Question

I wrote the following code to retrieve data about stocks in the S&P 500. The code works, but it is very slow due to the number of urlopen requests. What strategies can I use to speed this up?

from urllib.request import urlopen
import csv


class StockQuote:
    """gets stock data from Yahoo Finance"""

    def __init__(self, quote):
        self.quote = quote

    def lastPrice(self):
        url = 'http://finance.yahoo.com/d/quotes.csv?s={ticker}&f=l1'.format(ticker=self.quote)
        return bytes.decode((urlopen(url).read().strip()))

    def volume(self):
        url = 'http://finance.yahoo.com/d/quotes.csv?s={ticker}&f=v0'.format(ticker=self.quote)
        return bytes.decode((urlopen(url).read().strip()))

    def yearrange(self):
        url = 'http://finance.yahoo.com/d/quotes.csv?s={ticker}&f=w0'.format(ticker=self.quote)
        return bytes.decode((urlopen(url).read().strip()))

    def PEratio(self):
        url = 'http://finance.yahoo.com/d/quotes.csv?s={ticker}&f=r0'.format(ticker=self.quote)
        return bytes.decode((urlopen(url).read().strip()))

    def bookValue(self):
        url = 'http://finance.yahoo.com/d/quotes.csv?s={ticker}&f=b4'.format(ticker=self.quote)
        return bytes.decode((urlopen(url).read().strip()))

    def EBITDA(self):
        url = 'http://finance.yahoo.com/d/quotes.csv?s={ticker}&f=j4'.format(ticker=self.quote)
        return bytes.decode((urlopen(url).read().strip()))

    def PEGRatio(self):
        url = 'http://finance.yahoo.com/d/quotes.csv?s={ticker}&f=r5'.format(ticker=self.quote)
        return bytes.decode((urlopen(url).read().strip()))

    def ticker(self):
        url = 'http://finance.yahoo.com/d/quotes.csv?s={ticker}&f=s0'.format(ticker=self.quote)
        return bytes.decode((urlopen(url).read().strip()))


def openSP500file():
    SP500 = csv.reader(open(r'C:\Users\dev\Desktop\SP500.csv', 'r'), delimiter=',')
    for x in SP500:
        indStk = x[0]
        printdata(indStk)

def printdata(stk):
    stkObj = StockQuote(stk)
    stkdata= {}
    stkdata['Ticker'] = stkObj.ticker()
    stkdata['Price'] = stkObj.lastPrice()
    stkdata['PE Ratio'] = stkObj.PEratio()
    stkdata['Volume'] = stkObj.volume()
    stkdata['Year Range'] = stkObj.yearrange()
    stkdata['Book Value per Share'] = stkObj.bookValue()
    stkdata['EBITDA'] = stkObj.EBITDA()
    stkdata['PEG Ratio'] = stkObj.PEGRatio()
    print(stkdata)  

def main():
    openSP500file()


if __name__ == '__main__':
    main()

Thanks!

Answer 1

You can use threading or multiprocessing module to fetch all those URLs in same time, so you can save a lot of time since the fetching are all individual not related to others.