Python - Stock Price Quote

주식시세 query

webservicex는 response가 간단해서 빠른편인데, data 자체는 realtime도 아니고 15-20분에 한번씩 update는것 같음.

Google finance는 response자체가 너무 복잡함. 시간이 좀 걸림. 개인적인 용도로는 상관없지만.

간단하게 빠르게 update되는 서버는 무료는 없을듯. Nasdaq에서 한달에 얼마씩 내면 준다고 함.

-------------

http://www.webservicex.net/stockquote.asmx/GetQuote?symbol=aapl

XML response example)

<string xmlns="http://www.webserviceX.NET/">

<StockQuotes>

<Stock>

<Symbol>aapl</Symbol>

<Last>109.06</Last>

<Date>9/29/2015</Date>

<Time>4:00pm</Time>

<Change>-3.38</Change>

<Open>112.79</Open>

<High>113.51</High>

<Low>107.86</Low>

<Volume>73365384</Volume>

<MktCap>621.94B</MktCap>

<PreviousClose>112.44</PreviousClose>

<PercentageChange>-3.01%</PercentageChange>

<AnnRange>92.00 - 134.54</AnnRange>

<Earns>8.65</Earns>

<P-E>12.62</P-E>

<Name>Apple Inc.</Name>

</Stock>

</StockQuotes>

*but from urllib2 read, all tags are UTF-9 encoded(llike corrupted) like below ==> HTML parser로 escape문자를 바꿔줘야함

<?xml version="1.0" encoding="utf-8"?>

<string xmlns="http://www.webserviceX.NET/">&lt;StockQuotes&gt;&lt;Stock&gt;&lt;Symbol&gt;AAPL&lt;/Symbol&gt;&lt;Last&gt

;109.06&lt;/Last&gt;&lt;Date&gt;9/29/2015&lt;/Date&gt;&lt;Time&gt;4:00pm&lt;/Time&gt;&lt;Change&gt;-3.38&lt;/Change&gt;&

lt;Open&gt;112.79&lt;/Open&gt;&lt;High&gt;113.51&lt;/High&gt;&lt;Low&gt;107.86&lt;/Low&gt;&lt;Volume&gt;73365384&lt;/Vol

ume&gt;&lt;MktCap&gt;621.94B&lt;/MktCap&gt;&lt;PreviousClose&gt;112.44&lt;/PreviousClose&gt;&lt;PercentageChange&gt;-3.0

1%&lt;/PercentageChange&gt;&lt;AnnRange&gt;92.00 - 134.54&lt;/AnnRange&gt;&lt;Earns&gt;8.65&lt;/Earns&gt;&lt;P-E&gt;12.6

2&lt;/P-E&gt;&lt;Name&gt;Apple Inc.&lt;/Name&gt;&lt;/Stock&gt;&lt;/StockQuotes&gt;</string>

-------------

Pattern matching in XML

import urllib2, time, os, re

import HTMLParser
def fetchStockPrice(ticker):
	url="http://www.webservicex.net/stockquote.asmx/GetQuote?symbol="
	txt=urllib2.urlopen(url+ticker).read()
	html_parser = HTMLParser.HTMLParser()
	parsed = html_parser.unescape(txt)
	#print parsed
	#unicode =  txt.encode('utf-8')
	#print unicode

	#result=re.search('(.*?)',parsed)
	result=re.search('([0-9]+\.[0-9]+)', parsed)
	if result:
		stockprice = result.group(1)
		cur_date = re.search('(.*?)',parsed)
		cur_time = re.search('(.*?)',parsed)
		ret = stockprice + " " + cur_date.group(1) + " " + cur_time.group(1)
	else:
		stockprice = "Nothing found for: " + ticker
		ret = "Nothing found for: " + ticker
	return ret

print ("NOW = " + time.ctime())
print "Stock Price is " + fetchStockPrice("AAPL") 

-------------

Just Pattern Matching Python code

import  urllib2, time, os, re
def fetchStockPrice(ticker):
	url="http://www.webservicex.net/stockquote.asmx/GetQuote?symbol="
	txt=urllib2.urlopen(url+ticker).read()
	#f=open("sample.xml")
	#txt = f.read()
	#print txt
	#result=re.search('(.*?)',txt)
	result=re.search('([0-9]+\.[0-9]+)',txt)
	#result=re.search("Last\>(\d+\.\d+)\</Last", txt)
	if result:
		stockprice = result.group(1)
	else:
		stockprice = "Nothing found for: " + ticker
	return stockprice

print(time.ctime())
print fetchStockPrice("AAPL") 

-------------

XML parsing example

https://docs.python.org/2/library/xml.dom.minidom.html?highlight=xml.dom.minidom#module-xml.dom.minidom

import xml.dom.minidom

document = """\

	
		aapl
		109.06
		9/29/2015
		4:00pm
		-3.38
		112.79
		113.51
		107.86
		73365384
		621.94B
		112.44
		-3.01%
		92.00 - 134.54
		8.65
		12.62
		Apple Inc.
	

