未获取数据 Web.DataReader Panda

Question

当我尝试从整个标准普尔 500 指数创建 CSV 文件时收到此错误消息：

Exception has occurred: pandas_datareader._utils.RemoteDataError

没有使用 YahooDailyReader 获取符号 3M 公司的数据

我认为这是有问题的：

for row in table.findAll('tr') [1:]:
    ticker = row.findAll('td')[0:].text

有人能帮帮我吗？提前致谢。

完整代码-

import bs4 as bs
import datetime as dt
import os
import pandas_datareader.data as web
import pickle
import requests

def save_sp500_tickers():
    resp = requests.get('http://en.wikipedia.org/wiki/List_of_S%26P_500_companies')
    soup = bs.BeautifulSoup(resp.text, 'lxml')
    table = soup.find('table', {'class': 'wikitable sortable'})
    tickers = []

    for row in table.findAll('tr') [1:]:
        ticker = row.findAll('td')[0:].text
        tickers.append(ticker)
    with open("sp500tickers.pickle", "wb") as f:
        pickle.dump(tickers, f)
    return tickers

# save_sp500_tickers()
def get_data_from_yahoo(reload_sp500=False):
    if reload_sp500:
        tickers = save_sp500_tickers()
    else:
        with open("sp500tickers.pickle", "rb") as f:
            tickers = pickle.load(f)
    if not os.path.exists('stock_dfs'):
        os.makedirs('stock_dfs')

    start = dt.datetime(2010, 1, 1)
    end = dt.datetime.now()
    for ticker in tickers:
    # just in case your connection breaks, we'd like to save our progress!
        if not os.path.exists('stock_dfs/{}.csv'.format(ticker)):
            df = web.DataReader(ticker, 'yahoo', start, end)
            df.reset_index(inplace=True)
            df.set_index("Date", inplace=True)
            df = df.drop("Symbol", axis=1)
            df.to_csv('stock_dfs/{}.csv'.format(ticker))
        else:
            print('Already have {}'.format(ticker))


 get_data_from_yahoo()

Answer 1

有各种过时的代码部分。我发现的解决方案需要使用以下命令安装 fix_yahoo_finance 和 yfinance：

pip install yfinance
pip install fix_yahoo_finance

这似乎对我有用，完整代码如下。

import bs4 as bs
import datetime as dt
import os
from pandas_datareader import data as pdr
import pickle
import requests
import fix_yahoo_finance as yf

yf.pdr_override()

def save_sp500_tickers():
    resp = requests.get('http://en.wikipedia.org/wiki/List_of_S%26P_500_companies')
    soup = bs.BeautifulSoup(resp.text, 'lxml')
    table = soup.find('table', {'class': 'wikitable sortable'})
    tickers = []
    for row in table.findAll('tr')[1:]:
        ticker = row.findAll('td')[0].text.replace('.', '-')
        ticker = ticker[:-1]
        tickers.append(ticker)
    with open("sp500tickers.pickle", "wb") as f:
        pickle.dump(tickers, f)
    return tickers


# save_sp500_tickers()
def get_data_from_yahoo(reload_sp500=False):
    if reload_sp500:
        tickers = save_sp500_tickers()
    else:
        with open("sp500tickers.pickle", "rb") as f:
            tickers = pickle.load(f)
    if not os.path.exists('stock_dfs'):
        os.makedirs('stock_dfs')
    start = dt.datetime(2019, 6, 8)
    end = dt.datetime.now()
    for ticker in tickers:
        print(ticker)
        if not os.path.exists('stock_dfs/{}.csv'.format(ticker)):
            df = pdr.get_data_yahoo(ticker, start, end)
            df.reset_index(inplace=True)
            df.set_index("Date", inplace=True)
            df.to_csv('stock_dfs/{}.csv'.format(ticker))
        else:
            print('Already have {}'.format(ticker))


save_sp500_tickers()
get_data_from_yahoo()

Answer 2

从维基百科刮取返回 'MMM/n' 到 pickle 文件。

添加

ticker = ticker[:-1]

到

for row in table.findAll('tr')[1:]: 
    ticker = row.findAll('td')[0].text
    ticker = ticker[:-1]
    tickers.append(ticker)

并重新生成您的泡菜文件。

那应该将股票代码保留为“MMM”而不是“MMM/n”