503 lines
20 KiB
Python
503 lines
20 KiB
Python
"""南方基金指定产品行情模块。"""
|
||
# Public-source adapter retains readable request expressions; line-length checks are not useful here.
|
||
# ruff: noqa: E501
|
||
from __future__ import annotations
|
||
|
||
import logging
|
||
import re
|
||
import time
|
||
from datetime import date, datetime
|
||
from datetime import time as clock_time
|
||
from html import unescape
|
||
from typing import Any
|
||
|
||
import httpx
|
||
|
||
logger = logging.getLogger(__name__)
|
||
|
||
NAV_API = "https://api.fund.eastmoney.com/f10/lsjz"
|
||
RETURN_API = "https://api.fund.eastmoney.com/pinzhong/LJSYLZS"
|
||
QUOTE_API = "https://push2.eastmoney.com/api/qt/ulist.np/get"
|
||
TENCENT_QUOTE_API = "https://qt.gtimg.cn/q="
|
||
DETAIL_API = "https://fund.eastmoney.com/pingzhongdata/{code}.js"
|
||
SOUTHERN_COMPANY_API = "https://fund.eastmoney.com/company/80000220.html"
|
||
REQUEST_TIMEOUT = 12.0
|
||
MAX_FUNDS_PER_CALL = 1000
|
||
FUND_TYPE_GROUPS = {
|
||
"货币型": ("202308", "020480", "511810"),
|
||
"债券型": ("007161", "003776", "020281", "511070", "159700", "160128", "160129"),
|
||
"混合型": ("018019", "014189", "018020", "160105", "160142", "160143", "501062"),
|
||
"股票型": (
|
||
"020553", "016449", "008854", "008264", "008736", "010592", "160127", "588890",
|
||
"020839", "589700", "159382", "159511", "002900", "021958", "159948", "009059",
|
||
"001421", "510500",
|
||
),
|
||
"QDII": ("501018", "159329", "159615", "159687"),
|
||
}
|
||
SOUTHERN_FUND_CODES = tuple(
|
||
dict.fromkeys(code for codes in FUND_TYPE_GROUPS.values() for code in codes)
|
||
)
|
||
FUND_TYPE_BY_CODE = {
|
||
code: fund_type for fund_type, codes in FUND_TYPE_GROUPS.items() for code in codes
|
||
}
|
||
HEADERS = {"User-Agent": "Mozilla/5.0", "Referer": "https://fund.eastmoney.com/"}
|
||
_history_date: str | None = None
|
||
_history_cache: dict[str, dict[str, str | None]] = {}
|
||
_name_cache: dict[str, str] = {}
|
||
|
||
|
||
class ExchangeQuoteSourceError(RuntimeError):
|
||
"""A public exchange quote provider could not supply a usable response."""
|
||
|
||
|
||
def is_market_trading_time(now: datetime | None = None) -> bool:
|
||
"""判断中国大陆工作日盘中时段。"""
|
||
current = now or datetime.now()
|
||
if current.weekday() >= 5:
|
||
return False
|
||
current_time = current.time()
|
||
return (clock_time(9, 30) <= current_time <= clock_time(11, 30)
|
||
or clock_time(13, 0) <= current_time <= clock_time(15, 0))
|
||
|
||
|
||
def get_southern_fund_market(
|
||
target_date: str | None = None,
|
||
limit: int | None = None,
|
||
fund_type: str | None = None,
|
||
fund_codes: list[str] | tuple[str, ...] | None = None,
|
||
) -> list[dict[str, Any]]:
|
||
"""获取指定南方基金的完整行情表。
|
||
|
||
每次调用刷新整张表的实时行情；历史收益同一日期只请求一次并保存在进程缓存。
|
||
limit 不传时返回 SOUTHERN_FUND_CODES 中的全部产品。
|
||
"""
|
||
query_date = target_date or date.today().isoformat()
|
||
date.fromisoformat(query_date)
|
||
if fund_type and fund_type not in FUND_TYPE_GROUPS:
|
||
raise ValueError("基金类型不在南方基金白名单内")
|
||
available_codes = FUND_TYPE_GROUPS[fund_type] if fund_type else SOUTHERN_FUND_CODES
|
||
if fund_codes is not None:
|
||
requested = tuple(dict.fromkeys(fund_codes))
|
||
if any(code not in SOUTHERN_FUND_CODES for code in requested):
|
||
raise ValueError("基金代码不在南方基金白名单内")
|
||
