4 files changed, 464 insertions, 0 deletions
diff --git a/crawl/analyze.py b/crawl/analyze.py
new file mode 100644
index 0000000..add1484
--- /dev/null
+++ b/crawl/analyze.py
@@ -0,0 +1,122 @@
+import time
+import json
+
+with open("subjects.json", 'r') as f:
+  subjects = json.load(f);
+
+with open("teachers.json", 'r') as f:
+  teachers=json.load(f);
+
+with open("timetables.json", 'r') as f:
+  timetables=json.load(f);
+
+
+allteachers = teachers["teachers"];
+myteachers = [];
+for teacher in allteachers:
+  fullname = teacher["teacher"]["displayName"];
+  try:
+    [surname, firstname] = fullname.split();
+  except ValueError:
+    surname = "";
+    firstname = "";
+  faculty = teacher["departments"][0]["shortName"] if teacher["departments"] else "";
+  myteachers.append({"fullname": fullname,
+    "surname": surname,
+    "firstname": firstname,
+    "faculty": faculty});
+
+with open("myteachers.json", 'w') as f:
+  json.dump(myteachers, f);
+
+myfaculties=[];
+allfaculties = teachers["departments"];
+for faculty in allfaculties:
+  shortname = faculty["shortName"];
+  longname  = faculty["displayName"];
+  myfaculties.append({"shortname": shortname, "longname": longname});
+with open("myfaculties.json", 'w') as f:
+  json.dump(myfaculties, f);
+
+
+myrealteachers=set();
+mytimetable={};
+myrooms={};
+mycourses=[];
+for course in timetables:
+  melpomeid = course.get("id", course.get("melpomeid"));
+  shortname = course["shortname"];
+  longname =  course["longname"];
+  timetable = course["timetable"];
+  days=timetable["days"];
+  courseteachers=set();
+  courserooms=set();
+  courseklassen=set();
+  courseslots=[];
+  for day in days:
+    grids=day["gridEntries"];
+    for grid in grids:
+      if grid["position1"]:
+        for klasse in grid["position1"]:
+          if not klasse.get("current"):
+            continue;
+          klassenname=klasse["current"]["displayName"];
+          courseklassen.add(klassenname)
+      if grid["position2"]:
+        for room in grid["position2"]:
+          if not room.get("current"):
+            continue;
+          roomname=room["current"]["displayName"];
+          roomlongname=room["current"]["longName"];
+          myrooms[roomname] = roomlongname;
+          courserooms.add(roomname);
+      cteachers=grid["position3"];
+      if cteachers :
+        for teacher in cteachers:
+          if not teacher.get("current"):
+            continue;
+          teachername=teacher["current"]["displayName"];
+          print(teachername);
+          myrealteachers.add(teachername);
+          courseteachers.add(teachername);
+      duration=grid["duration"];
+      courseslots.append({"teachers": list(courseteachers),
+        "rooms": list(courserooms),
+        "klassen": list(courseklassen),
+        "info": grid["lessonInfo"],
+        "time": duration});
+  mycourses.append({"melpomeid": melpomeid,
+    "shortname": shortname,
+    "longname": longname,
+#    "timetable": timetable,
+    "slots": courseslots});
+
+#print(mycourses);
+
+with open("mycourses.json", 'w') as f:
+  json.dump(mycourses, f);
+
+myrealcourses=[];
+for c in mycourses:
+  if len(c["slots"]) > 0 :
+    myrealcourses.append(c);
+
+with open("myrealcourses.json", 'w') as f:
+  json.dump(myrealcourses, f);
+
+myrealteachers_upper = {name.upper() for name in myrealteachers};
+myteachersincourses=[];
+for teacher in myteachers:
+  fullname = teacher["fullname"];
+  if fullname.upper() in myrealteachers_upper :
+    myteachersincourses.append(teacher);
+
+with open("myrealteachers.json", 'w') as f:
+  json.dump(myteachersincourses, f);
+
+print("Total number of courses: " + str(len(mycourses)));
+print("Courses in timetable: " + str(len(myrealcourses)));
+print("Total number of teachers: " + str(len(myteachers)));
+print("Teachers in timetable: " + str(len(myteachersincourses)));
+
+
diff --git a/crawl/crawl.py b/crawl/crawl.py
new file mode 100644
index 0000000..49cce83
--- /dev/null
+++ b/crawl/crawl.py
@@ -0,0 +1,96 @@
+from selenium import webdriver
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from dotenv import load_dotenv
+import requests
+import json
+import os
+
+load_dotenv()
+
+username = os.environ["WEBUNTIS_USER"]
+password = os.environ["WEBUNTIS_PASS"]
+
+driver = webdriver.Chrome()
+driver.get("https://tha.webuntis.com/WebUntis/#/basic/login")
+
+wait = WebDriverWait(driver, 15)
+
+user_input = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, "input.un-input-group__input[type='text']")))
+pass_input = driver.find_element(By.CSS_SELECTOR, "input.un-input-group__input[type='password']")
+
+user_input.send_keys(username)
+pass_input.send_keys(password)
+
+login_btn = driver.find_element(By.XPATH, "//button[contains(@class, 'redesigned-button__primary') and text()='Login']")
+login_btn.click()
+
+# Wait until login completes
+wait.until(EC.url_changes("https://tha.webuntis.com/WebUntis/#/basic/login"))
+
+# Get Bearer token in the browser before closing
+driver.set_script_timeout(15)
+bearer_token = driver.execute_async_script("""
+    var callback = arguments[arguments.length - 1];
+    var xhr = new XMLHttpRequest();
+    xhr.open('GET', '/WebUntis/api/token/new');
+    xhr.onload = function() { callback(xhr.responseText); };
+    xhr.send();
+""")
+print(f"Token: {bearer_token[:50]}...")
