parse.py
9.17 KB
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
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
#!/usr/bin/env python3
import os.path
import sys
import argparse
import datetime
import urllib.request
import dateutil.parser
from icalendar import Calendar
from html.parser import HTMLParser
from icalendar import vDatetime, Calendar, Event as CalEvent
# Parse command line arguments
parser = argparse.ArgumentParser(description='Convertit l\'emploi du temps IMA en ICS')
parser.add_argument('annee', metavar='ANNEE', type=int, help='année (3 ou 4)')
parser.add_argument('edt', metavar='EDT', type=str, help='la page pointant vers l\'emploi du temps concerné')
parser.add_argument('-o', '--output', dest='file', type=str, default='-', help='fichier de sortie, - pour stdout')
args = parser.parse_args()
if args.annee == 3:
url = 'http://dptima3.polytech-lille.net/' + args.edt + '.html'
SLOTS = [(( 8, 0), (10, 0)),
((10, 20), (12, 20)),
((13, 50), (15, 50)),
((16, 10), (18, 10))]
DATE_FORMAT = '%d/%m/%Y'
elif args.annee == 4:
url = 'http://ima3.polytech-lille.net/IMA4/' + args.edt + '.html'
SLOTS = [(( 8, 0), ( 9, 0)),
(( 9, 0), (10, 00)),
((10, 20), (11, 20)),
((11, 20), (12, 20)),
((13, 50), (14, 50)),
((14, 50), (15, 50)),
((16, 10), (17, 10)),
((17, 10), (18, 10))]
DATE_FORMAT = '%d/%m/%Y'
else:
raise ValueError('Année inconnue : ' + annee)
DAYS_PER_WEEK = 5.5
TABLE_1_DATE_X = 1
TABLE_1_FIRST_SLOT_X = 2
TABLE_2_DATE_X = 0
TABLE_2_FIRST_SLOT_X = 1
class TableHTMLParser(HTMLParser):
tables = [] # Tables
table = False # Current table content
line = False # Current line content
cell = False # Current cell content
cellx = 1
celly = 1
# Logic
def iscell(self):
"""
Return if we are currently in a cell
"""
return isinstance(self.cell, str)
def isline(self):
"""
Return if we are currently in a line
"""
return isinstance(self.line, list)
def istable(self):
"""
Return if we are currently in a table
"""
return isinstance(self.table, list)
# Actions
def endcell(self):
if self.iscell():
self.line.append((self.cell.strip(), self.cellx, self.celly))
self.cell = False
def endline(self):
self.endcell()
if self.isline():
self.table.append(self.line.copy())
self.line = False
def endtable(self):
self.endline()
if self.istable():
self.tables.append(self.table.copy())
self.table = False
# Inheritance
def handle_starttag(self, tag, attrs):
if tag == 'table':
self.table = []
elif tag == 'tr':
self.endline()
self.line = []
elif tag == 'td':
self.endcell()
self.cell = ''
self.cellx = 1
self.celly = 1
for attr in attrs:
if attr[0] == 'colspan':
self.cellx = int(attr[1])
elif attr[0] == 'rowspan':
self.celly = int(attr[1])
def handle_endtag(self, tag):
if tag == 'table':
self.endtable()
elif tag == 'tr':
self.endline()
elif tag == 'td':
self.endcell()
def handle_data(self, data):
if self.iscell():
