cmeshare 0.1.0__py3-none-any.whl

cmeshare/__init__.py

@@ -0,0 +1,14 @@
+# -*- coding: utf-8 -*-
+"""CMEShare Python 接口库。"""
+
+from cmeshare.historydata import (
+    get_historical_data,
+    HistoryDataError,
+    RateLimitError,
+)
+
+__all__ = [
+    'get_historical_data',
+    'HistoryDataError',
+    'RateLimitError',
+]

cmeshare/historydata.py

@@ -0,0 +1,188 @@
+# -*- coding: utf-8 -*-
+"""CMEShare 历史数据接口（精简版）。
+
+约定：数据目录与 key 同名，请求 HQ：
+  POST /api/down_file_by_token  { token, key, filename }
+落盘：DATA_ROOT/{key}/{code}.zip
+"""
+
+import io
+import os
+import zipfile
+from datetime import date, datetime
+
+import pandas as pd
+import requests
+
+
+class HistoryDataError(Exception):
+    """历史数据错误。"""
+
+
+class RateLimitError(HistoryDataError):
+    def __init__(self, message='', status_code=429):
+        super().__init__(message or '访问过于频繁，请降低请求频率！')
+        self.status_code = status_code
+
+
+def _hq_url():
+    return (os.environ.get('CMESHARE_HQ_URL') or 'http://127.0.0.1:5000').rstrip('/')
+
+
+def _require_token(token_str=''):
+    tok = (token_str or '').strip()
+    if not tok:
+        raise ValueError('请提供 token_str')
+    return tok
+
+
+def _as_zip_name(name):
+    name = str(name or '').strip()
+    if not name:
+        return ''
+    return name if name.lower().endswith('.zip') else f'{name}.zip'
+
+
+def _parse_date(value):
+    if value is None or (isinstance(value, str) and not str(value).strip()):
+        raise ValueError('日期不能为空')
+    if isinstance(value, datetime):
+        return value.date()
+    if isinstance(value, date):
+        return value
+    s = str(value).strip().replace('/', '-').replace('.', '-')
+    if len(s) == 8 and s.isdigit():
+        return datetime.strptime(s, '%Y%m%d').date()
+    if ' ' in s:
+        s = s.split(' ', 1)[0]
+    if 'T' in s:
+        s = s.split('T', 1)[0]
+    return datetime.strptime(s, '%Y-%m-%d').date()
+
+
+def _time_col(df):
+    for col in ('时间', '交易日期', '日期', 'datetime', 'date', 'Date', 'DATE'):
+        if col in df.columns:
+            return col
+    return None
+
+
+def _filter_df_by_date(df, start_date, end_date):
+    if df is None or df.empty:
+        return pd.DataFrame() if df is None else df
+    col = _time_col(df)
+    if not col:
+        return df
+    start_d = _parse_date(start_date)
+    end_d = _parse_date(end_date)
+    if start_d > end_d:
+        start_d, end_d = end_d, start_d
+    start_ts = pd.Timestamp(start_d)
+    end_ts = pd.Timestamp(end_d) + pd.Timedelta(days=1) - pd.Timedelta(microseconds=1)
+    ts = pd.to_datetime(df[col], errors='coerce')
+    mask = (ts >= start_ts) & (ts <= end_ts)
+    return df.loc[mask].reset_index(drop=True)
+
+
+def _read_csv_bytes(raw):
+    last_err = None
+    for enc in ('utf-8-sig', 'utf-8', 'gbk'):
+        try:
+            return pd.read_csv(io.BytesIO(raw), encoding=enc, low_memory=False)
+        except Exception as exc:
+            last_err = exc
+    raise HistoryDataError(f'CSV 解码失败: {last_err}') from last_err
+
+
+def _zip_bytes_to_df(content):
+    if not content:
+        raise HistoryDataError('下载内容为空')
+    try:
+        with zipfile.ZipFile(io.BytesIO(content)) as zf:
+            for name in zf.namelist():
+                if name.endswith('/') or name.startswith('__MACOSX'):
+                    continue
+                if name.lower().endswith('.csv'):
+                    return _read_csv_bytes(zf.read(name))
+    except HistoryDataError:
+        raise
+    except Exception as exc:
+        raise HistoryDataError(f'zip 解析失败: {exc}') from exc
+    raise HistoryDataError('zip 内未找到 csv 文件')
+
+
+def _is_rate_limited(status_code=None, err_msg=''):
+    if status_code == 429:
+        return True
+    text = str(err_msg or '')
+    return ('频繁' in text) or ('请求处理中' in text)
+
+
+def _download_file(key, filename, token, folder=''):
+    """调用 HQ：key 即数据目录名。"""
+    payload = {
+        'key': key,
+        'filename': filename,
+        'folder': str(folder or ''),
+        'token': token,
+    }
+    resp = requests.post(
+        f'{_hq_url()}/api/down_file_by_token',
+        json=payload,
+        headers={'Content-Type': 'application/json', 'Authorization': f'Bearer {token}'},
+        timeout=600,
+    )
+    ctype = (resp.headers.get('Content-Type') or '').lower()
+    if 'application/json' in ctype:
+        try:
+            data = resp.json()
+        except Exception as exc:
+            raise HistoryDataError(f'下载失败 HTTP {resp.status_code}: {exc}') from exc
+        err = str((data or {}).get('error') or (data or {}).get('message') or resp.text or '')
+        if _is_rate_limited(resp.status_code, err):
+            raise RateLimitError(err, status_code=resp.status_code)
+        raise HistoryDataError(err or f'下载失败 HTTP {resp.status_code}')
+    if not resp.ok:
+        err = (resp.text or '')[:500]
+        if _is_rate_limited(resp.status_code, err):
+            raise RateLimitError(err, status_code=resp.status_code)
+        raise HistoryDataError(err or f'下载失败 HTTP {resp.status_code}')
+    return resp.content
+
+
+def get_historical_data(key, code, start_date=None, end_date=None, token_str='', adjust='adj_none'):
+    """下载历史行情并返回 DataFrame。
+
+    Args:
+        key: 数据目录名，如 split_daily / a_index_day
+        code: 标的代码，如 SH.600000
+        start_date / end_date: 可选，按「时间」列裁剪
+        token_str: 个人 token（必填）
+        adjust: 暂仅支持 adj_none（占位，与文档参数兼容）
+    """
+    key = (key or '').strip()
+    code = (code or '').strip()
+    if not key:
+        raise ValueError('key 不能为空')
+    if not code:
+        raise ValueError('code 不能为空')
+
+    adjust_key = (adjust or 'adj_none').strip().lower()
+    if adjust_key not in ('', 'adj_none', 'none'):
+        raise ValueError('当前仅支持 adjust=adj_none')
+
+    token = _require_token(token_str)
+    zip_name = _as_zip_name(code)
+    content = _download_file(key, zip_name, token)
+    df = _zip_bytes_to_df(content)
+
+    has_start = start_date is not None and str(start_date).strip() != ''
+    has_end = end_date is not None and str(end_date).strip() != ''
+    if has_start or has_end:
+        start_s = str(start_date).strip() if has_start else str(end_date).strip()
+        end_s = str(end_date).strip() if has_end else start_s
+        df = _filter_df_by_date(df, start_s, end_s)
+
+    if df is None or df.empty:
+        raise HistoryDataError(f'未获取到数据：{key} {code}')
+    return df

