akshare 1.12.99__py3-none-any.whl → 1.15.73__py3-none-any.whl

akshare/crypto/crypto_hist_investing.py

@@ -1,249 +0,0 @@
-#!/usr/bin/env python
-# -*- coding:utf-8 -*-
-"""
-Date: 2022/5/11 17:52
-Desc: 加密货币
-https://cn.investing.com/crypto/currencies
-高频数据
-https://bitcoincharts.com/about/markets-api/
-"""
-import math
-
-import pandas as pd
-import requests
-from tqdm import tqdm
-
-from akshare.datasets import get_crypto_info_csv
-
-
-def crypto_name_url_table(symbol: str = "web") -> pd.DataFrame:
-    """
-    加密货币名称、代码和 ID，每次更新较慢
-    https://cn.investing.com/crypto/ethereum/historical-data
-    :param symbol: choice of {"web", "local"}; web 表示从网页获取最新，local 表示利用本地本文件
-    :type symbol: str
-    :return: 加密货币名称、代码和 ID
-    :rtype: pandas.DataFrame
-    """
-    if symbol == "web":
-        headers = {
-            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.111 Safari/537.36",
-            "X-Requested-With": "XMLHttpRequest",
-        }
-        url = "https://cn.investing.com/crypto/Service/LoadCryptoCurrencies"
-        payload = {
-            'draw': '14',
-            'columns[0][data]': 'currencies_order',
-            'columns[0][name]': 'currencies_order',
-            'columns[0][searchable]': 'true',
-            'columns[0][orderable]': 'true',
-            'columns[0][search][value]': '',
-            'columns[0][search][regex]': 'false',
-            'columns[1][data]': 'function',
-            'columns[1][name]': 'crypto_id',
-            'columns[1][searchable]': 'true',
-            'columns[1][orderable]': 'false',
-            'columns[1][search][value]': '',
-            'columns[1][search][regex]': 'false',
-            'columns[2][data]': 'function',
-            'columns[2][name]': 'name',
-            'columns[2][searchable]': 'true',
-            'columns[2][orderable]': 'true',
-            'columns[2][search][value]': '',
-            'columns[2][search][regex]': 'false',
-            'columns[3][data]': 'symbol',
-            'columns[3][name]': 'symbol',
-            'columns[3][searchable]': 'true',
-            'columns[3][orderable]': 'true',
-            'columns[3][search][value]': '',
-            'columns[3][search][regex]': 'false',
-            'columns[4][data]': 'function',
-            'columns[4][name]': 'price_usd',
-            'columns[4][searchable]': 'true',
-            'columns[4][orderable]': 'true',
-            'columns[4][search][value]': '',
-            'columns[4][search][regex]': 'false',
-            'columns[5][data]': 'market_cap_formatted',
-            'columns[5][name]': 'market_cap_usd',
-            'columns[5][searchable]': 'true',
-            'columns[5][orderable]': 'true',
-            'columns[5][search][value]': '',
-            'columns[5][search][regex]': 'false',
-            'columns[6][data]': '24h_volume_formatted',
-            'columns[6][name]': '24h_volume_usd',
-            'columns[6][searchable]': 'true',
-            'columns[6][orderable]': 'true',
-            'columns[6][search][value]': '',
-            'columns[6][search][regex]': 'false',
-            'columns[7][data]': 'total_volume',
-            'columns[7][name]': 'total_volume',
-            'columns[7][searchable]': 'true',
-            'columns[7][orderable]': 'true',
-            'columns[7][search][value]': '',
-            'columns[7][search][regex]': 'false',
-            'columns[8][data]': 'change_percent_formatted',
-            'columns[8][name]': 'change_percent',
