BTW 250 Crawling script

btw250crawl.py

from bs4 import BeautifulSoup
import requests
import time

NO_INFO = "We're sorry, there is currently no information available.  Please check back later."

last_updated = ""

while 1:
    r = requests.get('https://campusrec.illinois.edu/counts/')

    soup = BeautifulSoup(r.text)

    table = soup.find(id="rove_table")

    if NO_INFO in table.descendants:
        last_update = table.find('p').string.split()[2] + table.find('p').string.split()[3]
        print("There is no data for this runtime " + last_update)
    else:
        with open('btw250.dat', 'a') as f:
            write_buffer = []
            for tr in table.children:
                try:
                    arr = []
                    for td in tr.children:
                        if td.string is not None:
                            string = td.string.replace(u'\xa0', u'')
                            arr.append(string)
                    if(len(arr)) is 3:
                        write_buffer.append(arr[0] + " - " + arr[1] + " - " + arr[2])
                    elif len(arr) is 1:
                        checked = arr[0].split()[4] + arr[0].split()[5]
                        checked = checked.replace("(", "").replace(",", "")

                        if checked not in last_updated:
                            last_updated = checked
                            f.write("Updated at " + checked + '\n')
                            print("Updated at " + checked)
                            for line in write_buffer:
                                f.write(line + '\n')
                            f.write('\n')
                        else:
                            print "No update for time " + checked
                except AttributeError:
                    pass

    time.sleep(1800)