stundenplanparser.py

#!/usr/bin/env python
import re, urllib.request, sys
from html.parser  import HTMLParser
from urllib.error import HTTPError,URLError

class TableHTMLParser(HTMLParser):
    def __init__(self):
        super(TableHTMLParser,self).__init__()
        self.__interest = False
        self.__lastday  = "Montag"
        self.__partlist = []
        self.__record   = []
        self.plandict = {}

    def __add_record(self,day):
        if len(self.__record) > 0:
            self.plandict[self.__lastday] = self.__record
            self.__record = []
        self.__lastday = day

    def handle_starttag(self, tag, attrs):
        if tag == 'td' and ('class','data') in attrs:
            self.__interest = True

    def handle_endtag(self, tag):
        self.__interest = False

    def handle_data(self, data):
        if self.__interest:
            data = re.sub(r'-*','',data).strip()
            if data in ["Montag","Dienstag","Mittwoch","Donnerstag","Freitag"]:
                self.__add_record(data)
            elif data != '':
                self.__partlist.append(data)
                if re.search('F[A-Z][0-9]*',data):
                    self.__record.append(tuple(self.__partlist))
                    self.__partlist = []

    def feed(self,input_data):
        super(TableHTMLParser,self).feed(input_data)
        self.__add_record(self.__lastday)

    def print_table(self):
        for k,v in self.plandict.items():
            print(k)
            for t in v:
                print('{time:18} {room:15} {name:32} {prof}'.format(
                    time =  (t[0] + " bis " + t[1]),
                    room = t[-1],
                    name = t[2],
                    prof = t[-3]))

class Download():
    def __init__(self,**param):
        self.url = "http://www.hof-university.de/index.php?id=515&st={st}&fs={fs}&jahr=2012&semester=SS".format(**param)
        try:
            handle = urllib.request.urlopen(self.url)
            self.data = str(handle.read(),'UTF-8')
        except HTTPError as e:
            print("Unable to load URL:",e,self.url)
            sys.exit(-1)
        except URLError as e:
            print("Invalid URL:",e,self.url)
            sys.exit(-2)

if __name__ == '__main__':
    if len(sys.argv) < 3:
        print('{} <Studiengang> <Fachsemester>'.format(sys.argv[0]))
        sys.exit(-3)

    parser = TableHTMLParser()
    parser.feed(Download(**{
       'st': sys.argv[1],
       'fs': sys.argv[2]
    }).data)
    parser.print_table()