available_codes = tuple(code for code in requested if code in available_codes)
|
||
count = len(available_codes) if limit is None else min(max(limit, 1), MAX_FUNDS_PER_CALL)
|
||
codes = list(available_codes[:count])
|
||
names = _get_names(codes)
|
||
history = _get_history(codes, query_date)
|
||
quotes = _get_quotes(codes) if is_market_trading_time() else {}
|
||
now = time.strftime("%Y-%m-%d")
|
||
rows = []
|
||
for code in codes:
|
||
old = history.get(code, {})
|
||
live = quotes.get(code, {})
|
||
rows.append({
|
||
"基金代码": code, "基金名称": names.get(code, f"南方基金 {code}"),
|
||
"基金类型": FUND_TYPE_BY_CODE.get(code, "未分类"),
|
||
"基金净值": live.get("基金净值") or old.get("基金净值"),
|
||
"日期": live.get("日期") or old.get("日期"),
|
||
"日涨幅": live.get("日涨幅") or old.get("日涨幅"),
|
||
"最近半年": old.get("最近半年"), "最近一年": old.get("最近一年"),
|
||
"今年以来": old.get("今年以来"), "成立以来": old.get("成立以来"),
|
||
"行情时间": now,
|
||
"行情来源": "盘中实时行情" if live.get("基金净值") else "收盘后最新净值",
|
||
"是否盘中": is_market_trading_time(),
|
||
})
|
||
return rows
|
||
|
||
|
||
def get_southern_fund_nav_history(
|
||
fund_code: str, start_date: str, end_date: str
|
||
) -> list[dict[str, str]]:
|
||
"""Return validated historical unit-NAV observations for an allowed fund."""
|
||
if fund_code not in SOUTHERN_FUND_CODES:
|
||
raise ValueError("基金代码不在南方基金白名单内")
|
||
start = date.fromisoformat(start_date)
|
||
end = date.fromisoformat(end_date)
|
||
if start > end:
|
||
raise ValueError("开始日期不能晚于结束日期")
|
||
records = _fetch_nav_records(
|
||
fund_code, start_date=start.isoformat(), end_date=end.isoformat(), all_pages=True
|
||
)
|
||
observations: list[dict[str, str]] = []
|
||
for record in records:
|
||
value_date = str(record.get("FSRQ") or "")
|
||
nav = str(record.get("DWJZ") or "").strip()
|
||
try:
|
||
parsed_date = date.fromisoformat(value_date)
|
||
if parsed_date < start or parsed_date > end or float(nav) <= 0:
|
||
continue
|
||
except ValueError:
|
||
continue
|
||
observations.append({"fund_code": fund_code, "trade_date": value_date, "nav": nav})
|
||
return sorted(observations, key=lambda item: item["trade_date"])
|
||
|
||
|
||
def get_southern_fund_catalog(
|
||
fund_codes: list[str] | tuple[str, ...],
|
||
) -> list[dict[str, Any]]:
|
||
"""Return Southern Fund's public catalogue rows.
|
||
|
||
The company directory supplies fund type and reported asset scale, which are
|
||
needed to select test products. It is reference data only: product risk is
|
||
intentionally not inferred here because the source does not publish a
|
||
channel-independent R1-R5 suitability rating.
|
||
"""
|
||
requested = tuple(dict.fromkeys(fund_codes))
|
||
if not requested:
|
||
return []
|
||
response = httpx.get(SOUTHERN_COMPANY_API, headers=HEADERS, timeout=REQUEST_TIMEOUT)
|
||
response.raise_for_status()
|
||
content = response.content.decode("utf-8")
|
||
scale_as_of_date = _company_scale_as_of_date(content)
|
||
rows = []
|
||
for code in requested:
|
||
row = _company_catalog_row(content, code)
|
||
if row is not None:
|
||
row["scale_as_of_date"] = scale_as_of_date
|
||
rows.append(row)
|
||
return rows
|
||
|
||
|
||
def get_southern_exchange_catalog(
|
||
fund_codes: list[str] | tuple[str, ...],
|
||
) -> list[dict[str, Any]]:
|
||
"""Backward-compatible alias for callers that only request exchange codes."""
