we needz jorbs!

gistfile1.py

#!/usr/bin/python2.7

from BeautifulSoup import BeautifulSoup
import urllib2
import re
import time

pause = 30 #seconds
awesum_jorbs = {}


def sub_signal(jorb_id):
    print("New Job: {0}, {1}, {2}.".format(*awesum_jorbs[jorb_id]))
    


while(True):

    f = urllib2.urlopen('https://employment.pps.k12.or.us/ats/job_board?refresh=Y&COMPANY_ID=00002736&APPLICANT_TYPE_ID=00000001')

    s = f.readlines()

    f.close()

    soup = BeautifulSoup(''.join(s))

    jorbs = soup.findAll('tr')
    jorbs = jorbs[2:]

    #the dumb thing here is to len(jorbs) 
    #the smart thing would be to parse it and make content of text message out of info
        #uhoh, what if one gets removed and another added? better go by name
        #fuck it, throw 'er in a dict and move on with our lives

    for jorb in jorbs:

        jorb_dept = jorb.contents[-2].string

        jorb_title = jorb.contents[-4].string
        
        jorb_link = jorb.contents[1].contents[0].attrs[0][1]

        jorb_id = int(re.search('210000\d\d\d\d', jorb_link).group(0))


        if jorb_id not in awesum_jorbs:
            awesum_jorbs[jorb_id] = (jorb_title, jorb_dept, jorb_link)
            sub_signal(jorb_id)

    print("Pausing for {0:03.2f} minutes.".format(pause / 60.))
    time.sleep(pause)