Downloading stock prices from Google Finance

Question

import pandas as pd
import requests

from bs4 import BeautifulSoup
from datetime import datetime
import pandas_datareader.data as web

tickers
['MMM', 'ABT', 'ABBV', 'ACN', 'ATVI', 'AYI', 'ADBE', 'AMD', 'AAP', 'AES', 'AET', 'AMG', 'AFL', 'A', 'APD', 'AKAM', 'ALK', 'ALB', 'ARE', 'ALXN', 'ALGN', 'ALLE', 'AGN', 'ADS', 'LNT', 'ALL', 'GOOGL', 'GOOG', 'MO', 'AMZN', 'AEE', 'AAL', 'AEP', 'AXP', 'AIG', 'AMT', 'AWK', 'AMP', 'ABC', 'AME', 'AMGN', 'APH', 'APC', 'ADI', 'ANDV', 'ANSS', 'ANTM', 'AON', 'AOS', 'APA', 'AIV', 'AAPL', 'AMAT', 'APTV', 'ADM', 'ARNC', 'AJG', 'AIZ', 'T', 'ADSK', 'ADP', 'AZO', 'AVB', 'AVY', 'BHGE', 'BLL', 'BAC', 'BK', 'BAX', 'BBT', 'BDX', 'BRK.B', 'BBY', 'BIIB', 'BLK', 'HRB', 'BA', 'BWA', 'BXP', 'BSX', 'BHF', 'BMY', 'AVGO', 'BF.B', 'CHRW', 'CA', 'COG', 'CDNS', 'CPB', 'COF', 'CAH', 'CBOE', 'KMX', 'CCL', 'CAT', 'CBG', 'CBS', 'CELG', 'CNC', 'CNP', 'CTL', 'CERN', 'CF', 'SCHW', 'CHTR', 'CHK', 'CVX', 'CMG', 'CB', 'CHD', 'CI', 'XEC', 'CINF', 'CTAS', 'CSCO', 'C', 'CFG', 'CTXS', 'CLX', 'CME', 'CMS', 'KO', 'CTSH', 'CL', 'CMCSA', 'CMA', 'CAG', 'CXO', 'COP', 'ED', 'STZ', 'COO', 'GLW', 'COST', 'COTY', 'CCI', 'CSRA', 'CSX', 'CMI', 'CVS', 'DHI', 'DHR', 'DRI', 'DVA', 'DE', 'DAL', 'XRAY', 'DVN', 'DLR', 'DFS', 'DISCA', 'DISCK', 'DISH', 'DG', 'DLTR', 'D', 'DOV', 'DWDP', 'DPS', 'DTE', 'DRE', 'DUK', 'DXC', 'ETFC', 'EMN', 'ETN', 'EBAY', 'ECL', 'EIX', 'EW', 'EA', 'EMR', 'ETR', 'EVHC', 'EOG', 'EQT', 'EFX', 'EQIX', 'EQR', 'ESS', 'EL', 'ES', 'RE', 'EXC', 'EXPE', 'EXPD', 'ESRX', 'EXR', 'XOM', 'FFIV', 'FB', 'FAST', 'FRT', 'FDX', 'FIS', 'FITB', 'FE', 'FISV', 'FLIR', 'FLS', 'FLR', 'FMC', 'FL', 'F', 'FTV', 'FBHS', 'BEN', 'FCX', 'GPS', 'GRMN', 'IT', 'GD', 'GE', 'GGP', 'GIS', 'GM', 'GPC', 'GILD', 'GPN', 'GS', 'GT', 'GWW', 'HAL', 'HBI', 'HOG', 'HRS', 'HIG', 'HAS', 'HCA', 'HCP', 'HP', 'HSIC', 'HSY', 'HES', 'HPE', 'HLT', 'HOLX', 'HD', 