root endpoint — returns service name, exchange, symbols, timeframes, and ready status. Same data as <code>/health</code>.</p>
</div>
</div>
</div>
<!-- ==================== WEBSOCKET ==================== -->
<div class="section" id="section-ws">
<div class="card endpoint-card ws">
<div class="card-header"><span class="method-badge method-WS">WS</span> /ws — Real-time K-line Streaming</div>
<div class="card-body">
<p class="small">Connect to receive live incremental candle updates. Subscribe to specific symbol/timeframe pairs; receive a full snapshot followed by real-time push.</p>
<h6 class="mt-3">Connection URL</h6>
<pre><code>ws://localhost:80/ws</code></pre>
<p class="small text-muted">Replace <code>localhost:80</code> with the server address if connecting remotely.</p>
<h6 class="mt-3">Client → Server Messages</h6>
<table class="table table-bordered table-sm">
<thead class="table-light"><tr><th>Action</th><th>Payload</th><th>Description</th></tr></thead>
<tbody>
<tr>
<td><code>subscribe</code></td>
<td><pre style="margin:0;padding:4px 8px;font-size:0.78rem;"><code>{{"action":"subscribe","symbol":"BTC/USDT:USDT","timeframe":"1m"}}</code></pre></td>
<td>Subscribe to a symbol/timeframe. Server replies with <code>subscribed</code>, then a <code>snapshot</code> of recent candles.</td>
</tr>
<tr>
<td><code>unsubscribe</code></td>
<td><pre style="margin:0;padding:4px 8px;font-size:0.78rem;"><code>{{"action":"unsubscribe","symbol":"BTC/USDT:USDT","timeframe":"1m"}}</code></pre></td>
<td>Stop receiving updates for this pair.</td>
</tr>
<tr>
<td><code>ping</code></td>
<td><pre style="margin:0;padding:4px 8px;font-size:0.78rem;"><code>{{"action":"ping"}}</code></pre></td>
<td>Keepalive ping. Server replies with <code>pong</code>.</td>
</tr>
</tbody>
</table>
<h6 class="mt-3">Server → Client Messages</h6>
<table class="table table-bordered table-sm">
<thead class="table-light"><tr><th>Type</th><th>Description</th></tr></thead>
<tbody>
<tr><td><code>subscribed</code></td><td>Confirms subscription: <code>{{"type":"subscribed","symbol":"...","timeframe":"..."}}</code></td></tr>
<tr><td><code>snapshot</code></td><td>Full recent candles on subscribe: <code>{{"type":"snapshot","symbol":"...","timeframe":"...","data":[...]}}</code></td></tr>
<tr><td><code>kline</code></td><td>Incremental candle updates (last 2 candles): <code>{{"type":"kline","symbol":"...","timeframe":"...","data":[...]}}</code></td></tr>
<tr><td><code>pong</code></td><td>Ping response.</td></tr>
<tr><td><code>unsubscribed</code></td><td>Unsubscribe confirmation.</td></tr>
<tr><td><code>error</code></td><td>Error message: <code>{{"type":"error","message":"..."}}</code></td></tr>
</tbody>
</table>
<h6 class="mt-3">Python Client Example</h6>
<pre><code>import asyncio, json
import websockets
async def listen():
async with websockets.connect("ws://localhost:80/ws") as ws:
# Subscribe to BTC 1m candles
await ws.send(json.dumps({{
"action": "subscribe",
"symbol": "BTC/USDT:USDT",
"timeframe": "1m"
}}))
while True:
msg = json.loads(await ws.recv())
print(f"[{{msg['type']}}] {{msg.get('symbol','')}} {{msg.get('timeframe','')}}")
if msg['type'] == 'kline':
for candle in msg.get('data', []):
print(f" o={{candle['open']}} h={{candle['high']}} "
f"l={{candle['low']}} c={{candle['close']}}")
asyncio.run(listen())</code></pre>
<p class="small text-muted">Requires: <code>pip install websockets</code>. Subscribe to multiple symbol/timeframe pairs by sending additional subscribe messages.</p>