|
||
return get_southern_fund_catalog(fund_codes)
|
||
|
||
|
||
def _company_catalog_row(content: str, fund_code: str) -> dict[str, Any] | None:
|
||
marker = f'class="code">{fund_code}</a>'
|
||
position = content.find(marker)
|
||
if position < 0:
|
||
return None
|
||
start = content.rfind("<tr", 0, position)
|
||
end = content.find("</tr>", position)
|
||
if start < 0 or end < 0:
|
||
return None
|
||
row = content[start:end + len("</tr>")]
|
||
name_match = re.search(r'class="name" title="([^"]+)"', row)
|
||
cells = [
|
||
_html_cell_text(match.group(1))
|
||
for match in re.finditer(r"<td[^>]*>(.*?)</td>", row, flags=re.DOTALL)
|
||
]
|
||
if name_match is None or len(cells) < 10:
|
||
return None
|
||
return {
|
||
"fund_code": fund_code,
|
||
"fund_name": unescape(name_match.group(1)).strip(),
|
||
"fund_type": cells[2],
|
||
"nav_date": _catalog_nav_date(cells[3]),
|
||
"nav": cells[4],
|
||
"fund_asset_scale_billion": cells[9],
|
||
"trading_venue": cells[11] if len(cells) > 11 else "场内交易",
|
||
}
|
||
|
||
|
||
def _company_scale_as_of_date(content: str) -> str | None:
|
||
match = re.search(r"(?:数据截止|截止日期)[：:]\s*(20\d{2}-\d{2}-\d{2})", content)
|
||
return match.group(1) if match else None
|
||
|
||
|
||
def _catalog_nav_date(value: str) -> str | None:
|
||
match = re.fullmatch(r"(\d{2})-(\d{2})", value)
|
||
if match is None:
|
||
return None
|
||
return f"{date.today().year}-{match.group(1)}-{match.group(2)}"
|
||
|
||
|
||
def _html_cell_text(value: str) -> str:
|
||
return re.sub(r"\s+", " ", re.sub(r"<[^>]+>", "", unescape(value))).strip()
|
||
|
||
|
||
def _get_names(codes: list[str]) -> dict[str, str]:
|
||
for code in codes:
|
||
if code in _name_cache:
|
||
continue
|
||
try:
|
||
response = httpx.get(DETAIL_API.format(code=code), headers=HEADERS, timeout=REQUEST_TIMEOUT)
|
||
response.raise_for_status()
|
||
match = re.search(r"var\s+fS_name\s*=\s*[\"']([^\"']+)", response.text)
|
||
_name_cache[code] = match.group(1).strip() if match else f"南方基金 {code}"
|
||
except (httpx.HTTPError, UnicodeError) as exc:
|
||
logger.warning("基金名称接口失败 code=%s error=%s", code, type(exc).__name__)
|
||
_name_cache[code] = f"南方基金 {code}"
|
||
return {code: _name_cache.get(code, f"南方基金 {code}") for code in codes}
|
||
|
||
|
||
def _get_quotes(codes: list[str]) -> dict[str, dict[str, str | None]]:
|
||
secids = ",".join(("1." if code.startswith(("5", "6", "9")) else "0.") + code for code in codes)
|
||
try:
|
||
response = httpx.get(QUOTE_API, params={"fltt": 2, "invt": 2, "fields": "f12,f2,f3", "secids": secids}, headers=HEADERS, timeout=REQUEST_TIMEOUT)
|
||
response.raise_for_status()
|
||
items = ((response.json().get("data") or {}).get("diff") or [])
|
||
except (httpx.HTTPError, ValueError, TypeError) as exc:
|
||
logger.warning("实时行情接口失败 count=%s error=%s", len(codes), type(exc).__name__)
|
||
return {}
|
||
return {str(item["f12"]): {"基金净值": str(item["f2"]) if item.get("f2") not in (None, "-") else None, "日期": None, "日涨幅": f"{item.get('f3')}%" if item.get("f3") not in (None, "-") else None} for item in items if item.get("f12")}
|
||
|
||
|
||
def get_southern_exchange_quotes(
|
||
fund_codes: list[str] | tuple[str, ...],
|
||
) -> dict[str, dict[str, str | None]]:
|
||
"""Backward-compatible Eastmoney quote lookup that degrades to an empty result."""
