Yahoo python downloader wrapper. Refer to documentations: http://victorliew.quora.com/3-Ways-to-programatically-download-stuff-from-Yahoo-Financials (YQL, Yahoo Finance)

yahoo_finance_downloader.py

import sys
import os
import time
from datetime import datetime
import urllib2

"""
Use this function to allow applications to communicate via HTTP to the internet 
"""
def setProxy():
        #configure Credit- Suisse specific Agent here.
        internal_proxy_host = 'http://myproxy.com:8080'
        internal_proxy_protocol = 'http'
        proxy = urllib2.ProxyHandler({internal_proxy_protocol : internal_proxy_host})
        opener = urllib2.build_opener(proxy)
        opener.addheaders = [('User-agent', 'Mozilla/5.0')]
        return opener


"""
This function downloads historical data for a particular ticker
sample usage: get_historical_data("AAPL", datetime.strptime("20 Nov 00", "%d %b %y"), datetime.strptime("20 Nov 13", "%d %b %y"))
"""
def get_historical_data(symbol,fromDate, toDate):
        urlQuery = 'http://ichart.yahoo.com/table.csv?a='+ str(fromDate.month -1) +'&c='+ str(fromDate.year) +'&b=' + str(fromDate.day) + '&e='+  str(toDate.day) + '&d='+ str(toDate.month-1) +'&g=d&f=' + str(toDate.year) + '&s=' + symbol + '&ignore=.csv'
        print "Query: " + urlQuery
        
        opener = setProxy()        
        f = opener.open(urlQuery).read()
        print f


"""
This function Get spot price + earnings per share.
for other  details, refer to: http://www.gummy-stuff.org/Yahoo-data.htm
"""
def get_spot_data(symbol):
        numberOfAttempts = 0
        urlQuery = 'http://download.finance.yahoo.com/d/quotes.csv?s='+symbol+'&f=l1e&e=.cs'
        print "Query: " + urlQuery

        opener = setProxy()
        data = opener.open(urlQuery).read()
        print symbol + "," + data
        

"""
Extract tickers from file list. format of file should be:
<header in first line>
<ticker1><seperatpr><bla bla data>
<ticker2><seperatpr><bla bla data>
"""
def read_ticker_from_file(file_path, seperator):
        file = open(file_path)
        file.readline() #ignore header
        tickers = []
        for line in file:
                data = line.split(seperator)
                tickers.append(data[0])

        return tickers
        
"""
Program entry point goes here. 
"""
def main(argv=None):        
        print "Running Script " + sys.argv[0]
        #set ticker input file path 
        ticker_file_path = "//gbl.ad.hedani.net//home_ap$//jliew4$//Desktop//QuantResearchPlatform//public//python downloader//NASDAQ_TICKER.txt"
        ticker_list = read_ticker_from_file(ticker_file_path, '|')
        count = 1 
        for ticker in ticker_list:
                get_spot_data(ticker)

                # test top 10 tickers for now.
                if count > 10: 
                        break
                count += 1
                
                
        return 0

if __name__ == "__main__":
    main()