-            'columns[8][searchable]': 'true',
-            'columns[8][orderable]': 'true',
-            'columns[8][search][value]': '',
-            'columns[8][search][regex]': 'false',
-            'columns[9][data]': 'percent_change_7d_formatted',
-            'columns[9][name]': 'percent_change_7d',
-            'columns[9][searchable]': 'true',
-            'columns[9][orderable]': 'true',
-            'columns[9][search][value]': '',
-            'columns[9][search][regex]': 'false',
-            'order[0][column]': 'currencies_order',
-            'order[0][dir]': 'asc',
-            'start': '0',
-            'length': '100',
-            'search[value]': '',
-            'search[regex]': 'false',
-            'currencyId': '12',
-        }
-        r = requests.post(url, data=payload, headers=headers)
-        data_json = r.json()
-        total_page = math.ceil(int(data_json['recordsTotal']) / 100)
-        big_df = pd.DataFrame()
-        for page in tqdm(range(1, total_page+1), leave=False):
-            payload.update({
-                "start": (page-1)*100,
-                'length': 100
-            })
-            r = requests.post(url, data=payload, headers=headers)
-            data_json = r.json()
-            temp_df = pd.DataFrame(data_json['data'])
-            big_df = pd.concat([big_df, temp_df], ignore_index=True)
-        big_df = big_df[[
-            'symbol',
-            'name',
-            'name_trans',
-            'sml_id',
-            'related_pair_ID',
-        ]]
-        return big_df
-    else:
-        get_crypto_info_csv_path = get_crypto_info_csv()
-        name_url_df = pd.read_csv(get_crypto_info_csv_path)
-        return name_url_df
-
-
-def crypto_hist(
-    symbol: str = "BTC",
-    period: str = "每日",
-    start_date: str = "20191020",
-    end_date: str = "20201020",
-):
-    """
-    加密货币历史数据
-    https://cn.investing.com/crypto/ethereum/historical-data
-    :param symbol: 货币名称
-    :type symbol: str
-    :param period: choice of {"每日", "每周", "每月"}
-    :type period: str
-    :param start_date: '20151020', 注意格式
-    :type start_date: str
-    :param end_date: '20201020', 注意格式
-    :type end_date: str
-    :return: 加密货币历史数据获取
-    :rtype: pandas.DataFrame
-    """
-    import warnings
-    warnings.filterwarnings('ignore')
-    headers = {
-        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.111 Safari/537.36",
-        "X-Requested-With": "XMLHttpRequest",
-    }
-    period_map = {"每日": "Daily", "每周": "Weekly", "每月": "Monthly"}
-    start_date = "/".join([start_date[:4], start_date[4:6], start_date[6:]])
-    end_date = "/".join([end_date[:4], end_date[4:6], end_date[6:]])
-    name_url_df = crypto_name_url_table(symbol='local')
-    curr_id = name_url_df[name_url_df["symbol"] == symbol]["related_pair_ID"].values[0]
-    sml_id = name_url_df[name_url_df["symbol"] == symbol]["sml_id"].values[0]
-    url = "https://cn.investing.com/instruments/HistoricalDataAjax"
-    payload = {
-        "curr_id": curr_id,
-        "smlID": sml_id,
-        "header": "null",
-        "st_date": start_date,
-        "end_date": end_date,
-        "interval_sec": period_map[period],
-        "sort_col": "date",
-        "sort_ord": "DESC",
-        "action": "historical_data",
-    }
-    r = requests.post(url, data=payload, headers=headers)
-
-    temp_df = pd.read_html(r.text)[0]
-    df_data = temp_df.copy()
-    if period == "每月":
-        df_data.index = pd.to_datetime(df_data["日期"], format="%Y年%m月")
-    else:
-        df_data.index = pd.to_datetime(df_data["日期"], format="%Y年%m月%d日")
-    if any(df_data["交易量"].astype(str).str.contains("-")):
-        df_data["交易量"][df_data["交易量"].str.contains("-")] = df_data["交易量"][
-            df_data["交易量"].str.contains("-")
-        ].replace("-", 0)
-    if any(df_data["交易量"].astype(str).str.contains("B")):
-        df_data["交易量"][df_data["交易量"].str.contains("B").fillna(False)] = (
-            df_data["交易量"][df_data["交易量"].str.contains("B").fillna(False)]
-            .str.replace("B", "")
-            .str.replace(",", "")
-            .astype(float)
-            * 1000000000
-        )
-    if any(df_data["交易量"].astype(str).str.contains("M")):
-        df_data["交易量"][df_data["交易量"].str.contains("M").fillna(False)] = (
-            df_data["交易量"][df_data["交易量"].str.contains("M").fillna(False)]
-            .str.replace("M", "")
-            .str.replace(",", "")
-            .astype(float)
-            * 1000000
-        )
-    if any(df_data["交易量"].astype(str).str.contains("K")):
-        df_data["交易量"][df_data["交易量"].str.contains("K").fillna(False)] = (
-            df_data["交易量"][df_data["交易量"].str.contains("K").fillna(False)]
-            .str.replace("K", "")
-            .str.replace(",", "")
-            .astype(float)
-            * 1000
-        )
-    df_data["交易量"] = df_data["交易量"].astype(float)
-    df_data["涨跌幅"] = pd.DataFrame(
-        round(
-            df_data["涨跌幅"].str.replace(",", "").str.replace("%", "").astype(float)
-            / 100,
-            6,
-        )
-    )
-    del df_data["日期"]
-    df_data.reset_index(inplace=True)
-    df_data = df_data[[
-        "日期",
-        "收盘",
-        "开盘",
-        "高",
-        "低",
-        "交易量",
-        "涨跌幅",
-    ]]
-    df_data['日期'] = pd.to_datetime(df_data['日期']).dt.date
-    df_data['收盘'] = pd.to_numeric(df_data['收盘'])
-    df_data['开盘'] = pd.to_numeric(df_data['开盘'])
-    df_data['高'] = pd.to_numeric(df_data['高'])
-    df_data['低'] = pd.to_numeric(df_data['低'])
-    df_data['交易量'] = pd.to_numeric(df_data['交易量'])
-    df_data['涨跌幅'] = pd.to_numeric(df_data['涨跌幅'])
-    df_data.sort_values('日期', inplace=True)
-    df_data.reset_index(inplace=True, drop=True)
-    return df_data
-
-
-if __name__ == "__main__":
-    crypto_name_url_table_df = crypto_name_url_table(symbol="local")
-    print(crypto_name_url_table_df)
-
-    crypto_hist_df = crypto_hist(
-        symbol="BTC", period="每日", start_date="20201020", end_date="20220511"
-    )
-    print(crypto_hist_df)

akshare/fortune/fortune_it_juzi.py

@@ -1,123 +0,0 @@
-#!/usr/bin/env python
-# -*- coding:utf-8 -*-
-"""
-Date: 2021/6/30 15:55
-Desc: 获取 IT桔子 的死亡公司数据、千里马和独角兽
-https://www.itjuzi.com/deathCompany
-https://www.itjuzi.com/chollima
-https://www.itjuzi.com/unicorn
-"""
-import pandas as pd
-
-
-def death_company() -> pd.DataFrame:
-    """
-    此数据未更新
-    IT桔子-死亡公司名单
-    https://www.itjuzi.com/deathCompany
-    :return: 死亡公司名单
-    :rtype: pandas.DataFrame
-    """
-    temp_df = pd.read_csv(
-        "https://jfds-1252952517.cos.ap-chengdu.myqcloud.com/akshare/data/data_juzi/juzi.csv"
-    )
-
-    temp_df.reset_index(inplace=True, drop=True)
-    temp_df.columns = [
-        "公司简称",
-        "成立时间",
-        "关闭时间",
-        "存活天数",
-        "融资规模",
-        "行业",
-        "地点",
-    ]
-    return temp_df
-
-
-def nicorn_company() -> pd.DataFrame:
-    """
-    此数据未更新