|
||
try:
|
||
return fetch_southern_exchange_quotes_eastmoney(fund_codes)
|
||
except ExchangeQuoteSourceError as exc:
|
||
logger.warning("exchange quote endpoint failed error=%s", type(exc).__name__)
|
||
return {}
|
||
|
||
|
||
def fetch_southern_exchange_quotes_eastmoney(
|
||
fund_codes: list[str] | tuple[str, ...],
|
||
) -> dict[str, dict[str, str | None]]:
|
||
"""Return Eastmoney exchange quotes and raise on a provider-level failure."""
|
||
requested = tuple(dict.fromkeys(fund_codes))
|
||
if any(code not in SOUTHERN_FUND_CODES for code in requested):
|
||
raise ValueError("fund code is not in the Southern Fund whitelist")
|
||
if not requested:
|
||
return {}
|
||
secids = ",".join(
|
||
("1." if code.startswith(("5", "6", "9")) else "0.") + code for code in requested
|
||
)
|
||
try:
|
||
response = httpx.get(
|
||
QUOTE_API,
|
||
params={
|
||
"fltt": 2,
|
||
"invt": 2,
|
||
"fields": "f12,f2,f3,f5,f6,f17,f18",
|
||
"secids": secids,
|
||
},
|
||
headers=HEADERS,
|
||
timeout=REQUEST_TIMEOUT,
|
||
)
|
||
response.raise_for_status()
|
||
items = ((response.json().get("data") or {}).get("diff") or [])
|
||
except (httpx.HTTPError, ValueError, TypeError) as exc:
|
||
raise ExchangeQuoteSourceError("eastmoney quote request failed") from exc
|
||
|
||
def value(item: dict[str, Any], field: str) -> str | None:
|
||
raw = item.get(field)
|
||
return str(raw) if raw not in (None, "-") else None
|
||
|
||
return {
|
||
str(item["f12"]): {
|
||
"last_price": value(item, "f2"),
|
||
"change_pct": value(item, "f3"),
|
||
"volume": value(item, "f5"),
|
||
"turnover_amount": value(item, "f6"),
|
||
"open_price": value(item, "f17"),
|
||
"previous_close": value(item, "f18"),
|
||
}
|
||
for item in items
|
||
if item.get("f12")
|
||
}
|
||
|
||
|
||
def fetch_southern_exchange_quotes_tencent(
|
||
fund_codes: list[str] | tuple[str, ...],
|
||
) -> dict[str, dict[str, str | None]]:
|
||
"""Return Tencent Finance exchange quotes as an independent fallback source.
|
||
|
||
Tencent publishes volume in lots. Turnover is deliberately left unset
|
||
because its payload does not provide a field with compatible semantics.
