Script to parse VM Superhub status page HTML in to CSV

parse.py

#!/usr/bin/env python

from os import listdir
from os.path import isfile, join, splitext
import csv

from BeautifulSoup import BeautifulSoup

PATH = '.'

files = [f for f in listdir(PATH) if isfile(join(PATH, f)) and splitext(f)[1] == '.html']

with open('result.csv', 'w') as csvfile:
    csv_writer = csv.writer(csvfile)

    for filename in files:
        f = open(filename, 'r')
        soup = BeautifulSoup(f)
        f.close()

        row = []
        for td in soup.tbody.findAll('tr')[-1].findAll('td')[1:]:
            text = td.text
            if text == 'N/A': text = '0'
            row.append(int(text))
        row.append(sum(row)/len(row))

        datetime = '%s/%s/%s %s:00:00' % (filename[6:8], filename[4:6], filename[0:4], filename[9:11])
        row = [datetime] + row

        csv_writer.writerow(row)