1 files changed, 58 insertions, 0 deletions
diff --git a/management/commands/scraptimetables.py b/management/commands/scraptimetables.py
new file mode 100644
index 0000000..1904b42
--- /dev/null
+++ b/management/commands/scraptimetables.py
@@ -0,0 +1,58 @@
+#    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
+#    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 edt.models import Source, Timetable, Year
+
+import re
+import requests
+
+
+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, 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, _ = Year.objects.get_or_create(
+                        name=search.groups(0)[0])
+                else:
+                    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, url