1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
|
# 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 bs4 import BeautifulSoup
from django.utils import timezone
from edt.models import Group, Room, Course
from edt.utils import get_week
import datetime
import re
import requests
class Week:
def __init__(self, number, start):
self.number = number
self.start = timezone.make_aware(
datetime.datetime.strptime(start, "%d/%m/%Y"))
def get_day(self, id):
return self.start + datetime.timedelta(id)
@property
def year(self):
return self.start.year
def add_time(date, time):
delta = datetime.timedelta(hours=time.hour, minutes=time.minute)
return date + delta
def consolidate_group(group):
group_content_key = ("mention", "subgroup", "td", "tp")
group_content_list = group.group_info[1:]
group_content = dict(zip(group_content_key, group_content_list))
for i in range(len(group_content_list))[::-1]:
del group_content[group_content_key[i]]
group_content[group_content_key[i] + "__isnull"] = True
if group_content_list[i] is not None:
break
if "subgroup" in group_content:
group.parent = Group.objects.filter(**group_content).first()
group.save()
def consolidate_groups(groups):
for group in groups:
if group.parent == None:
consolidate_group(group)
def delete_courses_in_week(timetable, year, week):
start, end = get_week(year, week)
Course.objects.filter(begin__gte=start, begin__lt=end,
timetable=timetable).delete()
def get_from_db_or_create(cls, **kwargs):
obj = cls.objects.all().filter(**kwargs)
obj = obj.first()
if obj is None:
obj = cls(**kwargs)
obj.save()
return obj
def get_events(timetable, year, week, soup, weeks_in_soup):
for event in soup.find_all("event"):
title = None
type_ = None
groups = None
rooms = None
notes = None
if weeks_in_soup[event.rawweeks.text].number == week and \
weeks_in_soup[event.rawweeks.text].year == year and \
event.resources.group is not None and \
event.starttime is not None and event.endtime is not None:
date = weeks_in_soup[event.rawweeks.text].get_day(int(
event.day.text))
begin = add_time(date, datetime.datetime.strptime(
event.starttime.text, "%H:%M"))
end = add_time(date, datetime.datetime.strptime(
event.endtime.text, "%H:%M"))
groups = [get_from_db_or_create(Group, timetable=timetable,
celcat_name=item.text)
for item in event.resources.group.find_all("item")]
consolidate_groups(groups)
if event.notes is not None:
notes = event.notes.text
if event.resources.module is not None:
title = event.resources.module.item.text
elif notes is not None:
title = notes
notes = None
else:
title = "Aucune information"
if event.category is not None:
type_ = event.category.text
if event.resources.room is not None:
rooms = [get_from_db_or_create(Room, name=item.text)
for item in event.resources.room.find_all("item")]
yield title, type_, groups, rooms, notes, begin, end
def get_update_date(soup):
# Explication de la regex
#
# (\d+)/(\d+)/(\d+)\s+(\d+):(\d+):(\d+)
# (\d+) au moins un nombre
# / un slash
# (\d+) au moins un nombre
# / un slash
# (\d+) au moins un nombre
# \s+ au moins un espace
# (\d+) au moins un nombre
# : un deux-points
# (\d+) au moins un nombre
# : un deux-points
# (\d+) au moins un nombre
datetime_regex = re.compile("(\d+)/(\d+)/(\d+)\s+(\d+):(\d+):(\d+)")
search = datetime_regex.search(soup.footer.text)
if search is None:
return None
day, month, year, hour, minute, second = [int(v) for v in search.groups()]
date = datetime.datetime(year, month, day, hour, minute, second)
return timezone.make_aware(date)
def get_weeks(soup):
weeks = {}
for span in soup.find_all("span"):
weeks[span.alleventweeks.text] = Week(int(span.title.text),
span["date"])
return weeks
def get_xml(url):
r = requests.get(url)
r.encoding = "utf8"
soup = BeautifulSoup(r.text, "html.parser")
return soup
|
