Download Option Data from Yahoo Finance

from lxml.html import parse
from urllib2 import urlopen
import pandas as pd

def unpack(row, kind='td'):
    elts = row.findall('.//%s' % kind)
    return [val.text_content() for val in elts]

optionurl = 'http://finance.yahoo.com/q/op?s=AAPL&date=1429833600'

parsed = parse(urlopen(optionurl))
doc = parsed.getroot()

tables = doc.findall('.//table')

########################################
# process call option data
########################################
table = tables[1]
rows = table.findall('.//tr')
calldata = []

# generate header for the table
header_raw = unpack(rows[0],'th')
header = []
for colname in header_raw:
    colname_raw = colname.split('\n')
    if len(colname_raw)==1:
        header.append(colname_raw[0])
    else:
        header.append(colname_raw[2].strip())

# get data
rows = rows[2:]
for row in rows:
    data_raw = unpack(row,'td')
    calldata.append([item.strip() for item in data_raw])
    
calls = pd.DataFrame(calldata, columns=header)
    
########################################
# process put option data
########################################       
table = tables[2]
rows = table.findall('.//tr')
putdata = []

# generate header for the table
header_raw = unpack(rows[0],'th')
header = []
for colname in header_raw:
    colname_raw = colname.split('\n')
    if len(colname_raw)==1:
        header.append(colname_raw[0])
    else:
        header.append(colname_raw[2].strip())

# get data
rows = rows[2:]
for row in rows:
    data_raw = unpack(row,'td')
    putdata.append([item.strip() for item in data_raw])
    
puts = pd.DataFrame(putdata, columns=header)

related links:

http://python4econ.blogspot.hk/2013/02/building-stock-options-historical.html

http://www.pythoncentral.io/python-beautiful-soup-example-yahoo-finance-scraper/

http://blog.nag.com/2013/10/implied-volatility-using-pythons-pandas.html

http://nycdatascience.com/students-work/python-multiprocessing-and-monte-carlo-option-pricing/