+
+cookies = driver.get_cookies()
+driver.quit()
+
+s = requests.Session()
+for cookie in cookies:
+    s.cookies.set(cookie['name'], cookie['value'], domain=cookie.get('domain', ''))
+
+BASE = "https://tha.webuntis.com/WebUntis"
+
+headers = {
+    "Authorization": f"Bearer {bearer_token}",
+}
+
+print("Teachers")
+result = s.get(f"{BASE}/api/rest/view/v1/timetable/filter?resourceType=TEACHER&timetableType=STANDARD", headers=headers)
+teachers = result.json()
+with open("teachers.json", 'w') as f:
+    json.dump(teachers, f)
+
+print("Subjects")
+result = s.get(f"{BASE}/api/rest/view/v1/timetable/filter?resourceType=SUBJECT&timetableType=STANDARD", headers=headers)
+subjects = result.json()
+with open("subjects.json", 'w') as f:
+    json.dump(subjects, f)
+
+DATE_START = "2026-03-16"
+DATE_END = "2026-03-21"
+
+print("Timetables by subject (format=2: class, room, teacher)")
+timetables = []
+for sj in subjects["subjects"]:
+    subject = sj["subject"]
+    sid = subject["id"]
+    shortname = subject["shortName"]
+    longname = subject["longName"]
+    print(longname)
+    result = s.get(
+        f"{BASE}/api/rest/view/v1/timetable/entries"
+        f"?start={DATE_START}&end={DATE_END}&format=2"
+        f"&resourceType=SUBJECT&resources={sid}"
+        f"&periodTypes=&timetableType=STANDARD",
+        headers=headers)
+    timetable = result.json()
+    timetables.append({
+        "id": sid,
+        "shortname": shortname,
+        "longname": longname,
+        "timetable": timetable,
+    })
+
+with open("timetables.json", 'w') as f:
+    json.dump(timetables, f)
+
+print("Done")
diff --git a/crawl/get.py b/crawl/get.py
new file mode 100644
index 0000000..2f72ef1
--- /dev/null
+++ b/crawl/get.py
@@ -0,0 +1,75 @@
+from selenium import webdriver
+from selenium.webdriver.common.by import By
+import requests
+import time
+import json
+
+driver = webdriver.Chrome()
+driver.get("https://melpomene.webuntis.com/WebUntis/?school=HS-Augsburg#/basic/timetablePublic")
+
+time.sleep(5)
+
+cookies = driver.get_cookies()
+
+s = requests.Session()
+for cookie in cookies:
+    s.cookies.set(cookie['name'], cookie['value'])
+
+myheaders = {
+    "Accept": "application/json, text/plain, */*",
+    "anonymous-school": "HS-Augsburg"}
+
+myrealteachers=set();
+myrooms={};
+mycourses=[];
+
+melpomeid = 14880;
+shortname="FredK";
+longname="FredL";
+
+result = s.get("https://melpomene.webuntis.com/WebUntis/api/rest/view/v1/timetable/entries?start=2025-04-07&end=2025-04-12&format=3&resourceType=SUBJECT&resources=" + str(melpomeid) + "&periodTypes=&timetableType=STANDARD",
+  headers=myheaders);
+timetable = json.loads(result.text);
+print(timetable);
+days=timetable["days"];
+courseteachers=set();
+courserooms=set();
+courseklassen=set();
+courseslots=[];
+for day in days:
+  grids=day["gridEntries"];
+  for grid in grids:
+    print(grid);
+    teachers=grid["position2"];
+    for teacher in teachers: 
+      teachername=teacher["current"]["displayName"];
+      print(teachername);
+      courseteachers.add(teachername);
+    try:
+      for room in grid["position3"]:
+        roomname=room["current"]["displayName"];
+        roomlongname=room["current"]["longName"];
+        print(roomname);
+        myrooms[roomname] = roomlongname;
+        courserooms.add(roomname);
+    except TypeError:
+      print("Cannot handle: ");
+      print(grid);
+      pass;
+    for klasse in grid["position1"]:
+      klassenname=klasse["current"]["displayName"];
+      print(klassenname);
+    courseklassen.add(klassenname)
+    duration=grid["duration"];
+    print(duration);
+    courseslots.append({"teachers": list(courseteachers),
+      "rooms": list(courserooms),
+      "klassen": list(courseklassen),
+      "time": duration});
+mycourses.append({"melpomeid": melpomeid,