'HON', 'HRL', 'HST', 'HPQ', 'HUM', 'HBAN', 'HII', 'IDXX', 'INFO', 'ITW', 'ILMN', 'IR', 'INTC', 'ICE', 'IBM', 'INCY', 'IP', 'IPG', 'IFF', 'INTU', 'ISRG', 'IVZ', 'IQV', 'IRM', 'JEC', 'JBHT', 'SJM', 'JNJ', 'JCI', 'JPM', 'JNPR', 'KSU', 'K', 'KEY', 'KMB', 'KIM', 'KMI', 'KLAC', 'KSS', 'KHC', 'KR', 'LB', 'LLL', 'LH', 'LRCX', 'LEG', 'LEN', 'LUK', 'LLY', 'LNC', 'LKQ', 'LMT', 'L', 'LOW', 'LYB', 'MTB', 'MAC', 'M', 'MRO', 'MPC', 'MAR', 'MMC', 'MLM', 'MAS', 'MA', 'MAT', 'MKC', 'MCD', 'MCK', 'MDT', 'MRK', 'MET', 'MTD', 'MGM', 'KORS', 'MCHP', 'MU', 'MSFT', 'MAA', 'MHK', 'TAP', 'MDLZ', 'MON', 'MNST', 'MCO', 'MS', 'MOS', 'MSI', 'MYL', 'NDAQ', 'NOV', 'NAVI', 'NTAP', 'NFLX', 'NWL', 'NFX', 'NEM', 'NWSA', 'NWS', 'NEE', 'NLSN', 'NKE', 'NI', 'NBL', 'JWN', 'NSC', 'NTRS', 'NOC', 'NCLH', 'NRG', 'NUE', 'NVDA', 'ORLY', 'OXY', 'OMC', 'OKE', 'ORCL', 'PCAR', 'PKG', 'PH', 'PDCO', 'PAYX', 'PYPL', 'PNR', 'PBCT', 'PEP', 'PKI', 'PRGO', 'PFE', 'PCG', 'PM', 'PSX', 'PNW', 'PXD', 'PNC', 'RL', 'PPG', 'PPL', 'PX', 'PCLN', 'PFG', 'PG', 'PGR', 'PLD', 'PRU', 'PEG', 'PSA', 'PHM', 'PVH', 'QRVO', 'PWR', 'QCOM', 'DGX', 'RRC', 'RJF', 'RTN', 'O', 'RHT', 'REG', 'REGN', 'RF', 'RSG', 'RMD', 'RHI', 'ROK', 'COL', 'ROP', 'ROST', 'RCL', 'CRM', 'SBAC', 'SCG', 'SLB', 'SNI', 'STX', 'SEE', 'SRE', 'SHW', 'SIG', 'SPG', 'SWKS', 'SLG', 'SNA', 'SO', 'LUV', 'SPGI', 'SWK', 'SBUX', 'STT', 'SRCL', 'SYK', 'STI', 'SYMC', 'SYF', 'SNPS', 'SYY', 'TROW', 'TPR', 'TGT', 'TEL', 'FTI', 'TXN', 'TXT', 'TMO', 'TIF', 'TWX', 'TJX', 'TMK', 'TSS', 'TSCO', 'TDG', 'TRV', 'TRIP', 'FOXA', 'FOX', 'TSN', 'UDR', 'ULTA', 'USB', 'UAA', 'UA', 'UNP', 'UAL', 'UNH', 'UPS', 'URI', 'UTX', 'UHS', 'UNM', 'VFC', 'VLO', 'VAR', 'VTR', 'VRSN', 'VRSK', 'VZ', 'VRTX', 'VIAB', 'V', 'VNO', 'VMC', 'WMT', 'WBA', 'DIS', 'WM', 'WAT', 'WEC', 'WFC', 'HCN', 'WDC', 'WU', 'WRK', 'WY', 'WHR', 'WMB', 'WLTW', 'WYN', 'WYNN', 'XEL', 'XRX', 'XLNX', 'XL', 'XYL', 'YUM', 'ZBH', 'ZION', 'ZTS']