"""

def getText(nodelist):
    rc = []
    for node in nodelist:
        if node.nodeType == node.TEXT_NODE:
            rc.append(node.data)
    return ''.join(rc)

def getStockPrice(quote):
	 print "Last Stock Price is :" % getText(quote.childNodes)

def handleToc(stocks):
    for stock in stocks:
		symbol = stock.getElementsByTagName("Symbol")[0]
		print "
%s
" % getText(symbol.childNodes)

		last = stock.getElementsByTagName("Last")[0]
		print "
%s
" % getText(last.childNodes)

		date = stock.getElementsByTagName("Date")[0]
		print "
%s
" % getText(date.childNodes)

		time = stock.getElementsByTagName("Time")[0]
		print "
%s
" % getText(time.childNodes)

dom = xml.dom.minidom.parseString(document)
stocks = dom.getElementsByTagName("Stock")
handleToc(stocks)

-------------

Stock Quote from Google finance

import urllib2, time, os, re, csv
 
def fetchGF(googleticker):
	url="http://www.google.com/finance?&q="
	txt=urllib2.urlopen(url+googleticker).read()
	#print txt
	#search phase 112.44
	k=re.search('id="ref_(.*?)">(.*?)<',txt)
	#print k
	if k:
		tmp1=k.group(0)
		tmp2=k.group(1)
		#print tmp1
		#print tmp2
		tmp=k.group(2)
		#print tmp
		q=tmp.replace(',','')
		#print q
	else:
		q="Nothing found for: "+googleticker
	return q
	
print(time.ctime())
print fetchGF("AAPL")
#print fetchGF("NASDAQ:AAPL")

-------------

Stock Portfolio를 query하려면

#file에서 읽어도 좋겠다.
tickers=["NASDAQ:AAPL","NASDAQ:GOOG","NASDAQ:BIDU","NYSE:IBM", \
         "NASDAQ:INTC","NASDAQ:MSFT","NYSEARCA:SPY"]

for ticker in tickers:
	data=combine(ticker)
	print(data)

-------------

 xmlparsing_finished.py

-------------

import urllib2, time, os, re
import HTMLParser
def fetchStockPrice(ticker):
    url="http://www.webservicex.net/stockquote.asmx/GetQuote?symbol="
    txt=urllib2.urlopen(url+ticker).read()
    html_parser = HTMLParser.HTMLParser()
    parsed = html_parser.unescape(txt)
    #print parsed
    #unicode =  txt.encode('utf-8')
    #print unicode
 
    #result=re.search('(.*?)',parsed)
    result=re.search('([0-9]+\.[0-9]+)', parsed)
    if result:
        stockprice = result.group(1)
        cur_date = re.search('(.*?)',parsed)
        cur_time = re.search('(.*?)',parsed)
        cur_percent = re.search('(.*?)',parsed)
        #Text formatting
        ret = '{:4s}: {:7s} {:7s} - {:10s} {:7s}'.format(ticker, stockprice, cur_percent.group(1), cur_date.group(1), cur_time.group(1))
        #ret =  '{:4s}'.format(ticker) + ": " +stockprice + " " + cur_percent.group(1) + " " + cur_date.group(1) + " " + cur_time.group(1)
    else:
        stockprice = "Nothing found for: " + ticker
        ret = "Nothing found for: " + ticker
    return ret
 
print(time.ctime())

#tickers=["NASDAQ:AAPL","NASDAQ:GOOG","NASDAQ:QCOM","NYSE:NUAN", \
#         "NASDAQ:INTC","NYSE:DAL","NYSE:F", "NYSE:SMI", "NASDAQ:HQCL", "NYSEARCA:UCO"]
tickers=["AAPL","GOOG","QCOM","NUAN", \
         "INTC","DAL","F", "SMI", "HQCL", "UCO"]
print ("--------------------------")
#print fetchStockPrice("AAPL")
for ticker in tickers:
    data=fetchStockPrice(ticker)
    print(data)
print ("--------------------------") 

-------------

stockprices.py