diff options
| -rw-r--r-- | management/commands/_private.py | 2 | ||||
| -rw-r--r-- | management/commands/scraptimetables.py | 43 |
2 files changed, 44 insertions, 1 deletions
diff --git a/management/commands/_private.py b/management/commands/_private.py index 17896c4..2b57599 100644 --- a/management/commands/_private.py +++ b/management/commands/_private.py @@ -159,5 +159,5 @@ def get_xml(url): r = requests.get(url) r.encoding = "utf8" - soup = BeautifulSoup(r.text, "html.parser") + soup = BeautifulSoup(r.content, "html.parser") return soup diff --git a/management/commands/scraptimetables.py b/management/commands/scraptimetables.py new file mode 100644 index 0000000..cb5753d --- /dev/null +++ b/management/commands/scraptimetables.py @@ -0,0 +1,43 @@ +# 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 ._private import 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): + url = options["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: + print() + print("Groupe :", search.groups(0)[0]) + else: + print(option.text, option["value"]) |