def scrape(self):
prefix = ntnu.prefix(self.semester)
groups = {}
courses = Course.objects.filter(semester=self.semester)
courses = {c.code: c for c in courses}
query = ('SELECT aktkode, studieprogramkode FROM '
'%s_akt_studieprogram') % prefix
for row in fetch.sql('ntnu', query):
groups.setdefault(row.aktkode, set()).add(row.studieprogramkode)
query = ('SELECT emnekode, typenavn, dag, start, slutt, uke, romnr, '
'romnavn, larer, aktkode FROM %s_timeplan ORDER BY emnekode, '
'dag, start, slutt, uke, romnavn, aktkode') % prefix
for row in fetch.sql('ntnu', query):
code, version = ntnu.parse_course(row.emnekode)
if not code:
logging.warning('Skipped invalid course name: %s',
row.emnekode)
continue
elif code not in courses:
logging.debug("Unknown course %s.", code)
continue
elif not self.should_proccess_course(code):
continue
yield {
'course':
courses[code],
'type':
row.typenavn,
'day':
utils.parse_day_of_week(row.dag),
'start':
utils.parse_time(row.start),
'end':
utils.parse_time(row.slutt),
'weeks':
utils.parse_weeks(row.uke),
'rooms':
zip(utils.split(row.romnr, '#'), utils.split(row.romnavn,
'#')),
'lecturers':
utils.split(row.larer, '#'),
'groups':
groups.get(row.aktkode, set())
}
def parse_row(tr, room_codes):
data = {}
for i, td in enumerate(tr.cssselect('td')):
if i == 0:
if td.attrib.get('colspan', 1) == '4':
lecture_type = utils.clean_string(td.text_content())
if lecture_type:
data['lecture_type'] = lecture_type
else:
time = td.cssselect('b')[0].text_content().strip()
raw_day, period = time.split(' ', 1)
raw_start, raw_end = period.split('-')
data['day'] = utils.parse_day_of_week(raw_day)
data['start'] = utils.parse_time(raw_start)
data['end'] = utils.parse_time(raw_end)
match = re.match('.*Uke: (.+)', td.text_content())
data['weeks'] = utils.parse_weeks(match.group(1))
elif i == 1 and len(td.cssselect('a')) > 0:
if len(td.cssselect('a')) > 1:
logging.warning('Multiple rooms links found, simply '
'using first one.')
a = td.cssselect('a')[0]
rooms = [a.text] + [e.tail for e in a]
data['rooms'] = []
for name in utils.clean_list(rooms, utils.clean_string):
if name not in room_codes:
data['rooms'].append((None, name))
continue
if len(room_codes[name]) > 1:
logging.warning(
'Multiple rooms with name %s, '
'simply using first code.', name)
data['rooms'].append((room_codes[name][0], name))
elif i == 2:
data['lecturers'] = [td.text] + [e.tail for e in td]
elif i == 3:
data['groups'] = [g.text_content() for g in td.cssselect('span')]
return data
def parse_row(tr, room_codes):
data = {}
for i, td in enumerate(tr.cssselect('td')):
if i == 0:
if td.attrib.get('colspan', 1) == '4':
lecture_type = utils.clean_string(td.text_content())
if lecture_type:
data['lecture_type'] = lecture_type
else:
time = td.cssselect('b')[0].text_content().strip()
raw_day, period = time.split(' ', 1)
raw_start, raw_end = period.split('-')
data['day'] = utils.parse_day_of_week(raw_day)
data['start'] = utils.parse_time(raw_start)
data['end'] = utils.parse_time(raw_end)
match = re.match('.*Uke: (.+)', td.text_content())
data['weeks'] = utils.parse_weeks(match.group(1))
elif i == 1 and len(td.cssselect('a')) > 0:
if len(td.cssselect('a')) > 1:
logging.warning('Multiple rooms links found, simply '
'using first one.')
a = td.cssselect('a')[0]
rooms = [a.text] + [e.tail for e in a]
data['rooms'] = []
for name in utils.clean_list(rooms, utils.clean_string):
if name not in room_codes:
data['rooms'].append((None, name))
continue
if len(room_codes[name]) > 1:
logging.warning('Multiple rooms with name %s, '
'simply using first code.', name)
data['rooms'].append((room_codes[name][0], name))
elif i == 2:
data['lecturers'] = [td.text] + [e.tail for e in td]
elif i == 3:
data['groups'] = [g.text_content() for g in td.cssselect('span')]
return data
def scrape(self):
prefix = ntnu.prefix(self.semester)
groups = {}
courses = Course.objects.filter(semester=self.semester)
courses = {c.code: c for c in courses}
query = ("SELECT aktkode, studieprogramkode FROM " "%s_akt_studieprogram") % prefix
for row in fetch.sql("ntnu", query):
groups.setdefault(row.aktkode, set()).add(row.studieprogramkode)
query = (
"SELECT emnekode, typenavn, dag, start, slutt, uke, romnr, "
"romnavn, larer, aktkode FROM %s_timeplan ORDER BY emnekode, "
"dag, start, slutt, uke, romnavn, aktkode"
) % prefix
for row in fetch.sql("ntnu", query):
code, version = ntnu.parse_course(row.emnekode)
if not code:
logging.warning("Skipped invalid course name: %s", row.emnekode)
continue
elif code not in courses:
logging.debug("Unknown course %s.", code)
continue
elif not self.should_proccess_course(code):
continue
yield {
"course": courses[code],
"type": row.typenavn,
"day": utils.parse_day_of_week(row.dag),
"start": utils.parse_time(row.start),
"end": utils.parse_time(row.slutt),
"weeks": utils.parse_weeks(row.uke),
"rooms": zip(utils.split(row.romnr, "#"), utils.split(row.romnavn, "#")),
"lecturers": utils.split(row.larer, "#"),
"groups": groups.get(row.aktkode, set()),
}
def scrape(self):
prefix = ntnu.prefix(self.semester)
groups = {}
courses = Course.objects.filter(semester=self.semester)
courses = dict((c.code, c) for c in courses)
query = ('SELECT aktkode, studieprogramkode FROM '
'%s_akt_studieprogram') % prefix
for row in fetch.sql('ntnu', query):
groups.setdefault(row.aktkode, set()).add(row.studieprogramkode)
query = ('SELECT emnekode, typenavn, dag, start, slutt, uke, romnr, '
'romnavn, larer, aktkode FROM %s_timeplan ORDER BY emnekode, '
'dag, start, slutt, uke, romnavn, aktkode') % prefix
for row in fetch.sql('ntnu', query):
code, version = ntnu.parse_course(row.emnekode)
if not code:
logging.warning('Skipped invalid course name: %s', row.emnekode)
continue
elif code not in courses:
logging.debug("Unknown course %s.", code)
continue
yield {'course': courses[code],
'type': row.typenavn,
'day': utils.parse_day_of_week(row.dag),
'start': utils.parse_time(row.start),
'end': utils.parse_time(row.slutt),
'weeks': utils.parse_weeks(row.uke),
'rooms': zip(utils.split(row.romnr, '#'),
utils.split(row.romnavn, '#')),
'lecturers': utils.split(row.larer, '#'),
'groups': groups.get(row.aktkode, set())}