Commit 8767a8cf authored by Julian Rother's avatar Julian Rother

Add rwth-online-importer

parent a1fd6f0c
......@@ -111,20 +111,65 @@ def fetch_co_course_events(i):
# it is parsed.
return events
def fetch_ro_event_ical(ids):
data = {'pMode': 'T', 'pInclPruef': 'N', 'pInclPruefGepl': 'N', 'pOutputFormat': '99', 'pCharset': 'UTF8', 'pMaskAction': 'DOWNLOAD'}
data = list(data.items())
for id in ids:
data.append(('pTerminNr', id))
data = urllib.parse.urlencode(data).encode('utf-8')
r = urllib.request.Request('https://online.rwth-aachen.de/RWTHonline/pl/ui/%24ctx/wbKalender.wbExport',
data=data, method='POST')
with urllib.request.urlopen(r) as f:
return f.read().decode('utf-8')
def fetch_ro_course_ical(id):
from lxml import html
url = 'https://online.rwth-aachen.de/RWTHonline/pl/ui/%24ctx/wbTermin_List.wbLehrveranstaltung?pStpSpNr='+'%i'%(int(id))
req = urllib.request.urlopen(url)
dom = html.fromstring(req.read())
event_ids = [x.value for x in dom.xpath('//input[@name="pTerminNr"]')]
return fetch_ro_event_ical(event_ids)
def fetch_ro_course_events(item):
import icalendar
# First fix crappy javascript fragment-Paths
url = urllib.parse.urlparse(item['url'].replace('#/', ''))
args = urllib.parse.parse_qs(url.query)
if 'pStpSpNr' in args: # Legacy URLs
id = args['pStpSpNr'][0]
elif url.path.split('/')[-2] == 'courses': # New URLs
id = url.path.split('/')[-1]
else:
flash("Ungültige URL: '"+i['url']+"'")
cal = icalendar.Calendar().from_ical(fetch_ro_course_ical(id))
events = []
for comp in cal.subcomponents:
if comp.name != 'VEVENT':
continue
if comp.get('STATUS') != 'CONFIRMED':
continue
e = {}
e['place'] = str(comp.get('LOCATION', ''))
e['time'] = comp['DTSTART'].dt # TODO: tz
e['duration'] = int((comp['DTEND'].dt - comp['DTSTART'].dt).seconds/60)
e['title'] = item['type']
events.append(e)
return events
@app.route('/internal/import/<int:id>/now', methods=['GET', 'POST'])
@mod_required
def import_from(id):
courses = query('SELECT * FROM courses WHERE id = ?', id)[0]
lectures = query('SELECT * FROM lectures WHERE course_id = ?', courses['id'])
import_campus = query('SELECT * FROM import_campus WHERE course_id = ?',id)
events = []
try:
# if u have to port this to anything new, god be with you.
for i in import_campus:
events += fetch_co_course_events(i)
if 'www.campus.rwth-aachen.de' in i['url']:
events += fetch_co_course_events(i)
else:
events += fetch_ro_course_events(i)
except ImportError:
flash('python-lxml not found, campus import will not work.')
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment