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
|
# -*- coding: utf-8 -*-
# Copyright(C) 2012 Romain Bignon
#
# This file is part of weboob.
#
# weboob 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.
#
# weboob 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 weboob. If not, see <http://www.gnu.org/licenses/>.
import re
from decimal import Decimal
from dateutil.parser import parse as parse_date
from weboob.tools.browser import BasePage
from weboob.capabilities.base import NotAvailable
from weboob.capabilities.housing import Housing
__all__ = ['SearchResultsPage', 'HousingPage']
class SearchResultsPage(BasePage):
DATE_RE = re.compile('Annonce \w+ du (.*)')
MONTHS = {u'janvier': 'january',
u'février': 'february',
u'mars': 'march',
u'avril': 'april',
u'mai': 'may',
u'juin': 'june',
u'juillet': 'july',
u'août': 'august',
u'septembre': 'september',
u'octobre': 'october',
u'novembre': 'november',
u'décembre': 'december',
}
def iter_housings(self):
for div in self.document.getroot().cssselect('div.annonce-resume'):
a = div.cssselect('td.lien-annonce')[0].find('a')
id = a.attrib['href'].split('-')[-1]
housing = Housing(id)
housing.title = a.text.strip()
m = re.match('(\w+) (.+) (\d+)\xa0m\xb2 (.*)', housing.title)
if m:
housing.area = Decimal(m.group(3))
housing.cost = Decimal(div.cssselect('td.prix')[0].text.strip(u' \t\u20ac\xa0€\n\r').replace('.', '').replace(',', '.'))
housing.currency = u'€'
m = self.DATE_RE.match(div.cssselect('p.date-publication')[0].text.strip())
if m:
date = m.group(1)
for fr, en in self.MONTHS.iteritems():
date = date.replace(fr, en)
housing.date = parse_date(date)
metro = div.cssselect('p.metro')
if len(metro) > 0:
housing.station = metro[0].text.strip()
else:
housing.station = NotAvailable
p = div.cssselect('p.annonce-resume-texte')[0]
b = p.findall('b')
if len(b) > 0:
housing.text = b[0].tail.strip()
housing.location = b[0].text
else:
housing.text = p.text.strip()
housing.photos = NotAvailable
yield housing
class HousingPage(BasePage):
def get_housing(self):
div = self.parser.select(self.document.getroot(), 'div#annonce_detail', 1)
housing = Housing(self.url.split('-')[-1])
parts = div.find('h1').text.split(' - ')
housing.title = parts[0].strip()
housing.cost = Decimal(parts[1].strip(u' \t\u20ac\xa0€\n\r').replace('.', '').replace(',', '.'))
housing.currency = u'€'
m = re.match('(\w+) (.+) (\d+)\xa0m\xb2 (.*)', housing.title)
if m:
housing.area = Decimal(m.group(3))
housing.date = housing.station = housing.location = housing.phone = NotAvailable
metro = div.cssselect('p.metro')
if len(metro) > 0:
housing.station = metro[0].text.strip()
p = div.cssselect('p.annonce-detail-texte')[0]
b = p.findall('b')
if len(b) > 0:
housing.text = b[0].tail.strip()
housing.location = b[0].text
if len(b) > 1:
housing.phone = b[1].text
else:
housing.text = p.text.strip()
housing.details = NotAvailable
housing.photos = NotAvailable
return housing
|
