From 0717c8ccd6ac10989d86593ff73a86a0c4398408 Mon Sep 17 00:00:00 2001 From: Alban Gruin Date: Thu, 29 Aug 2019 12:53:05 +0200 Subject: ups2019: nouveau parseur pour le format UPS2019 Signed-off-by: Alban Gruin --- management/parsers/ups2019.py | 128 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 128 insertions(+) create mode 100644 management/parsers/ups2019.py (limited to 'management/parsers/ups2019.py') diff --git a/management/parsers/ups2019.py b/management/parsers/ups2019.py new file mode 100644 index 0000000..c7ab7c9 --- /dev/null +++ b/management/parsers/ups2019.py @@ -0,0 +1,128 @@ +# Copyright (C) 2019 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 . + +from datetime import date, datetime, timedelta +from html import unescape + +from django.utils import timezone + +import requests + +from ...models import Course, Group, Module, Room +from ...utils import get_current_week, get_week +from .abstractparser import AbstractParser +from .ups2018 import GROUP_PREFIXES + + +class Parser(AbstractParser): + def __get_name(self, raw_name): + return raw_name.split('[')[1][:-1] + + def __get_event(self, event, year, week): + if event["allDay"]: + return + + begin = timezone.make_aware( + datetime.strptime(event["start"], "%Y-%m-%dT%H:%M:%S") + ) + end = timezone.make_aware( + datetime.strptime(event["end"], "%Y-%m-%dT%H:%M:%S") + ) + + if year is not None and week is not None: + event_year, event_week, _ = begin.isocalendar() + if event_year != year or event_week != week: + return + + data = [unescape(st.strip()) + for st in event["description"].split("
")] + groups = [] + rooms = [] + + course = Course.objects.create( + source=self.source, begin=begin, end=end, + celcat_id=event["id"] + ) + + i = 0 + if event.get("eventCategory") is not None and \ + len(event.get("eventCategory", "")) > 0: + course.type = event["eventCategory"] + i = 1 + + if event.get("module", "") is not None and \ + len(event.get("module", "")) > 0: + module, _ = Module.objects.get_or_create(name=event["module"]) + course.module = module + + if '[' in data[i]: + course.name = self.__get_name(data[i]) + i += 1 + + while '[' in data[i]: + course.name += ", " + self.__get_name(data[i]) + i += 1 + + while i < len(data) and not data[i].startswith(GROUP_PREFIXES): + rooms.append(data[i]) + i += 1 + course.rooms.add(*Room.objects.filter(name__in=rooms)) + + while i < len(data) and data[i].startswith(GROUP_PREFIXES): + groups.append(Group.objects.get_or_create( + source=self.source, celcat_name=data[i] + )[0]) + i += 1 + course.groups.add(*groups) + + if i < len(data): + course.notes = "\n".join(data[i:]).strip() + if "other" in course.notes: + print("Warning: 'other' in course.notes") + + return course + + def get_events(self, today, year=None, week=None): + for event in self.events: + course = self.__get_event(event, year, week) + if course is not None: + yield course + + def get_update_date(self): + return + + def get_weeks(self): + # FIXME: détection automatique à partir des événements présents + beginning, _ = get_week(*get_current_week()) + self.weeks = {"1": beginning} + + return self.weeks + + def get_source(self): + start = date.today() + end = start + timedelta(days=365) + + req = requests.post(self.source.url, + headers={"User-Agent": self.user_agent}, + data={"calView": "month", + "resType": 103, + "federationIds[]": self.source.metadata, + "start": start.strftime("%Y-%m-%d"), + "end": end.strftime("%Y-%m-%d")}) + req.encoding = "uft8" + req.raise_for_status() + + self.events = req.json() + return self.events -- cgit v1.2.1 From a85f2fb91d1a4a0e31c41c392e404d7ddbf21109 Mon Sep 17 00:00:00 2001 From: Alban Gruin Date: Sun, 1 Sep 2019 12:41:19 +0200 Subject: ups2019: réadaptation du parseur L’emplacement des différents éléments a changé, mdr. Signed-off-by: Alban Gruin --- management/parsers/ups2019.py | 42 ++++++++++++++++++++---------------------- 1 file changed, 20 insertions(+), 22 deletions(-) (limited to 'management/parsers/ups2019.py') diff --git a/management/parsers/ups2019.py b/management/parsers/ups2019.py index c7ab7c9..c6bd7e3 100644 --- a/management/parsers/ups2019.py +++ b/management/parsers/ups2019.py @@ -27,9 +27,6 @@ from .ups2018 import GROUP_PREFIXES class Parser(AbstractParser): - def __get_name(self, raw_name): - return raw_name.split('[')[1][:-1] - def __get_event(self, event, year, week): if event["allDay"]: return @@ -56,41 +53,42 @@ class Parser(AbstractParser): celcat_id=event["id"] ) - i = 0 + max_i = len(data) + if event.get("eventCategory") is not None and \ len(event.get("eventCategory", "")) > 0: course.type = event["eventCategory"] - i = 1 + max_i -= 1 if event.get("module", "") is not None and \ len(event.get("module", "")) > 0: module, _ = Module.objects.get_or_create(name=event["module"]) course.module = module - if '[' in data[i]: - course.name = self.__get_name(data[i]) - i += 1 - - while '[' in data[i]: - course.name += ", " + self.__get_name(data[i]) - i += 1 - - while i < len(data) and not data[i].startswith(GROUP_PREFIXES): + i = 0 + while i < max_i and not data[i].startswith(GROUP_PREFIXES): rooms.append(data[i]) i += 1 course.rooms.add(*Room.objects.filter(name__in=rooms)) - while i < len(data) and data[i].startswith(GROUP_PREFIXES): - groups.append(Group.objects.get_or_create( - source=self.source, celcat_name=data[i] - )[0]) + if len(rooms) != course.rooms.count(): + print(rooms, course.rooms) + + while i < max_i and data[i].startswith(GROUP_PREFIXES): + group, _ = Group.objects.get_or_create(source=self.source, + celcat_name=data[i]) + groups.append(group) i += 1 course.groups.add(*groups) - if i < len(data): - course.notes = "\n".join(data[i:]).strip() - if "other" in course.notes: - print("Warning: 'other' in course.notes") + if i < max_i and course.module is not None and \ + data[i].startswith(course.module.name): + course.name = data[i] + i += 1 + + course.notes = "\n".join(data[i:max_i]).strip() + if "other" in data[i]: + print("Warning: \"other\" in notes") return course -- cgit v1.2.1