+    "shortname": shortname,
+    "longname": longname,
+    "slots": courseslots});
+
+print(mycourses);
+
diff --git a/crawl/wp.py b/crawl/wp.py
new file mode 100644
index 0000000..55d33e0
--- /dev/null
+++ b/crawl/wp.py
@@ -0,0 +1,171 @@
+import json
+from datetime import datetime
+
+# PDF courses: (SP, Name, Dozent, SWS, CP, Turnus, shortname in WebUntis)
+# Only courses with SoSe or WiSe/SoSe turnus are relevant
+PDF_COURSES = [
+    # Aufbau
+    ("Aufbau", "Praktikum Messtechnik", "Großmann", 2, 2, "SoSe", "E-MT.PR"),
+    # Automat./Robotik
+    ("Autom./Robotik", "Antriebstechnik", "Meyer", 4, 5, "SoSe", "E-ANT"),
+    ("Autom./Robotik", "Automatisierungstechnik 1", "Zeller / Danzer", 4, 5, "WiSe/SoSe", "E-AUT.1"),
+    ("Autom./Robotik", "Praktikum Automatisierungstechnik", "Zeller / Danzer", 2, 2, "WiSe/SoSe", "E-AUT.PR"),
+    ("Autom./Robotik", "Robot Systems Engineering", "Dietrich", 4, 5, "SoSe", "E-RSE"),
+    # Elektronik
+    ("Elektronik", "Automobilelektronik", "Schurk", 2, 2, "WiSe/SoSe", "E-%AUTOM"),
+    ("Elektronik", "Formula Student Electric", "Markgraf", 4, 5, "WiSe/SoSe", None),
+    ("Elektronik", "Fortgeschrittene Messtechnik", "Großmann", 4, 5, "SoSe", "E-FMT"),
+    ("Elektronik", "Schaltungstechnik", "Zedler", 4, 5, "WiSe/SoSe", "E-SCHT"),
+    ("Elektronik", "Elektrische Maschinen", "Meyer", 4, 5, "SoSe", "E-ELMA"),
+    # Energietechnik
+    ("Energietechnik", "Erneuerbare Energien", "Schwägerl", 4, 5, "SoSe", "E-EREN"),
+    ("Energietechnik", "Praktikum Erneuerbare Energien", "Schwägerl", 2, 2, "WiSe/SoSe", "E-EREN.PR"),
+    ("Energietechnik", "Hochspannungstechnik", "Finkel", 4, 5, "SoSe", "E-HST"),
+    ("Energietechnik", "Leistungselektronik", "Ritter", 4, 5, "SoSe", "E-LE"),
+    # Information
+    ("Information", "Eingebettete Echtzeitsysteme mit Praktikum", "Werthschulte", 4, 5, "SoSe", "E-EES"),
+    ("Information", "Künstliche Intelligenz: Grundlagen und Anwendungen", "Legat", 4, 5, "SoSe", None),
+    ("Information", "Digitale Zwillinge: Grundkonzepte und Anwendungen", "Legat", 4, 5, "SoSe", "E-DIGTWIN"),
+    ("Information", "Industrial Security Basics", "Hollmann", 4, 5, "SoSe", "E-IS1C5"),
+    ("Information", "Matlab/Simulink", "Werthschulte", 2, 2, "WiSe/SoSe", "E-MATLAB"),
+    # Kommunikation
+    ("Kommunikation", "Digitale Kommunikation mit Praktikum", "Kamuf", 4, 5, "SoSe", "E-DIGK"),
+    ("Kommunikation", "Hochfrequenz-Schaltungstechnik mit Praktikum", "Stolle", 4, 5, "SoSe", "E-HFSCH"),
+    ("Kommunikation", "Hochfrequenzsysteme mit Praktikum", "Stolle", 4, 5, "SoSe", "E-HFSYS"),
+    ("Kommunikation", "Funktechnik in der Praxis", "Bögl", 2, 2, "SoSe", None),
+    # Übergreifend
+    ("Übergreifend", "Fertigungstechnik", "Dietrich", 4, 5, "SoSe", "E-FT"),
+    ("Übergreifend", "Systems Engineering", "Frommelt", 4, 5, "WiSe/SoSe", None),
+    ("Übergreifend", "Elektrokonstruktion mit E-Plan", "Danzer / Voicau-Ottlik", 2, 2, "SoSe", "E-%EPLAN"),
+    ("Übergreifend", "Elektronikproduktion", "Dietrich / Baur", 2, 2, "SoSe", "E-EP"),
+    ("Übergreifend", "Systemdenken im Produktentstehungsprozess", "Königbauer", 4, 5, "SoSe", "E-THINK"),
+    ("Übergreifend", "Advanced Topics in Electrical Engineering", "Gastdozierende", 2, 2, "WiSe/SoSe", None),
+    ("Übergreifend", "Amateurfunk", "Stolle", 2, 2, "WiSe/SoSe", None),
+]
+
+DAY_NAMES = {
+    0: "Montag",
+    1: "Dienstag",
+    2: "Mittwoch",
+    3: "Donnerstag",
+    4: "Freitag",
+    5: "Samstag",
+}
+
+with open("timetables.json", 'r') as f:
+    timetables = json.load(f)
+
+# Build lookup by shortname
+by_shortname = {}
+for course in timetables:
+    by_shortname[course["shortname"]] = course
+
+def get_slots(course_data):
+    """Extract (day_name, start_time, end_time, room) tuples from timetable data."""
