def sec_based(a, b, c=3600):
path = r'C:\StockData\Hourly'
if not os.path.exists(path):
os.makedirs(path)
warnings.filterwarnings("ignore")
url = "https://www.google.com/finance/getprices?i=%d&p=%dd&f=d,o,h,l,v,c&df=cpct&q=%s" % (
c, b, a)
csv = u(url).read()
temp = open('Stocktemp.csv', 'wb')
temp.write(csv)
temp.close()
temp = open('Stocktemp.csv', 'r')
lines = temp.readlines()
temp.close()
temp = open("Stocktemp.csv", 'w')
temp.write(lines[4][8:])
temp.write(lines[7][1:])
for i in lines[8:]:
temp.write(i)
temp.close()
d1 = pd.read_csv("Stocktemp.csv")
os.remove('Stocktemp.csv')
for i in range(1, d1.shape[0]):
d1['DATE'][i] = d1['DATE'][i - 1] + c
for i in range(d1.shape[0]):
d1["DATE"][i] = datetime.utcfromtimestamp(float(
d1["DATE"][i])).strftime('%Y-%m-%d %H:%M:%S')
d1.to_csv("%s\%s.csv" % (path, a), index=False)
def daily(a, b, c, d, e, f, g):
path = r'C:\StockData\Daily'
if not os.path.exists(path):
os.makedirs(path)
x = c - 1
y = f - 1
url = "http://real-chart.finance.yahoo.com/table.csv?s=%s&a=%d&b=%d&c=%d&d=%d&e=%d&f=%d&g=d&ignore=.csv" % (
a, x, b, d, y, e, g)
csv = u(url).read()
temp = open("%s\%s.csv" % (path, a), 'wb+')
temp.write(csv)
temp.close()
def bse():
import time
import zipfile
path = r'C:\StockData\StockList'
if not os.path.exists(path):
os.makedirs(path)
x = datetime.fromtimestamp(time.time())
if (x.weekday() < 2):
if ((x.day - 4) < 10):
temp = '0' + str(x.day - 4)
else:
temp = str(x.day - 4)
else:
if ((x.day - 2) < 10):
temp = '0' + str(x.day - 2)
else:
temp = str(x.day - 2)
if ((x.month < 10)):
temp += '0'
temp += str(x.month)
else:
temp += str(x.month)
temp += str(x.year % 1000)
url = "http://www.bseindia.com/download/BhavCopy/Equity/EQ%s_CSV.ZIP" % temp
csv = u(url).read()
temp1 = open('temp.zip', 'wb')
temp1.write(csv)
temp1.close()
temp1 = zipfile.ZipFile("temp.zip")
data = temp1.read("EQ%s.CSV" % temp)
temp1.close()
temp2 = open('Stocktemp.csv', 'wb')
temp2.write(data)
temp2.close()
df1 = pd.read_csv('Stocktemp.csv', usecols=('SC_CODE', 'SC_NAME'))
df1.to_csv(r"%s\BSElist.csv" % (path), index=False)
os.remove('Stocktemp.csv')
os.remove('temp.zip')
import os
from urllib2 import urlopen
from urllib import urlretrieve as u
from bs4 import BeautifulSoup
r = urlopen("http://tutorialspoint.com/tutorialslibrary.htm").read()
b = BeautifulSoup(r, 'html.parser')
ull = b.findAll('ul', {'class': 'menu'})
for ul in ull:
cd = ul['id']
os.mkdir(cd)
print "Creating Directory - %s" % cd
os.chdir(cd)
print "Working Directory - %s" % cd
links = ul.findAll('a')
for link in links:
try:
sub = link['href'].split("/")[1]
fname = sub + "_tutorial.pdf"
flink = "http://tutorialspoint.com/" + sub + "/" + fname
print "Processing Link - %s" % flink
u(flink, fname)
except Exception, e:
print "[!!] err - No PDF for " + str(link['href'])
continue
os.chdir("..")
"""Extracting Data from XML.
In this assignment you will write a Python program somewhat similar to
http://www.pythonlearn.com/code/geoxml.py.
"""
from urllib import urlopen as u
from xml.etree.ElementTree import fromstring as fs
default = 'http://python-data.dr-chuck.net/comments_297292.xml'
url = raw_input('Enter location: ') or default
data = u(url).read()
print 'Retrieving', url, "\nRetrieved", len(data), 'characters'
counts = fs(data).findall('.//count')
kounts = list()
for count in counts:
kounts.append(int(count.text))
Sum = reduce(lambda c, s: c + s, kounts)
print "Count: ", len(counts), "\nSum: "