-    IT桔子-独角兽公司
-    https://www.itjuzi.com/unicorn
-    :return: 独角兽公司
-    :rtype: pandas.DataFrame
-    """
-    temp_df = pd.read_csv(
-        "https://jfds-1252952517.cos.ap-chengdu.myqcloud.com/akshare/data/data_juzi/nicorn_company.csv",
-        index_col=0,
-    )
-    temp_df.reset_index(drop=True, inplace=True)
-    del temp_df["com_id"]
-    del temp_df["com_logo_archive"]
-    del temp_df["com_city"]
-    del temp_df["invse_year"]
-    del temp_df["invse_month"]
-    del temp_df["invse_day"]
-    del temp_df["invse_guess_particulars"]
-    del temp_df["invse_detail_money"]
-    del temp_df["invse_currency_id"]
-    del temp_df["invse_similar_money_id"]
-    del temp_df["invse_round_id"]
-    del temp_df["money"]
-    del temp_df["invse_money"]
-    del temp_df["round"]
-    temp_df.reset_index(inplace=True)
-    temp_df["index"] = range(1, len(temp_df) + 1)
-    temp_df.columns = [
-        "序号",
-        "公司",
-        "地区",
-        "行业",
-        "子行业",
-    ]
-    return temp_df
-
-
-def maxima_company() -> pd.DataFrame:
-    """
-    此数据未更新
-    IT桔子-千里马公司
-    https://www.itjuzi.com/chollima
-    :return: 千里马公司
-    :rtype: pandas.DataFrame
-    """
-    temp_df = pd.read_csv(
-        "https://jfds-1252952517.cos.ap-chengdu.myqcloud.com/akshare/data/data_juzi/maxima.csv",
-        index_col=0,
-    )
-    temp_df.reset_index(drop=True, inplace=True)
-    del temp_df["com_id"]
-    del temp_df["com_logo_archive"]
-    del temp_df["com_scope_id"]
-    del temp_df["invse_year"]
-    del temp_df["invse_month"]
-    del temp_df["invse_day"]
-    del temp_df["invse_similar_money_id"]
-    del temp_df["invse_guess_particulars"]
-    del temp_df["invse_detail_money"]
-    del temp_df["invse_currency_id"]
-    del temp_df["invse_round_id"]
-    del temp_df["money"]
-    del temp_df["invse_money"]
-    del temp_df["round"]
-    temp_df.reset_index(inplace=True)
-    temp_df["index"] = range(1, len(temp_df) + 1)
-    temp_df.columns = [
-        "序号",
-        "公司",
-        "行业",
-        "地区",
-    ]
-    return temp_df
-
-
-if __name__ == "__main__":
-    death_company_df = death_company()
-    print(death_company_df)
-
-    nicorn_company_df = nicorn_company()
-    print(nicorn_company_df)
-
-    maxima_company_df = maxima_company()
-    print(maxima_company_df)

akshare/futures/futures_international.py

@@ -1,170 +0,0 @@
-#!/usr/bin/env python
-# -*- coding:utf-8 -*-
-"""
-Date: 2021/5/10 17:06
-Desc: 提供英为财情-国际大宗商品期货
-https://cn.investing.com/commodities/brent-oil-historical-data
-"""
-import re
-
-import pandas as pd
-import requests
-from bs4 import BeautifulSoup
-
-from akshare.index.cons import short_headers, long_headers
-
-
-def get_sector_symbol_name_url() -> dict:
-    """
-    期货所对应板块的 URL
-    :return: dict
-    {'能源': '/commodities/energy',
-    '金属': '/commodities/metals',
-    '农业': '/commodities/softs',
-    '商品指数': '/indices/commodities-indices'}
-    """
-    url = "https://cn.investing.com/commodities/"
-    res = requests.get(url, headers=short_headers)
-    soup = BeautifulSoup(res.text, "lxml")
-    name_url_option_list = soup.find_all(attrs={"class": "linkTitle"})  # 去掉-所有国家及地区
-    url_list = [item.find("a")["href"] for item in name_url_option_list]
-    name_list = [item.get_text() for item in name_url_option_list]
-    name_code_map_dict = {}
-    name_code_map_dict.update(zip(name_list, url_list))
-    return name_code_map_dict
-
-
-def futures_global_commodity_name_url_map(sector: str = "能源") -> dict:
