stock-tracker

2026-07-04 00:17:11 +08:00
commit 6087341a48
6463 changed files with 1929869 additions and 0 deletions
@@ -0,0 +1,6 @@
+#!/usr/bin/env python
+# -*- coding:utf-8 -*-
+"""
+Date: 2020/2/13 21:21
+Desc:
+"""
@@ -0,0 +1,10 @@
+# !/usr/bin/env python
+"""
+Date: 2024/4/7 15:30
+Desc: 通用变量
+"""
+
+headers = {
+    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
+    "Chrome/114.0.0.0 Safari/537.36"
+}
@@ -0,0 +1,43 @@
+class AkshareConfig:
+    _instance = None
+
+    def __new__(cls):
+        if cls._instance is None:
+            cls._instance = super().__new__(cls)
+            cls._instance.proxies = None
+        return cls._instance
+
+    @classmethod
+    def set_proxies(cls, proxies):
+        cls().proxies = proxies
+
+    @classmethod
+    def get_proxies(cls):
+        return cls().proxies
+
+
+config = AkshareConfig()
+
+
+# 导出 set_proxies 函数
+def set_proxies(proxies):
+    config.set_proxies(proxies)
+
+
+def get_proxies():
+    return config.get_proxies()
+
+
+class ProxyContext:
+    def __init__(self, proxies):
+        self.proxies = proxies
+        self.old_proxies = None
+
+    def __enter__(self):
+        self.old_proxies = config.get_proxies()
+        config.set_proxies(self.proxies)
+        return self
+
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        config.set_proxies(self.old_proxies)
+        return False  # 不处理异常
@@ -0,0 +1,77 @@
+# !/usr/bin/env python
+"""
+Date: 2025/3/10 18:00
+Desc: 通用帮助函数
+"""
+
+import math
+import random
+import time
+from typing import List, Dict
+
+import pandas as pd
+
+from akshare.utils.request import request_with_retry
+from akshare.utils.tqdm import get_tqdm
+
+
+def fetch_paginated_data(url: str, base_params: Dict, timeout: int = 15):
+    """
+    东方财富-分页获取数据并合并结果
+    https://quote.eastmoney.com/f1.html?newcode=0.000001
+    :param url: 股票代码
+    :type url: str
+    :param base_params: 基础请求参数
+    :type base_params: dict
+    :param timeout: 请求超时时间
+    :type timeout: str
+    :return: 合并后的数据
+    :rtype: pandas.DataFrame
+    """
+    # 复制参数以避免修改原始参数
+    params = base_params.copy()
+    # 获取第一页数据，用于确定分页信息
+    r = request_with_retry(url, params=params, timeout=timeout)
+    data_json = r.json()
+    # 计算分页信息
+    per_page_num = len(data_json["data"]["diff"])
+    total_page = math.ceil(data_json["data"]["total"] / per_page_num)
+    # 存储所有页面数据
+    temp_list = []
+    # 添加第一页数据
+    temp_list.append(pd.DataFrame(data_json["data"]["diff"]))
+    # 获取进度条
+    tqdm = get_tqdm()
+    # 获取剩余页面数据
+    for page in tqdm(range(2, total_page + 1), leave=False):
+        params.update({"pn": page})
+        # 添加随机延迟，避免请求过于频繁
+        time.sleep(random.uniform(0.5, 1.5))
+        r = request_with_retry(url, params=params, timeout=timeout)
+        data_json = r.json()
+        inner_temp_df = pd.DataFrame(data_json["data"]["diff"])
+        temp_list.append(inner_temp_df)
+    # 合并所有数据
+    temp_df = pd.concat(temp_list, ignore_index=True)
+    temp_df["f3"] = pd.to_numeric(temp_df["f3"], errors="coerce")
+    temp_df.sort_values(by=["f3"], ascending=False, inplace=True, ignore_index=True)
+    temp_df.reset_index(inplace=True)
+    temp_df["index"] = temp_df["index"].astype(int) + 1
+    return temp_df
+
+
+def set_df_columns(df: pd.DataFrame, cols: List[str]) -> pd.DataFrame:
+    """
+    设置 pandas.DataFrame 为空的情况
+    :param df: 需要设置命名的数据框
+    :type df: pandas.DataFrame
+    :param cols: 字段的列表
+    :type cols: list
+    :return: 重新设置后的数据
+    :rtype: pandas.DataFrame
+    """
+    if df.shape == (0, 0):
+        return pd.DataFrame(data=[], columns=cols)
+    else:
+        df.columns = cols
+        return df
@@ -0,0 +1,53 @@
+"""
+利用多进行执行 js 代码方案
+
+1. 未能解决 gevent 调用问题
+2. 导致 js 代码执行缓慢
+3. 该方案废弃，这里仅作参考
+
+同时发现 gevent 里面无法调用异步的接口
+"""
+
+import concurrent.futures
+
+
+# 定义在模块级别的函数
+def js_executor_function(js_code_str, method, args):
+    """在新进程中执行 JavaScript 代码的函数"""
+    from py_mini_racer import MiniRacer
+
+    js_code = MiniRacer()
+    js_code.eval(js_code_str)
+
+    if method == "call":
+        fn_name = args[0]
+        fn_args = args[1:]
