Downloads the course index of a Radboud prospectus and groups courses per quarter / semester.

courses_per_semester.py

#! /usr/bin/env python

import argparse
import urllib2
import re
from bs4 import BeautifulSoup

def setup_args():
    parser = argparse.ArgumentParser(description='Downloads the course index of a Radboud prospectus and groups courses per quarter / semester.')
    parser.add_argument('courselistURL',
        help='URL of the course list',
        nargs='?',
        default='http://www.studiegids.science.ru.nl/2013/science/prospectus/computing_science_master/courses/')
    return parser.parse_args()

def yn_choice(message, default='y'):
    ''' source: http://stackoverflow.com/a/4741730/1711232 '''
    choices = 'Y/n' if default.lower() in ('y', 'yes') else 'y/N'
    choice = raw_input("%s (%s) " % (message, choices))
    values = ('y', 'yes', '') if default == 'y' else ('y', 'yes')
    return choice.strip().lower() in values

def fetch_courses(url):
    html = urllib2.urlopen(url).read()
    soup = BeautifulSoup(html)
    thead = soup.find(text=re.compile("Gesorteerd op vaknaam"))
    table = thead.parent
    courses = []
    for course in table.find_next_sibling('table').find_all('a'):
        href = course.get('href')
        if href[0] == '/': #urls *sometimes* lack the domain
            href = "http://www.studiegids.science.ru.nl" + href
        courses.append((course.string, href))
    return courses
    
def get_q_by_url(url):
    html = urllib2.urlopen(url).read()
    soup = BeautifulSoup(html)
    scheduled = soup.find(text=re.compile("Scheduled|Periode"))
    if scheduled == None:
        return "Unknown"
    td = scheduled.parent.parent
    return list(td.children)[-1].strip()
    
def main(args):
    result = dict()
    courses = fetch_courses(args.courselistURL)
    if yn_choice("About to fetch "+str(len(courses))+" course pages. Continue?"):
        for course, url in courses:
            time = get_q_by_url(url)
            if time not in result:
                result[time] = [course]
            else:
                result[time].append(course)
        for timeslot in result:
            print '=====', timeslot, '====='
            for course in result[timeslot]:
                print course

if __name__ == "__main__":
    args = setup_args()
    main(args)