我尝试使用Pandas和Pandas Datareader从Google财经中提取数据。 这是我的代码：
#Importing libraries needed for pulls from Google
from pandas_datareader import data
import pandas as pd
import datetime
from datetime import date
#Define the instruments to download. In this case: Apple, Microsoft, and
the S&P500 index
tickers = ['APPL', 'MSFT', 'SPY']
start_date = datetime.datetime(2017, 12, 1)
end_date = datetime.datetime(2017, 12, 31)
#Use pandas_reader.data.DataReader to load the desired data
panel_data = data.DataReader('SPY', 'google', start_date, end_date)
#Getting just the adjusted closing prices. This will return a Pandas DataFrame
#The index in this DataFrame is the major index of the panel_data.
close = panel_data.ix['Close']
#Getting all weekdays within date range.
all_weekdays = pd.date_range(start=start_date, end=end_date, freq='B')
#How do we align the existing prices in the adj_close with out new set of dates?
#All we need to do is reindex close using all_weekdays as the new index.
close = close.reindex(all_weekdays)
close.head(10)
这是控制台输出：
runfile('C:/Users/kjohn_000/.spyder-py3/temp.py', wdir='C:/Users/kjohn_000/.spyder-py3')
C:\Users\kjohn_000\Anaconda3\lib\site-packages\pandas_datareader\base.py:201: SymbolWarning: Failed to read symbol:
'APPL', replacing with NaN.
warnings.warn(msg.format(sym), SymbolWarning)
C:\Users\kjohn_000\Anaconda3\lib\site-
packages\pandas_datareader\base.py:201: SymbolWarning: Failed to read
symbol: 'MSFT', replacing with NaN.
warnings.warn(msg.format(sym), SymbolWarning)
C:\Users\kjohn_000\Anaconda3\lib\site-packages\pandas_datareader\base.py:201: SymbolWarning: Failed to read symbol:
'SPY', replacing with NaN.
warnings.warn(msg.format(sym), SymbolWarning)
Traceback (most recent call last):
File "<ipython-input-2-0ddd75de0396>", line 1, in <module>
runfile('C:/Users/kjohn_000/.spyder-py3/temp.py',
wdir='C:/Users/kjohn_000/.spyder-py3')
File "C:\Users\kjohn_000\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 705, in runfile
execfile(filename, namespace)
File "C:\Users\kjohn_000\Anaconda3\lib\site-
packages\spyder\utils\site\sitecustomize.py", line 102, in execfile
exec(compile(f.read(), filename, 'exec'), namespace)
File "C:/Users/kjohn_000/.spyder-py3/temp.py", line 14, in <module>
panel_data = data.DataReader(tickers, dataSource, start_date, end_date)
File "C:\Users\kjohn_000\Anaconda3\lib\site-packages\pandas_datareader\data.py", line 137, in DataReader
session=session).read()
File "C:\Users\kjohn_000\Anaconda3\lib\site-
packages\pandas_datareader\base.py", line 186, in read
df = self._dl_mult_symbols(self.symbols)
File "C:\Users\kjohn_000\Anaconda3\lib\site-
packages\pandas_datareader\base.py", line 206, in _dl_mult_symbols
raise RemoteDataError(msg.format(self.__class__.__name__))
RemoteDataError: No data fetched using 'GoogleDailyReader'
为什么Pandas Datareader无法读取＆＃39;代码中的股票代码？清单？我现在几个小时都在寻找答案，但很多答案都是关于雅虎API的回答问题，剩下的答案要么是针对另一种语言，要么只是因为编码而已经超出我的深度（I＆＃ 39;相对较新的Python）。提前感谢您的帮助和反馈。
答案 0 :(得分：1)
这适用于Python 3.6.1
from pandas_datareader import data
import fix_yahoo_finance as yf
yf.pdr_override()
symbol = 'AMZN'
data_source='google'
start_date = '2010-01-01'
end_date = '2016-01-01'
df = data.get_data_yahoo(symbol, start_date, end_date)
print(df)
df.head()
这也适合我。
from urllib.request import urlopen
from bs4 import BeautifulSoup as bs
def get_historical_data(name, number_of_days):
data = []
url = "https://finance.yahoo.com/quote/" + name + "/history/"
rows = bs(urlopen(url).read()).findAll('table')[0].tbody.findAll('tr')
for each_row in rows:
divs = each_row.findAll('td')
if divs[1].span.text != 'Dividend': #Ignore this row in the table
#I'm only interested in 'Open' price; For other values, play with divs[1 - 5]
data.append({'Date': divs[0].span.text, 'Open': float(divs[1].span.text.replace(',',''))})
return data[:number_of_days]
#Test
for i in get_historical_data('googl', 25):
print(i)
答案 1 :(得分：0)
这不是使用Google，但是，如果您使用python YahooFinancials模块，则可以轻松地将金融数据加载到熊猫中。 YahooFinancials通过散列相关Yahoo Finance Page的数据存储对象来获取财务数据，因此它非常快速，构建良好，并且不依赖于旧的停产api或像web scraper一样的webdriver。数据以JSON返回。
$ pip安装yahoofinancials
用法示例：
from yahoofinancials import YahooFinancials
import pandas as pd
# Select Tickers and stock history dates
ticker = 'AAPL'
ticker2 = 'MSFT'
ticker3 = 'INTC'
index = '^NDX'
freq = 'daily'
start_date = '2012-10-01'
end_date = '2017-10-01'
# Function to clean data extracts
def clean_stock_data(stock_data_list):
new_list = []
for rec in stock_data_list:
if 'type' not in rec.keys():
new_list.append(rec)
return new_list
# Construct yahoo financials objects for data extraction
aapl_financials = YahooFinancials(ticker)
mfst_financials = YahooFinancials(ticker2)
intl_financials = YahooFinancials(ticker3)
index_financials = YahooFinancials(index)
# Clean returned stock history data and remove dividend events from price history
daily_aapl_data = clean_stock_data(aapl_financials.get_historical_stock_data(start_date, end_date, freq)[ticker]['prices'])
daily_msft_data = clean_stock_data(mfst_financials.get_historical_stock_data(start_date, end_date, freq)[ticker2]['prices'])
daily_intl_data = clean_stock_data(intl_financials.get_historical_stock_data(start_date, end_date, freq)[ticker3]['prices'])
daily_index_data = index_financials.get_historical_stock_data(start_date, end_date, freq)[index]['prices']
stock_hist_data_list = [{'NDX': daily_index_data}, {'AAPL': daily_aapl_data}, {'MSFT': daily_msft_data}, {'INTL': daily_intl_data}]
# Function to construct data frame based on a stock and it's market index
def build_data_frame(data_list1, data_list2, data_list3, data_list4):
data_dict = {}
i = 0
for list_item in data_list2:
if 'type' not in list_item.keys():
data_dict.update({list_item['formatted_date']: {'NDX': data_list1[i]['close'], 'AAPL': list_item['close'],
'MSFT': data_list3[i]['close'],
'INTL': data_list4[i]['close']}})
i += 1
tseries = pd.to_datetime(list(data_dict.keys()))
df = pd.DataFrame(data=list(data_dict.values()), index=tseries,
columns=['NDX', 'AAPL', 'MSFT', 'INTL']).sort_index()
return df