|
||
"""
|
||
requested = tuple(dict.fromkeys(fund_codes))
|
||
if any(code not in SOUTHERN_FUND_CODES for code in requested):
|
||
raise ValueError("fund code is not in the Southern Fund whitelist")
|
||
if not requested:
|
||
return {}
|
||
symbols = ",".join(
|
||
("sh" if code.startswith(("5", "6", "9")) else "sz") + code
|
||
for code in requested
|
||
)
|
||
try:
|
||
response = httpx.get(
|
||
TENCENT_QUOTE_API + symbols,
|
||
headers={"User-Agent": HEADERS["User-Agent"]},
|
||
timeout=REQUEST_TIMEOUT,
|
||
)
|
||
response.raise_for_status()
|
||
except httpx.HTTPError as exc:
|
||
raise ExchangeQuoteSourceError("tencent quote request failed") from exc
|
||
return _parse_tencent_exchange_quotes(response.content, requested)
|
||
|
||
|
||
def _parse_tencent_exchange_quotes(
|
||
content: bytes, requested: tuple[str, ...],
|
||
) -> dict[str, dict[str, str | None]]:
|
||
try:
|
||
payload = content.decode("gbk")
|
||
except UnicodeDecodeError as exc:
|
||
raise ExchangeQuoteSourceError("tencent quote response decoding failed") from exc
|
||
result: dict[str, dict[str, str | None]] = {}
|
||
for match in re.finditer(r'v_(?:sh|sz)(\d{6})="([^"]*)"', payload):
|
||
code, raw = match.groups()
|
||
if code not in requested:
|
||
continue
|
||
fields = raw.split("~")
|
||
if len(fields) < 7 or not _valid_quote_number(fields[3]):
|
||
continue
|
||
previous_close = fields[4] if _valid_quote_number(fields[4]) else None
|
||
change_pct = fields[33] if len(fields) > 33 and _valid_quote_number(fields[33]) else None
|
||
if change_pct is None and previous_close is not None:
|
||
change_pct = _quote_change_pct(fields[3], previous_close)
|
||
result[code] = {
|
||
"last_price": fields[3],
|
||
"previous_close": previous_close,
|
||
"change_pct": change_pct,
|
||
"volume": fields[6] if _valid_quote_number(fields[6]) else None,
|
||
"turnover_amount": None,
|
||
}
|
||
if not result:
|
||
raise ExchangeQuoteSourceError("tencent quote response had no usable quotes")
|
||
return result
|
||
|
||
|
||
def _valid_quote_number(value: str) -> bool:
|
||
try:
|
||
return float(value) > 0
|
||
except ValueError:
|
||
return False
|
||
|
||
|
||
def _quote_change_pct(last_price: str, previous_close: str) -> str | None:
|
||
try:
|
||
return str(round((float(last_price) / float(previous_close) - 1) * 100, 4))
|
||
except (ValueError, ZeroDivisionError):
|
||
return None
|
||
|
||
|
||
def _get_history(codes: list[str], query_date: str) -> dict[str, dict[str, str | None]]:
|
||
global _history_date, _history_cache
|
||
if _history_date == query_date and all(code in _history_cache for code in codes):
|
||
return _history_cache
|
||
result = {}
|
||
for code in codes:
|
||
try:
|
||
result[code] = _get_history_snapshot(code, query_date)
|
||
except (httpx.HTTPError, ValueError, TypeError) as exc:
|
||
logger.warning("历史净值计算失败 code=%s error=%s", code, type(exc).__name__)
|
||
result[code] = _empty_returns()
|
||
_history_date, _history_cache = query_date, result
|
||
return result
|
||
|
||
|
||
def _get_history_snapshot(fund_code: str, query_date: str) -> dict[str, str | None]:
|
||
"""读取净值与累计收益率快照。"""
|
||
latest_records = _fetch_nav_records(fund_code, all_pages=False)
|
||
valid = _valid_records(latest_records)
|
||
if not valid:
|
||
return _empty_returns()
|
||
target = date.fromisoformat(query_date)
|
||
latest_date, _, latest = next((item for item in valid if item[0] == target), valid[0])
|
||
return {
|
||
"基金净值": latest.get("DWJZ"),
|
||
"日期": latest.get("FSRQ"),
|
||
"日涨幅": _format_percent(latest.get("JZZZL")),
|
||
"最近半年": _fetch_return_rate(fund_code, "6月"),
|
||
"最近一年": _fetch_return_rate(fund_code, "1年"),
|
||
"今年以来": _fetch_return_rate(fund_code, "今年来"),
|
||
"成立以来": _fetch_return_rate(fund_code, "成立来"),