data_source = 'google'
start='2017-01-01'
end = '2018-01-01'

for i in tickers:
    web.DataReader(i, data_source, start, end).to_csv(i+'.csv')

I am trying to download stock prices from Google Finance, and it kinda work and not in same time. (only 289 stocks out of 505 tickers are downloaded)

it says:

Traceback (most recent call last):
  File "C:\python36\mana.py", line 26, in <module>
    web.DataReader(i, data_source, start, end).to_csv(i+'.csv')
  File "C:\python36\lib\site-packages\pandas_datareader\data.py", line 315, in DataReader
    session=session).read()
  File "C:\python36\lib\site-packages\pandas_datareader\base.py", line 206, in read
    params=self._get_params(self.symbols))
  File "C:\python36\lib\site-packages\pandas_datareader\base.py", line 84, in _read_one_data
    out = self._read_url_as_StringIO(url, params=params)
  File "C:\python36\lib\site-packages\pandas_datareader\base.py", line 95, in _read_url_as_StringIO
    response = self._get_response(url, params=params)
  File "C:\python36\lib\site-packages\pandas_datareader\base.py", line 155, in _get_response
    raise RemoteDataError(msg)
pandas_datareader._utils.RemoteDataError: Unable to read URL: https://finance.google.com/finance/historical?q=LMT&startdate=Jan+01%2C+2017&enddate=Jan+01%2C+2018&output=csv
Response Text:
b'<!DOCTYPE html><html lang=en><meta charset=utf-8><meta name=viewport content="initial-scale=1, minimum-scale=1, width=device-width"><title>Error 400 (Not Found)!!1</title><style>*{margin:0;padding:0}html,code{font:15px/22px arial,sans-serif}html{background:#fff;color:#222;padding:15px}body{color:#222;text-align:unset;margin:7% auto 0;max-width:390px;min-height:180px;padding:30px 0 15px;}* > body{background:url(//www.google.com/images/errors/robot.png) 100% 5px no-repeat;padding-right:205px}p{margin:11px 0 22px;overflow:hidden}pre{white-space:pre-wrap;}ins{color:#777;text-decoration:none}a img{border:0}@media screen and (max-width:772px){body{background:none;margin-top:0;max-width:none;padding-right:0}}#logo{background:url(//www.google.com/images/branding/googlelogo/1x/googlelogo_color_150x54dp.png) no-repeat;margin-left:-5px}@media only screen and (min-resolution:192dpi){#logo{background:url(//www.google.com/images/branding/googlelogo/2x/googlelogo_color_150x54dp.png) no-repeat 0% 0%/100% 100%;-moz-border-image:url(//www.google.com/images/branding/googlelogo/2x/googlelogo_color_150x54dp.png) 0}}@media only screen and (-webkit-min-device-pixel-ratio:2){#logo{background:url(//www.google.com/images/branding/googlelogo/2x/googlelogo_color_150x54dp.png) no-repeat;-webkit-background-size:100% 100%}}#logo{display:inline-block;height:54px;width:150px}</style><div id="af-error-container"><a href=//www.google.com><span id=logo aria-label=Google></span></a><p><b>400.</b> <ins>That\xe2\x80\x99s an error.</ins><p>The requested URL was not found on this server. <ins>That\xe2\x80\x99s all we know.</ins></div>'

Why am I having this issue, and how can I download rest 200+ data?

Thank you!

Answer 1

Well, for some reason, Google don't seem to have the day-series price data for Lockheed Martin for 2017 (the ticker symbol your query failed on.)

Also, Google don't like automated queries on financial data: if I run your code I regularly get a response including the text "We're sorry... but your computer or network may be sending automated queries. To protect our users, we can't process your request right now."

If you just want the price data, one simple answer is to use Yahoo instead. Here's a test program (based on your code) that I ran on Yahoo, to check for how many of your symbols it could supply price data:

import pandas as pd
import requests
from bs4 import BeautifulSoup
from datetime import datetime
import pandas_datareader.data as web

data_source = 'yahoo'
start='2017-01-01'
end = '2018-01-01'

