scrapMLBAM.py

from lxml import etree
import glob
import csv

# Input Files.
hipFiles  = glob.glob('*hip.xml')
gameFiles = glob.glob('*data.xml')

# Output File.
csvFile = open('hitsPerGame.csv', 'wb')

# CSV Writer.
writer = csv.writer( csvFile )

# XML Parser.
parser = etree.XMLParser( ns_clean = True )

# Lists were data will be stored.
h_desc = [] # Hit Description.
x_cord = [] # Hit x coordinate.
y_cord = [] # Hit y coordinate.
g_stad = [] # Stadium game was played in .
b_team = [] # Batting team.
g_num  = [] # Game number

for i in xrange( len( gameFiles ) ):
    
    # Game Data: Playing teams, Stadium.
    gameTree = etree.parse( gameFiles[i], parser )

    # hip Data: hip description, X & Y coordinates, Batting team.
    hipTree  = etree.parse( hipFiles[i], parser )
    
    h_desc.extend( hipTree.xpath( '//hip/@des' ) )
    x_cord.extend( hipTree.xpath( '//hip/@x' ) )
    y_cord.extend( hipTree.xpath( '//hip/@y' ) )

    # Check if team is guest or home, then set team name based on that.
    t_goh  = hipTree.xpath( '//hip/@team' )
    t_name = gameTree.xpath('//team/@name_brief')
                   
    # Extend stadium to fit number of hits. 
    g_stad.extend( gameTree.xpath('//stadium/@name') * len( t_goh ) )
    b_team.extend([ t_name[0] if j == 'H' else t_name[1] for j in t_goh ])

    # Game Number.
    g_num.extend( [i + 1] * len( t_goh ) )

data = zip( g_num, g_stad, b_team, x_cord, y_cord, h_desc ) 

# Add data to csv file.
for row in data:
    writer.writerow( row )

csvFile.close()