</div>
</div>
</div>
<!-- ==================== TIMEFRAMES ==================== -->
<div class="section" id="section-timeframes">
<div class="card">
<div class="card-header">Base & Derived Timeframes</div>
<div class="card-body">
<p class="small"><strong>Base</strong> timeframes are fetched directly from the exchange. <strong>Derived</strong> timeframes are synthesized on-the-fly by aggregating base candles — no extra API calls needed.</p>
</div>
<div class="card-body p-0">
<table class="table table-hover mb-0">
<thead class="table-light"><tr><th>Base Timeframe</th><th>Configured</th><th>Derived Timeframes Synthesized</th></tr></thead>
<tbody>{derived_rows}</tbody>
</table>
</div>
</div>
<div class="card">
<div class="card-header">Memory Limits</div>
<div class="card-body">
<p class="small">To bound memory usage, only a sliding window is held in RAM for high-frequency timeframes. Data beyond the window is served from CSV on disk lazily.</p>
</div>
<div class="card-body p-0">
<table class="table table-hover mb-0">
<thead class="table-light"><tr><th>Timeframe</th><th>Max Candles in Memory</th></tr></thead>
<tbody>{memory_rows}</tbody>
</table>
</div>
</div>
<div class="card">
<div class="card-header">CSV Storage</div>
<div class="card-body">
<p class="small">Data is persisted under <code>data/&lt;timeframe&gt;/</code> as one CSV file per symbol (e.g. <code>data/1m/BTC_USDT_USDT.csv</code>). Schema: <code>timestamp,datetime,open,high,low,close,volume</code>.</p>
</div>
</div>
</div>
<!-- ==================== CONFIGURATION ==================== -->
<div class="section" id="section-config">
<div class="card">
<div class="card-header">config.json</div>
<div class="card-body">
<pre><code>{config_example}</code></pre>
</div>
<div class="card-body p-0">
<table class="table table-hover mb-0">
<thead class="table-light"><tr><th>Field</th><th>Type</th><th>Description</th></tr></thead>
<tbody>
<tr><td><code>exchange</code></td><td>string</td><td>CCXT exchange ID. Tested with <code>binance</code> (Binance Futures).</td></tr>
<tr><td><code>symbols</code></td><td>string[]</td><td>Trading pairs in Binance Futures format: <code>BTC/USDT:USDT</code>. Also accepts comma-separated string.</td></tr>
<tr><td><code>start_time</code></td><td>string</td><td>Global earliest backfill date, ISO 8601 UTC. Used as fallback for timeframes not listed in <code>start_time_per_tf</code>.</td></tr>
<tr><td><code>start_time_per_tf</code></td><td>object</td><td><em>Optional.</em> Per-timeframe override. Keys are timeframe strings (e.g. <code>"1m"</code>), values are ISO 8601 UTC dates. Useful for limiting high-frequency data volume (e.g. 1m from recent date, longer timeframes from earlier).</td></tr>
<tr><td><code>timeframes</code></td><td>string[]</td><td>Base timeframes to fetch. Supported: <code>1m</code>, <code>1h</code>, <code>1d</code>, <code>1w</code>.</td></tr>
<tr><td><code>data_dir</code></td><td>string</td><td>Directory for CSV storage (created if missing).</td></tr>
</tbody>
</table>
</div>
</div>
<div class="card">
<div class="card-header">Environment Variables</div>
<div class="card-body p-0">
<table class="table table-hover mb-0">
<thead class="table-light"><tr><th>Variable</th><th>Default</th><th>Description</th></tr></thead>
<tbody>
<tr><td><code>CONFIG_PATH</code></td><td><code>config.json</code></td><td>Path to the JSON config file.</td></tr>
<tr><td><code>UVICORN_HOST</code></td><td><code>0.0.0.0</code></td><td>Host to bind.</td></tr>
