def count(cls,
where: str = "",
where_args: tuple = None,
group_by: str = "") -> int:
"""Count the number of scrapable objects present in the database, based on the parameters
Args:
where: where clause, with ? placeholders for the where_args. Defaults to "".
where_args: args used in the where clause. Defaults to None.
group_by: group by clause. Defaults to "".
Returns:
number of scrapable objects
"""
return DbManager.count_from(table_name=cls().table,
where=where,
where_args=where_args,
group_by=group_by)
def scrape(cls, delete: bool = False):
"""Scrapes the timetable slots of the provided year and stores them in the database
Args:
delete: whether the table contents should be deleted first. Defaults to False.
"""
timetable_slots = []
response = requests.get(read_md("aulario")).text
tables = pd.read_html(response)
for k, table in enumerate(tables):
rooms = table.iloc[:, 0]
schedule = table.iloc[:, 1:]
subjects = {}
for time in schedule:
for i, row in enumerate(table[time]):
if time[-1] == "1":
time = time[:3] + "30"
if not pd.isnull(row):
r = row[:20] + rooms[i]
if not r in subjects:
subjects[r] = cls(nome=row.replace('[]', '').replace('[', '(').replace(']', ')'),
giorno=k,
ora_inizio=time,
ora_fine=time,
aula=rooms[i])
else:
subjects[r].ora_fine = time
timetable_slots.extend(subjects.values())
if delete:
cls.delete_all()
offset = DbManager.count_from(table_name=cls().table) # number of rows already present
for i, timetable_slot in enumerate(timetable_slots):
timetable_slot.ID = i + offset # generate the ID of the timetable slot based on its position in the array
cls.bulk_save(timetable_slots)
logger.info("Aulario loaded.")