diff options
| -rw-r--r-- | __init__.py | 2 | ||||
| -rw-r--r-- | management/commands/scraptimetables.py | 64 |
2 files changed, 65 insertions, 1 deletions
diff --git a/__init__.py b/__init__.py index 1740b96..6a6789b 100644 --- a/__init__.py +++ b/__init__.py @@ -13,7 +13,7 @@ # You should have received a copy of the GNU Affero General Public License # along with celcatsanitizer. If not, see <http://www.gnu.org/licenses/>. -VERSION = "0.11" +VERSION = "0.11.0-pa1ch" __version__ = VERSION default_app_config = "edt.apps.EdtConfig" diff --git a/management/commands/scraptimetables.py b/management/commands/scraptimetables.py new file mode 100644 index 0000000..4421e46 --- /dev/null +++ b/management/commands/scraptimetables.py @@ -0,0 +1,64 @@ +# Copyright (C) 2017 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 django.core.management.base import BaseCommand +from edt.models import Timetable, Year +from ._private import get_from_db_or_create, get_xml + +import re + + +class Command(BaseCommand): + help = "Fetch timetables from a specified URL" + + def add_arguments(self, parser): + parser.add_argument("--url", type=str, required=True) + + def handle(self, *args, **options): + for year, name, finder in self.__get_finders(options["url"]): + soup = get_xml(finder) + for link in soup.find_all("a"): + if "toutes sections et semestres confondus" in link.text: + url_base = finder.rsplit("/", 1) + timetable_url = "/".join([url_base[0], link.parent.parent.find("a", attrs={"class": "xmllink"})["href"]]) + + try: + timetable = Timetable.objects.get(year=year, name=name) + timetable.url = timetable_url + except: + timetable = Timetable(year=year, name=name, url=timetable_url) + finally: + timetable.save() + + def __get_finders(self, url): + soup = get_xml(url) + choose_regex = re.compile("^- Choisissez votre ([\w ]+) -$") + + for form in soup.find_all("form"): + for i, option in enumerate(form.find_all("option")): + if i == 0 and option.text == "- Choisissez le niveau -": + break + + search = choose_regex.search(option.text) + if search is not None: + current_year = get_from_db_or_create(Year, name=search.groups(0)[0]) + else: + finder = option["value"].replace("finder", "finder2") + if option.text.startswith(current_year.name): + name = option.text[len(current_year.name):].strip() + else: + name = option.text + + yield current_year, name, finder |