+        return js_code.call(fn_name, *fn_args)
+    elif method == "eval":
+        return js_code.eval(args[0])
+    else:
+        raise ValueError(f"不支持的方法: {method}")
+
+
+def execute_js_in_executor(js_code_str, method, *args, timeout=30):
+    """
+    使用 ProcessPoolExecutor 在独立进程中执行 JavaScript
+
+    参数:
+        js_code_str: JavaScript 代码字符串
+        method: 'call' 或 'eval'
+        args: 如果 method 是 'call'，第一个参数是函数名，后续是函数参数
+              如果 method 是 'eval'，只需提供一个参数：要评估的代码
+        timeout: 超时时间（秒）
+
+    返回:
+        执行结果
+    """
+    with concurrent.futures.ProcessPoolExecutor(max_workers=1) as executor:
+        future = executor.submit(js_executor_function, js_code_str, method, args)
+        try:
+            return future.result(timeout=timeout)
+        except concurrent.futures.TimeoutError:
+            # 清理资源并抛出超时异常
+            executor.shutdown(wait=False)
+            raise TimeoutError("JavaScript 执行超时")
@@ -0,0 +1,64 @@
+# !/usr/bin/env python
+"""
+Date: 2025/12/31
+Desc: HTTP 请求工具函数
+"""
+
+import random
+import time
+from typing import Dict, Tuple
+
+import requests
+from requests.adapters import HTTPAdapter
+
+
+def request_with_retry(
+    url: str,
+    params: Dict = None,
+    timeout: int = 15,
+    max_retries: int = 3,
+    base_delay: float = 1.0,
+    random_delay_range: Tuple[float, float] = (0.5, 1.5),
+) -> requests.Response:
+    """
+    带重试机制的 HTTP GET 请求
+    :param url: 请求 URL
+    :type url: str
+    :param params: 请求参数
+    :type params: dict
+    :param timeout: 超时时间（秒）
+    :type timeout: int
+    :param max_retries: 最大重试次数
+    :type max_retries: int
+    :param base_delay: 基础延迟时间（秒），用于指数退避
+    :type base_delay: float
+    :param random_delay_range: 随机延迟范围（秒）
+    :type random_delay_range: tuple
+    :return: Response 对象
+    :rtype: requests.Response
+    :raises: 最后一次请求的异常
+    """
+    last_exception = None
+
+    for attempt in range(max_retries):
+        try:
+            # 每次请求创建新的 Session，避免复用连接
+            with requests.Session() as session:
+                # 禁用连接池复用
+                adapter = HTTPAdapter(pool_connections=1, pool_maxsize=1)
+                session.mount("http://", adapter)
+                session.mount("https://", adapter)
+
+                response = session.get(url, params=params, timeout=timeout)
+                response.raise_for_status()
+                return response
+
+        except (requests.RequestException, ValueError) as e:
+            last_exception = e
+
+            if attempt < max_retries - 1:
+                # 指数退避 + 随机抖动
+                delay = base_delay * (2**attempt) + random.uniform(*random_delay_range)
+                time.sleep(delay)
+
+    raise last_exception
@@ -0,0 +1,34 @@
+#!/usr/bin/env python
+# -*- coding:utf-8 -*-
+"""
+Date: 2020/2/13 21:22
+Desc: 存储和读取 Token 文件
+"""
+
+import os
+
+import pandas as pd
+
+from akshare.pro import cons
+
+
+def set_token(token):
+    df = pd.DataFrame([token], columns=["token"])
+    user_home = os.path.expanduser("~")
+    fp = os.path.join(user_home, cons.TOKEN_F_P)
+    df.to_csv(fp, index=False)
+
+
+def get_token():
+    user_home = os.path.expanduser("~")
+    fp = os.path.join(user_home, cons.TOKEN_F_P)
+    if os.path.exists(fp):
+        df = pd.read_csv(fp)
+        return str(df.iloc[0]["token"])
+    else:
+        print(cons.TOKEN_ERR_MSG)
+        return
+
+
+if __name__ == "__main__":
+    pass
@@ -0,0 +1,27 @@
+def get_tqdm(enable: bool = True):
+    """
+    返回适用于当前环境的 tqdm 对象。
+
+    Args:
+        enable (bool): 是否启用进度条。默认为 True。
+
+    Returns:
+        tqdm 对象。
+    """
+    if not enable:
+        # 如果进度条被禁用，返回一个不显示进度条的 tqdm 对象
+        return lambda iterable, *args, **kwargs: iterable
+
+    try:
+        # 尝试检查是否在 jupyter notebook 环境中，有利于退出进度条
+        # noinspection PyUnresolvedReferences
+        shell = get_ipython().__class__.__name__
+        if shell == "ZMQInteractiveShell":
+            from tqdm.notebook import tqdm
+        else:
+            from tqdm import tqdm
+    except (NameError, ImportError):
+        # 如果不在 Jupyter 环境中，就使用标准 tqdm
+        from tqdm import tqdm
+
+    return tqdm