tickers = ['MMM', 'ABT', 'ABBV', 'ACN', 'ATVI', 'AYI', 'ADBE', 'AMD', 'AAP', 'AES', 'AET', 'AMG', 'AFL', 'A', 'APD', 'AKAM', 'ALK', 'ALB', 'ARE', 'ALXN', 'ALGN', 'ALLE', 'AGN', 'ADS', 'LNT', 'ALL', 'GOOGL', 'GOOG', 'MO', 'AMZN', 'AEE', 'AAL', 'AEP', 'AXP', 'AIG', 'AMT', 'AWK', 'AMP', 'ABC', 'AME', 'AMGN', 'APH', 'APC', 'ADI', 'ANDV', 'ANSS', 'ANTM', 'AON', 'AOS', 'APA', 'AIV', 'AAPL', 'AMAT', 'APTV', 'ADM', 'ARNC', 'AJG', 'AIZ', 'T', 'ADSK', 'ADP', 'AZO', 'AVB', 'AVY', 'BHGE', 'BLL', 'BAC', 'BK', 'BAX', 'BBT', 'BDX', 'BRK.B', 'BBY', 'BIIB', 'BLK', 'HRB', 'BA', 'BWA', 'BXP', 'BSX', 'BHF', 'BMY', 'AVGO', 'BF.B', 'CHRW', 'CA', 'COG', 'CDNS', 'CPB', 'COF', 'CAH', 'CBOE', 'KMX', 'CCL', 'CAT', 'CBG', 'CBS', 'CELG', 'CNC', 'CNP', 'CTL', 'CERN', 'CF', 'SCHW', 'CHTR', 'CHK', 'CVX', 'CMG', 'CB', 'CHD', 'CI', 'XEC', 'CINF', 'CTAS', 'CSCO', 'C', 'CFG', 'CTXS', 'CLX', 'CME', 'CMS', 'KO', 'CTSH', 'CL', 'CMCSA', 'CMA', 'CAG', 'CXO', 'COP', 'ED', 'STZ', 'COO', 'GLW', 'COST', 'COTY', 'CCI', 'CSRA', 'CSX', 'CMI', 'CVS', 'DHI', 'DHR', 'DRI', 'DVA', 'DE', 'DAL', 'XRAY', 'DVN', 'DLR', 'DFS', 'DISCA', 'DISCK', 'DISH', 'DG', 'DLTR', 'D', 'DOV', 'DWDP', 'DPS', 'DTE', 'DRE', 'DUK', 'DXC', 'ETFC', 'EMN', 'ETN', 'EBAY', 'ECL', 'EIX', 'EW', 'EA', 'EMR', 'ETR', 'EVHC', 'EOG', 'EQT', 'EFX', 'EQIX', 'EQR', 'ESS', 'EL', 'ES', 'RE', 'EXC', 'EXPE', 'EXPD', 'ESRX', 'EXR', 'XOM', 'FFIV', 'FB', 'FAST', 'FRT', 'FDX', 'FIS', 'FITB', 'FE', 'FISV', 'FLIR', 'FLS', 'FLR', 'FMC', 'FL', 'F', 'FTV', 'FBHS', 'BEN', 'FCX', 'GPS', 'GRMN', 'IT', 'GD', 'GE', 'GGP', 'GIS', 'GM', 'GPC', 'GILD', 'GPN', 'GS', 'GT', 'GWW', 'HAL', 'HBI', 'HOG', 'HRS', 'HIG', 'HAS', 'HCA', 'HCP', 'HP', 'HSIC', 'HSY', 'HES', 'HPE', 'HLT', 'HOLX', 'HD', 'HON', 'HRL', 'HST', 'HPQ', 'HUM', 'HBAN', 'HII', 'IDXX', 'INFO', 'ITW', 'ILMN', 'IR', 'INTC', 'ICE', 'IBM', 'INCY', 'IP', 'IPG', 'IFF', 'INTU', 'ISRG', 'IVZ', 'IQV', 'IRM', 'JEC', 'JBHT', 'SJM', 'JNJ', 'JCI', 'JPM', 'JNPR', 'KSU', 'K', 'KEY', 'KMB', 'KIM', 'KMI', 'KLAC', 'KSS', 'KHC', 'KR', 'LB', 'LLL', 'LH', 'LRCX', 'LEG', 'LEN', 'LUK', 'LLY', 'LNC', 'LKQ', 'LMT', 'L', 'LOW', 'LYB', 'MTB', 'MAC', 'M', 'MRO', 'MPC', 'MAR', 