Extracts student names and homerooms from a FirstClass directory's HTML source.

FirstClassParser.py

#!/usr/bin/env python

import sys

try:
    stream = open(sys.argv[1], 'r')
except:
    stream = sys.stdin

students = []
class Student:
    def __init__(self,str):
        self.first, self.last, self.hr = str.split(',')

for l in stream:
    l = l.split(';')
    out = ''
    for part in l:
        if '7' in part[0]:
            out += ','.join(part.split(':')[1][1:-1].split()) + ','
        if '1252' in part and '17' in part:
            students.append(Student(out + part.split(':')[1].split('`')[1][-3:]))

if stream is not sys.stdin:
    stream.close()

print 'last\tfirst\thr'
for student in students:
    print '\t'.join([student.last,student.first,student.hr])

print 'hr\tfirst\tlast'
for student in sorted(students, key=lambda student: student.hr):
    print '\t'.join([student.hr,student.first,student.last])