From 713e3be3351a585c40838f7f7638f68d4088f7b6 Mon Sep 17 00:00:00 2001 From: Alban Gruin Date: Thu, 6 Sep 2018 18:17:20 +0200 Subject: management: mise à jour du script scraptimetables Signed-off-by: Alban Gruin --- management/commands/scraptimetables.py | 42 +++++++++++++++------------------- 1 file changed, 18 insertions(+), 24 deletions(-) (limited to 'management') diff --git a/management/commands/scraptimetables.py b/management/commands/scraptimetables.py index 4421e46..1904b42 100644 --- a/management/commands/scraptimetables.py +++ b/management/commands/scraptimetables.py @@ -1,4 +1,4 @@ -# Copyright (C) 2017 Alban Gruin +# Copyright (C) 2017-2018 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 @@ -13,11 +13,12 @@ # You should have received a copy of the GNU Affero General Public License # along with celcatsanitizer. If not, see . +from bs4 import BeautifulSoup from django.core.management.base import BaseCommand -from edt.models import Timetable, Year -from ._private import get_from_db_or_create, get_xml +from edt.models import Source, Timetable, Year import re +import requests class Command(BaseCommand): @@ -27,38 +28,31 @@ class Command(BaseCommand): 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) + for year, name, source in self.__get_timetables(options["url"]): + source, _ = Source.objects.get_or_create(url=source) + timetable = Timetable(year=year, name=name, source=source) + timetable.save() + + def __get_timetables(self, url): + req = requests.get(url) + soup = BeautifulSoup(req.content, "html.parser") 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 + if "finder.html" in option["value"]: + continue search = choose_regex.search(option.text) if search is not None: - current_year = get_from_db_or_create(Year, name=search.groups(0)[0]) + current_year, _ = Year.objects.get_or_create( + name=search.groups(0)[0]) else: - finder = option["value"].replace("finder", "finder2") + url = option["value"].replace("View=week", "View=month") if option.text.startswith(current_year.name): name = option.text[len(current_year.name):].strip() else: name = option.text - - yield current_year, name, finder + yield current_year, name, url -- cgit v1.2.1