|
||
}
|
||
|
||
|
||
def _fetch_nav_page(fund_code: str, page_index: int = 1, start_date: str | None = None, end_date: str | None = None) -> tuple[list[dict[str, Any]], int | None]:
|
||
"""读取一页历史净值，并返回接口提供的总条数。"""
|
||
response = httpx.get(NAV_API, params={"fundCode": fund_code, "pageIndex": page_index, "pageSize": 30, "startDate": start_date or "", "endDate": end_date or ""}, headers=HEADERS, timeout=REQUEST_TIMEOUT)
|
||
response.raise_for_status()
|
||
data = response.json().get("Data") or {}
|
||
records = data.get("LSJZList") or []
|
||
total = data.get("TotalCount") or data.get("totalCount")
|
||
try:
|
||
total = int(total) if total is not None else None
|
||
except (TypeError, ValueError):
|
||
total = None
|
||
return records, total
|
||
|
||
|
||
def _fetch_nav_records(fund_code: str, start_date: str | None = None, end_date: str | None = None, all_pages: bool = False) -> list[dict[str, Any]]:
|
||
"""调用历史净值接口；区间收益需要时读取完整分页，避免重复使用同一基准日。"""
|
||
records, total = _fetch_nav_page(fund_code, 1, start_date, end_date)
|
||
if not all_pages or (total is not None and total <= len(records)):
|
||
return records
|
||
if not (start_date and end_date):
|
||
return records
|
||
page_size = max(len(records), 1)
|
||
page_count = min((total + page_size - 1) // page_size, 40) if total else 40
|
||
seen_dates = {str(item.get("FSRQ") or "") for item in records}
|
||
for page_index in range(2, page_count + 1):
|
||
page_records, _ = _fetch_nav_page(fund_code, page_index, start_date, end_date)
|
||
if not page_records:
|
||
break
|
||
new_records = [
|
||
item for item in page_records if str(item.get("FSRQ") or "") not in seen_dates
|
||
]
|
||
if not new_records:
|
||
break
|
||
seen_dates.update(str(item.get("FSRQ") or "") for item in new_records)
|
||
records.extend(new_records)
|
||
if len(page_records) < page_size:
|
||
break
|
||
return records
|
||
|
||
|
||
def _fetch_return_rate(fund_code: str, period: str) -> str | None:
|
||
"""通过东方财富累计收益率接口读取指定区间的最新收益率。"""
|
||
period_map = {
|
||
"1月": "m",
|
||
"3月": "q",
|
||
"6月": "hy",
|
||
"1年": "y",
|
||
"3年": "try",
|
||
"5年": "fiy",
|
||
"今年来": "sy",
|
||
"成立来": "se",
|
||
}
|
||
try:
|
||
response = httpx.get(
|
||
RETURN_API,
|
||
params={"fundCode": fund_code, "indexcode": "000300", "type": period_map[period]},
|
||
headers={"Referer": "https://fund.eastmoney.com/"},
|
||
timeout=REQUEST_TIMEOUT,
|
||
)
|
||
response.raise_for_status()
|
||
payload = response.json()
|
||
series = (((payload.get("Data") or [{}])[0]).get("data") or [])
|
||
if not series:
|
||
return None
|
||
latest = series[-1]
|
||
if isinstance(latest, dict):
|
||
value = latest.get("y")
|
||
elif isinstance(latest, (list, tuple)) and len(latest) >= 2:
|
||
value = latest[1]
|
||
else:
|
||
value = None
|
||
if value in (None, ""):
|
||
return None
|
||
return _format_percent(value)
|
||
except (httpx.HTTPError, ValueError, TypeError, KeyError, IndexError) as exc:
|
||
logger.warning("累计收益率接口失败 code=%s period=%s error=%s", fund_code, period, type(exc).__name__)
|
||
return None
|
||
|
||
def _empty_returns() -> dict[str, str | None]:
|
||
return {key: None for key in ("基金净值", "日期", "日涨幅", "最近半年", "最近一年", "今年以来", "成立以来")}
|
||
|
||
|
||
def _valid_records(records: list[dict[str, Any]]) -> list[tuple[date, float, dict[str, Any]]]:
|
||
valid = []
|
||
for item in records:
|
||
try:
|
||
valid.append((date.fromisoformat(item["FSRQ"]), float(item["DWJZ"]), item))
|
||
except (KeyError, TypeError, ValueError):
|
||
continue
|
||
return sorted(valid, key=lambda item: item[0], reverse=True)
|
||
|
||
|
||
def _format_percent(value: Any) -> str | None:
|
||
if value in (None, ""):
|
||
return None
|
||
text = str(value).strip()
|
||
return text if text.endswith("%") else f"{text}%"
|