-    """
-    参考网页: https://cn.investing.com/commodities/
-    获取选择板块对应的: 具体期货品种的 url 地址
-    :param sector: 板块, 对应 get_global_country_name_url 品种名称
-    :type sector: str
-    :return: dict of name-url
-    :rtype: dict
-    {'伦敦布伦特原油': '/commodities/brent-oil',
-    'WTI原油': '/commodities/crude-oil',
-    '伦敦汽油': '/commodities/london-gas-oil',
-    '天然气': '/commodities/natural-gas?cid=49787',
-    '燃料油': '/commodities/heating-oil',
-    '碳排放': '/commodities/carbon-emissions',
-    'RBOB汽油': '/commodities/gasoline-rbob',
-    '布伦特原油': '/commodities/brent-oil?cid=49769',
-    '原油': '/commodities/crude-oil?cid=49774'}
-    """
-    name_url_dict = get_sector_symbol_name_url()
-    url = f"https://cn.investing.com{name_url_dict[sector]}"
-    res = requests.post(url, headers=short_headers)
-    soup = BeautifulSoup(res.text, "lxml")
-    url_list = [
-        item.find("a")["href"].split("?")[0]
-        for item in soup.find_all(attrs={"class": "plusIconTd"})
-    ]
-    name_list = [
-        item.find("a").get_text()
-        for item in soup.find_all(attrs={"class": "plusIconTd"})
-    ]
-    name_code_map_dict = {}
-    name_code_map_dict.update(zip(name_list, url_list))
-    return name_code_map_dict
-
-
-def futures_global_commodity_hist(
-    sector: str = "能源",
-    symbol: str = "伦敦布伦特原油",
-    start_date: str = "20000101",
-    end_date: str = "20191017",
-) -> pd.DataFrame:
-    """
-    国际大宗商品的历史量价数据
-    https://cn.investing.com/commodities
-    :param sector: 板块名称; 调用 futures_global_commodity_name_url_map 函数获取
-    :type sector: str
-    :param symbol: 品种名称; 通过访问网站查询
-    :type symbol: str
-    :param start_date: 开始日期
-    :type start_date: str
-    :param end_date: 结束日期
-    :type end_date: str
-    :return: 国际大宗商品的历史量价数据
-    :rtype: pandas.DataFrame
-    """
-    start_date = "/".join([start_date[:4], start_date[4:6], start_date[6:]])
-    end_date = "/".join([end_date[:4], end_date[4:6], end_date[6:]])
-    name_code_dict = futures_global_commodity_name_url_map(sector)
-    temp_url = f"https://cn.investing.com/{name_code_dict[symbol]}-historical-data"
-    res = requests.post(temp_url, headers=short_headers)
-    soup = BeautifulSoup(res.text, "lxml")
-    title = soup.find("h2", attrs={"class": "float_lang_base_1"}).get_text()
-    res = requests.post(temp_url, headers=short_headers)
-    soup = BeautifulSoup(res.text, "lxml")
-    data = soup.find_all(text=re.compile("window.histDataExcessInfo"))[0].strip()
-    para_data = re.findall(r"\d+", data)
-    payload = {
-        "curr_id": para_data[0],
-        "smlID": para_data[1],
-        "header": title,
-        "st_date": start_date,
-        "end_date": end_date,
-        "interval_sec": "Daily",
-        "sort_col": "date",
-        "sort_ord": "DESC",
-        "action": "historical_data",
-    }
-    url = "https://cn.investing.com/instruments/HistoricalDataAjax"
-    r = requests.post(url, data=payload, headers=long_headers)
-    temp_df = pd.read_html(r.text)[0]
-    temp_df["日期"] = pd.to_datetime(temp_df["日期"], format="%Y年%m月%d日")
-    if any(temp_df["交易量"].astype(str).str.contains("-")):
-        temp_df["交易量"][temp_df["交易量"].str.contains("-")] = temp_df["交易量"][
-            temp_df["交易量"].str.contains("-")
-        ].replace("-", 0)
-    if any(temp_df["交易量"].astype(str).str.contains("B")):
-        temp_df["交易量"][temp_df["交易量"].str.contains("B").fillna(False)] = (
-            temp_df["交易量"][temp_df["交易量"].str.contains("B").fillna(False)]