'MMC', 'MLM', 'MAS', 'MA', 'MAT', 'MKC', 'MCD', 'MCK', 'MDT', 'MRK', 'MET', 'MTD', 'MGM', 'KORS', 'MCHP', 'MU', 'MSFT', 'MAA', 'MHK', 'TAP', 'MDLZ', 'MON', 'MNST', 'MCO', 'MS', 'MOS', 'MSI', 'MYL', 'NDAQ', 'NOV', 'NAVI', 'NTAP', 'NFLX', 'NWL', 'NFX', 'NEM', 'NWSA', 'NWS', 'NEE', 'NLSN', 'NKE', 'NI', 'NBL', 'JWN', 'NSC', 'NTRS', 'NOC', 'NCLH', 'NRG', 'NUE', 'NVDA', 'ORLY', 'OXY', 'OMC', 'OKE', 'ORCL', 'PCAR', 'PKG', 'PH', 'PDCO', 'PAYX', 'PYPL', 'PNR', 'PBCT', 'PEP', 'PKI', 'PRGO', 'PFE', 'PCG', 'PM', 'PSX', 'PNW', 'PXD', 'PNC', 'RL', 'PPG', 'PPL', 'PX', 'PCLN', 'PFG', 'PG', 'PGR', 'PLD', 'PRU', 'PEG', 'PSA', 'PHM', 'PVH', 'QRVO', 'PWR', 'QCOM', 'DGX', 'RRC', 'RJF', 'RTN', 'O', 'RHT', 'REG', 'REGN', 'RF', 'RSG', 'RMD', 'RHI', 'ROK', 'COL', 'ROP', 'ROST', 'RCL', 'CRM', 'SBAC', 'SCG', 'SLB', 'SNI', 'STX', 'SEE', 'SRE', 'SHW', 'SIG', 'SPG', 'SWKS', 'SLG', 'SNA', 'SO', 'LUV', 'SPGI', 'SWK', 'SBUX', 'STT', 'SRCL', 'SYK', 'STI', 'SYMC', 'SYF', 'SNPS', 'SYY', 'TROW', 'TPR', 'TGT', 'TEL', 'FTI', 'TXN', 'TXT', 'TMO', 'TIF', 'TWX', 'TJX', 'TMK', 'TSS', 'TSCO', 'TDG', 'TRV', 'TRIP', 'FOXA', 'FOX', 'TSN', 'UDR', 'ULTA', 'USB', 'UAA', 'UA', 'UNP', 'UAL', 'UNH', 'UPS', 'URI', 'UTX', 'UHS', 'UNM', 'VFC', 'VLO', 'VAR', 'VTR', 'VRSN', 'VRSK', 'VZ', 'VRTX', 'VIAB', 'V', 'VNO', 'VMC', 'WMT', 'WBA', 'DIS', 'WM', 'WAT', 'WEC', 'WFC', 'HCN', 'WDC', 'WU', 'WRK', 'WY', 'WHR', 'WMB', 'WLTW', 'WYN', 'WYNN', 'XEL', 'XRX', 'XLNX', 'XL', 'XYL', 'YUM', 'ZBH', 'ZION', 'ZTS']
fail_count = 0
ok_count = 0

for ticker in tickers:
    try:
        result = web.DataReader('MMM', data_source, start, end)
        print ("got data for " + ticker + " " + repr(result.shape))
        ok_count += 1
    except:
        print ("did not get data for " + ticker)
        fail_count += 1

print repr(ok_count) + " loads, " + repr(fail_count) + " failures"

... and the answer is, all of them:

...
got data for XRX (251, 6)
got data for XLNX (251, 6)
got data for XL (251, 6)
got data for XYL (251, 6)
got data for YUM (251, 6)
got data for ZBH (251, 6)
got data for ZION (251, 6)
got data for ZTS (251, 6)
505 loads, 0 failures

Hope this may help.