self.cell += data
# TODO Do something that really is OOP or do not...
class Event:
# Mined data
shortText = ''
longText = ''
date = False
begSlot = 0
endSlot = 0
# Generated data
shortName = ''
longName = ''
location = ''
startTime = False
endTime = False
active = False
def feedShortText(self, shortText):
self.shortText = shortText
def feedLongText(self, longText):
self.longText = longText
def feedBegSlot(self, slot):
self.begSlot = slot
def feedEndSlot(self, slot):
self.endSlot = slot
def feedDate(self, date):
self.date = date
def endFeed(self):
self.shortName = self.shortText
self.longName = self.longText
if self.shortName:
self.active = True
if self.date and isinstance(self.begSlot, int) and isinstance(self.endSlot, int):
h, m = SLOTS[self.begSlot][0]
self.startTime = self.date + datetime.timedelta(hours=h, minutes=m)
h, m = SLOTS[self.endSlot][1]
self.endTime = self.date + datetime.timedelta(hours=h, minutes=m)
if self.longName:
e = self.longName.split('(')
if len(e) >= 2:
f = e[1].split(')')
self.longName = e[0].strip()
self.location = f[0].strip()
def __str__(self):
if self.active:
return self.shortName + ' [' + self.longName + '] ' + (str(self.startTime) + ' - ' + (str(self.endTime) + ' ') if self.startTime else '') + (('@ ' + self.location) if self.location else '')
else:
return 'Inactive event'
def getEvent(self):
e = CalEvent()
e.add('uid', '-'.join([
'polytech',
'ima' + str(args.annee),
args.edt,
vDatetime(self.startTime).to_ical().decode(),
vDatetime(self.endTime).to_ical().decode(),
self.shortName
]))
e.add('summary', self.shortName)
e.add('description', self.longName)
e.add('dtstart', self.startTime)
e.add('dtend', self.endTime)
e.add('location', self.location)
e.add('last-modified', updateTime)
e.add('dtstamp', updateTime)
return e
with urllib.request.urlopen(url) as handle:
updateTime = dateutil.parser.parse(handle.headers['Last-Modified'])
htmlStr = handle.read().decode('iso-8859-15')
# Read HTML tables
parser = TableHTMLParser()
parser.feed(htmlStr)
# Dupplicates cells with colspan & rowspan
tables = []
for parserTable in parser.tables:
# Figuring out dimensions
X, Y = 0, 0
for cell in parserTable[0]:
X += cell[1]
for line in parserTable:
Y += line[0][2]
# Constructing table with reals dimensions
table = []
for y in range(Y):
line = []
for x in range(X):
line.append(False)
table.append(line)
# Filling table with parsed table
x, y = 0, 0
for line in parserTable:
for cell in line:
# Offsetting to the right if cell is not empty
while isinstance(table[y][x], str):
x += 1
# Copying values
for y2 in range(y, y + cell[2]):
for x2 in range(x, x + cell[1]):
table[y2][x2] = cell[0]
x = 0
y += 1
tables.append(table)
# Creating events
days = dict()
# Parsing table 1
for line in tables[0]:
try:
date = datetime.datetime.strptime(line[TABLE_1_DATE_X], DATE_FORMAT)
except (ValueError, TypeError):
# This is not a date, no data to grab here
continue
for weekSlot in range(int(DAYS_PER_WEEK * len(SLOTS))):
daySlot = weekSlot % len(SLOTS)
# New day
if daySlot == 0:
if weekSlot != 0:
date = date + datetime.timedelta(days=1)
if date not in days:
days[date] = [Event() for s in range(len(SLOTS))]
cell = line[TABLE_1_FIRST_SLOT_X + weekSlot]
days[date][daySlot].feedShortText(cell)
# Parsing table 2
for line in tables[1]:
try:
date = datetime.datetime.strptime(line[TABLE_2_DATE_X], DATE_FORMAT)
except ValueError:
# This is not a date, no data to grab here
continue
if date not in days:
days[date] = [Event() for s in range(len(SLOTS))]
for slot in range(len(SLOTS)):
days[date][slot].feedLongText(line[slot + TABLE_2_FIRST_SLOT_X])
# Feeding back time and slot to events
events = []
for day in days:
prevEvent = False
for slot in range(len(SLOTS)):
event = days[day][slot]
sameAsPrevious = False
if prevEvent:
sameAsPrevious = event.longText == prevEvent.longText if prevEvent.longText else event.shortText == prevEvent.shortText
if sameAsPrevious:
prevEvent.feedEndSlot(slot)
else:
prevEvent.endFeed()
events.append(prevEvent)
if not prevEvent or (prevEvent and not sameAsPrevious):
event.feedDate(day)
event.feedBegSlot(slot)
event.feedEndSlot(slot)
prevEvent = event
prevEvent.endFeed()
events.append(prevEvent)
# Creating calendar
cal = Calendar()
cal.add('proid', '-//geoffrey.frogeye.fr//NONSGML Icalendar Calendar//EN')
cal.add('version', '2.0')
cal.add('calscale', 'GREGORIAN')
cal.add('x-wr-calname', 'Polytech IMA ' + str(args.annee) + ' ' + args.edt)
if os.path.isfile('custom.py'):
import custom
for event in events:
if event.active:
custom.filterEvent(event)
for event in events:
if event.active:
cal.add_component(event.getEvent())
# Writing calendar to file
data = cal.to_ical()
if args.file == '-':
sys.stdout.write(data.decode('utf-8'))
else:
with open(args.file, 'wb') as f:
f.write(data)