diff options
author | Alban Gruin | 2018-09-06 18:17:35 +0200 |
---|---|---|
committer | Alban Gruin | 2018-09-06 18:17:35 +0200 |
commit | 4f1a7073abead3e2d5c614557853094ccf0dabb8 (patch) | |
tree | 972d8575f3819bd433d13b97f953f67db3663397 | |
parent | 713e3be3351a585c40838f7f7638f68d4088f7b6 (diff) |
management: nouveau script pour scrapper les salles
Signed-off-by: Alban Gruin <alban at pa1ch dot fr>
-rw-r--r-- | management/commands/scraprooms.py | 36 |
1 files changed, 36 insertions, 0 deletions
diff --git a/management/commands/scraprooms.py b/management/commands/scraprooms.py new file mode 100644 index 0000000..c448d61 --- /dev/null +++ b/management/commands/scraprooms.py @@ -0,0 +1,36 @@ +# Copyright (C) 2018 Alban Gruin +# +# celcatsanitizer is free software: you can redistribute it and/or modify +# it under the terms of the GNU Affero General Public License as published +# by the Free Software Foundation, either version 3 of the License, or +# (at your option) any later version. +# +# celcatsanitizer is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU Affero General Public License for more details. +# +# You should have received a copy of the GNU Affero General Public License +# along with celcatsanitizer. If not, see <http://www.gnu.org/licenses/>. + +from bs4 import BeautifulSoup +from django.core.management.base import BaseCommand +from django.db import transaction + +from edt.models import Room + + +class Command(BaseCommand): + help = "Scraps rooms from file" + + def add_arguments(self, parser): + parser.add_argument("--file", type=str, required=True) + + @transaction.atomic + def handle(self, *args, **options): + with open(options["file"], "r") as rooms: + soup = BeautifulSoup(rooms.read(), "html.parser") + + rooms = [option.text for option in soup.find_all("option")[1:]] + for room in set(rooms): + Room(name=room).save() |