+    slots = []
+    for day in course_data["timetable"].get("days", []):
+        for grid in day.get("gridEntries", []):
+            start = datetime.fromisoformat(grid["duration"]["start"])
+            end = datetime.fromisoformat(grid["duration"]["end"])
+            day_name = DAY_NAMES[start.weekday()]
+            start_time = start.strftime("%H:%M")
+            end_time = end.strftime("%H:%M")
+
+            rooms = []
+            for room in (grid.get("position2") or []):
+                if room.get("current"):
+                    rooms.append(room["current"]["displayName"])
+            room_str = "/".join(rooms) if rooms else ""
+
+            slots.append((day_name, start_time, end_time, room_str))
+    return slots
+
+def merge_slots(slots):
+    """Merge consecutive slots on the same day into single blocks."""
+    if not slots:
+        return []
+    # Group by day
+    by_day = {}
+    for day, start, end, room in slots:
+        by_day.setdefault(day, []).append((start, end, room))
+
+    merged = []
+    for day in DAY_NAMES.values():
+        if day not in by_day:
+            continue
+        entries = sorted(by_day[day])
+        # Merge consecutive entries (end of one == start of next, same day)
+        current_start, current_end, current_room = entries[0]
+        rooms = {current_room} if current_room else set()
+        for start, end, room in entries[1:]:
+            if start <= current_end:
+                current_end = max(current_end, end)
+                if room:
+                    rooms.add(room)
+            else:
+                merged.append((day, current_start, current_end, "/".join(sorted(rooms))))
+                current_start, current_end = start, end
+                rooms = {room} if room else set()
+        merged.append((day, current_start, current_end, "/".join(sorted(rooms))))
+    return merged
+
+kurse = []
+no_data = []
+
+for sp, name, dozent, sws, cp, turnus, shortname in PDF_COURSES:
+    semester = "WS/SS" if "WiSe/SoSe" in turnus else "SS"
+
+    course_data = by_shortname.get(shortname) if shortname else None
+
+    if course_data:
+        slots = get_slots(course_data)
+        merged = merge_slots(slots)
+    else:
+        merged = []
+
+    if not merged:
+        no_data.append(name)
+
+    entry = {
+        "Vertiefung": sp,
+        "Name": name,
+        "Dozent": dozent,
+        "Semester": semester,
+        "SWS": str(sws),
+        "CP": str(cp),
+        "Tag1": "",
+        "Startzeit1": "",
+        "Ende1": "",
+        "Raum1": "",
+        "Tag2": "",
+        "Startzeit2": "",
+        "Ende2": "",
+        "Raum2": "",
+        "Tag3": "",
+        "Startzeit3": "",
+        "Ende3": "",
+        "Raum3": "",
+        "Tag4": "",
+        "Startzeit4": "",
+        "Ende4": "",
+        "Raum4": "",
+    }
+
+    for i, slot in enumerate(merged[:4], 1):
+        entry[f"Tag{i}"] = slot[0]
+        entry[f"Startzeit{i}"] = slot[1]
+        entry[f"Ende{i}"] = slot[2]
+        entry[f"Raum{i}"] = slot[3]
+    if len(merged) > 4:
+        print(f"  WARNING: {name} has {len(merged)} time blocks, only first 4 used")
+
+    kurse.append(entry)
+
+with open("kurse.json", 'w') as f:
+    json.dump(kurse, f, ensure_ascii=False, indent=2)
+
+print(f"Generated kurse.json with {len(kurse)} courses")
+if no_data:
+    print(f"\nNo timetable data for {len(no_data)} courses:")
+    for n in no_data:
+        print(f"  - {n}")