cmeshare-0.1.0.dist-info/METADATA

@@ -0,0 +1,15 @@
+Metadata-Version: 2.4
+Name: cmeshare
+Version: 0.1.0
+Summary: CMEShare 免费行情 Python 接口
+Author: CMEShare
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.8
+Requires-Dist: pandas>=1.3.0
+Requires-Dist: requests>=2.25.0
+Dynamic: author
+Dynamic: classifier
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary

cmeshare-0.1.0.dist-info/RECORD

@@ -0,0 +1,6 @@
+cmeshare/__init__.py,sha256=WRA5ZBE9FJGlk4L8-eBZN5jRPGyCeN2ZZ9VX_Ds4ZtI,252
+cmeshare/historydata.py,sha256=mKGevBaDXsWzV0Ipa2ajU6LQT4Vk6PHEMQ3APXc04Js,6246
+cmeshare-0.1.0.dist-info/METADATA,sha256=rVJ35Z3z7Kr6kuoOUmmhAW171-TfvFFgz4OLu7fLm-g,409
+cmeshare-0.1.0.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
+cmeshare-0.1.0.dist-info/top_level.txt,sha256=BKIIyUcRPUNECtthqPq65-qw7XHExGg22Mc6gpxXnLU,9
+cmeshare-0.1.0.dist-info/RECORD,,

cmeshare-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (82.0.1)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

cmeshare-0.1.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+cmeshare