-            .str.replace("B", "")
-            .astype(float)
-            * 1000000000
-        )
-    if any(temp_df["交易量"].astype(str).str.contains("M")):
-        temp_df["交易量"][temp_df["交易量"].str.contains("M").fillna(False)] = (
-            temp_df["交易量"][temp_df["交易量"].str.contains("M").fillna(False)]
-            .str.replace("M", "")
-            .astype(float)
-            * 1000000
-        )
-    if any(temp_df["交易量"].astype(str).str.contains("K")):
-        temp_df["交易量"][temp_df["交易量"].str.contains("K").fillna(False)] = (
-            temp_df["交易量"][temp_df["交易量"].str.contains("K").fillna(False)]
-            .str.replace("K", "")
-            .astype(float)
-            * 1000
-        )
-    temp_df["交易量"] = temp_df["交易量"].astype(float)
-    temp_df["涨跌幅"] = pd.DataFrame(
-        round(temp_df["涨跌幅"].str.replace("%", "").astype(float) / 100, 6)
-    )
-    temp_df.name = title
-    temp_df.columns.name = None
-    temp_df.sort_values(["日期"], ascending=False, inplace=True)
-    return temp_df
-
-
-if __name__ == "__main__":
-    temp_dict = futures_global_commodity_name_url_map(sector="能源")
-    print(temp_dict)
-
-    futures_global_commodity_hist_df = futures_global_commodity_hist(
-        sector="能源", symbol="伦敦布伦特原油", start_date="19700101", end_date="20210510"
-    )
-    print(futures_global_commodity_hist_df)
-
-    # futures_global_commodity_hist_df = futures_global_commodity_hist(
-    #     sector="能源", symbol="伦敦布伦特原油", start_date="1970/01/01", end_date="2021/05/10"
-    # )
-    # print(futures_global_commodity_hist_df.to_csv("伦敦布伦特原油_19880627_20080319.csv", encoding="gb2312"))
-    #
-    # futures_global_commodity_hist_df = futures_global_commodity_hist(
-    #     sector="能源", symbol="伦敦布伦特原油", start_date="2008/03/19", end_date="2021/05/10"
-    # )
-    # print(futures_global_commodity_hist_df.to_csv("伦敦布伦特原油_20080319_20210510.csv", encoding="gb2312"))

akshare/futures/futures_news_baidu.py

@@ -1,54 +0,0 @@
-#!/usr/bin/env python
-# -*- coding:utf-8 -*-
-"""
-Date: 2023/7/2 16:00
-Desc: 百度股市通-期货-新闻
-https://gushitong.baidu.com/futures/ab-CJ888
-"""
-import pandas as pd
-import requests
-
-
-def futures_news_baidu(symbol: str = "AL") -> pd.DataFrame:
-    """
-    百度股市通-期货-新闻
-    https://gushitong.baidu.com/futures/ab-CJ888
-    :param symbol: 期货品种代码；大写
-    :type symbol: str
-    :return: 新闻
-    :rtype: pandas.DataFrame
-    """
-    url = "https://finance.pae.baidu.com/vapi/getfuturesnews"
-    params = {"code": f"{symbol}888", "pn": "0", "rn": "2000", "finClientType": "pc"}
-    r = requests.get(url, params=params)
-    data_json = r.json()
-    temp_df = pd.DataFrame(data_json["Result"])
-    temp_df.rename(
-        columns={
-            "loc": "-",
-            "provider": "-",
-            "source": "-",
-            "publish_time": "发布时间",
-            "third_url": "新闻链接",
-            "title": "标题",
-            "is_self_build": "-",
-            "news_id": "-",
-            "locate_url": "-",
-        },
-        inplace=True,
-    )
-    temp_df = temp_df[
-        [
-            "标题",
-            "发布时间",
-            "新闻链接",
-        ]
-    ]
-    temp_df["发布时间"] = pd.to_datetime(pd.to_numeric(temp_df["发布时间"]), unit="s").dt.date
-    temp_df.sort_values(["发布时间"], inplace=True, ignore_index=True)
-    return temp_df
-
-
-if __name__ == "__main__":
-    futures_news_baidu_df = futures_news_baidu(symbol="AL")
-    print(futures_news_baidu_df)