<tr><td><code>UVICORN_PORT</code></td><td><code>80</code></td><td>Port to bind.</td></tr>
<tr><td><code>UVICORN_LOG_LEVEL</code></td><td><code>info</code></td><td>Log level: <code>debug</code>, <code>info</code>, <code>warning</code>, <code>error</code>.</td></tr>
</tbody>
</table>
</div>
</div>
</div>
<!-- ==================== EXAMPLES ==================== -->
<div class="section" id="section-examples">
<div class="card">
<div class="card-header">cURL — Fetch Last 500 5-Minute Candles</div>
<div class="card-body">
<pre><code>curl "http://localhost:80/api/candles?symbol=BTC/USDT:USDT&tf=5m&limit=500"</code></pre>
</div>
</div>
<div class="card">
<div class="card-header">cURL — Fetch Date Range</div>
<div class="card-body">
<pre><code># 4-hour candles for ETH, Jan–Mar 2024
curl "http://localhost:80/api/candles?symbol=ETH/USDT:USDT&tf=4h&start=1704067200000&end=1711929600000"</code></pre>
</div>
</div>
<div class="card">
<div class="card-header">Python — requests</div>
<div class="card-body">
<pre><code>import requests
# Check service is ready
resp = requests.get("http://localhost:80/health")
meta = resp.json()
print(f"Ready: {{meta['ready']}}")
# Fetch candles
params = {{
"symbol": "BTC/USDT:USDT",
"tf": "1h",
"limit": 200,
}}
resp = requests.get("http://localhost:80/api/candles", params=params)
candles = resp.json()
for c in candles[:3]:
print(c["datetime"], c["open"], c["close"])</code></pre>
</div>
</div>
<div class="card">
<div class="card-header">JavaScript — WebSocket</div>
<div class="card-body">
<pre><code>const ws = new WebSocket("ws://localhost:80/ws");
ws.onopen = () => {{
ws.send(JSON.stringify({{
action: "subscribe",
symbol: "BTC/USDT:USDT",
timeframe: "1m"
}}));
}};
ws.onmessage = (event) => {{
const msg = JSON.parse(event.data);
if (msg.type === "snapshot") {{
console.log("Initial data:", msg.data.length, "candles");
}} else if (msg.type === "kline") {{
console.log("Update:", msg.data);
}}
}};
// Keepalive every 30s
setInterval(() => ws.send(JSON.stringify({{action: "ping"}})), 30000);</code></pre>
</div>
</div>
<div class="card">
<div class="card-header">JavaScript — fetch (browser)</div>
<div class="card-body">
<pre><code>const params = new URLSearchParams({{
symbol: "BTC/USDT:USDT",
tf: "5m",
limit: "500"
}});
const resp = await fetch(`/api/candles?${{params}}`);
const candles = await resp.json();
console.log(`Got ${{candles.length}} candles`);</code></pre>
</div>
</div>
</div>
<footer>
Data Provider v1.0.0 &middot; Chan Project &middot; Served from {provider.exchange_name}
</footer>
</div>
<script>
// Simple tab switcher
document.querySelectorAll('#manualTabs .nav-link').forEach(btn => {{
btn.addEventListener('click', () => {{
document.querySelectorAll('#manualTabs .nav-link').forEach(b => b.classList.remove('active'));
document.querySelectorAll('.section').forEach(s => s.classList.remove('active'));
btn.classList.add('active');
document.getElementById('section-' + btn.dataset.section).classList.add('active');
}});
}});
</script>
</body>
</html>"""
@app.websocket("/ws")
async def websocket_endpoint(ws: WebSocket):
"""WebSocket 实时 K 线推送。
@@ -937,7 +1597,7 @@ app = build_app()
def main() -> None:
"""直接运行本模块时启动 uvicorn（监听 UVICORN_HOST / UVICORN_PORT）。"""
host = os.getenv("UVICORN_HOST", "0.0.0.0")
port = int(os.getenv("UVICORN_PORT", "9009"))
port = int(os.getenv("UVICORN_PORT", "80"))
uvicorn.run(app, host=host, port=port, log_level=os.getenv("UVICORN_LOG_LEVEL", "info"))