[cci][ICapJob] create CCI module
This commit is contained in:
Bezleputh
Florent
parent
6723cca59f
commit
60aa681475
6 changed files with 271 additions and 0 deletions
24
modules/cci/__init__.py
Normal file
24
modules/cci/__init__.py
Normal file
|
|
@ -0,0 +1,24 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
# Copyright(C) 2013 Bezleputh
|
||||
#
|
||||
# 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/>.
|
||||
|
||||
|
||||
from .backend import CciBackend
|
||||
|
||||
|
||||
__all__ = ['CciBackend']
|
||||
56
modules/cci/backend.py
Normal file
56
modules/cci/backend.py
Normal file
|
|
@ -0,0 +1,56 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
# Copyright(C) 2013 Bezleputh
|
||||
#
|
||||
# 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/>.
|
||||
|
||||
|
||||
from weboob.tools.backend import BaseBackend
|
||||
from weboob.capabilities.job import ICapJob, BaseJobAdvert
|
||||
|
||||
from .browser import CciBrowser
|
||||
|
||||
|
||||
__all__ = ['CciBackend']
|
||||
|
||||
|
||||
class CciBackend(BaseBackend, ICapJob):
|
||||
NAME = 'cci'
|
||||
DESCRIPTION = u'cci website'
|
||||
MAINTAINER = u'Bezleputh'
|
||||
EMAIL = 'carton_ben@yahoo.fr'
|
||||
LICENSE = 'AGPLv3+'
|
||||
VERSION = '0.h'
|
||||
|
||||
BROWSER = CciBrowser
|
||||
|
||||
def search_job(self, pattern=None):
|
||||
if not pattern:
|
||||
with self.browser:
|
||||
for job_advert in self.browser.search_job():
|
||||
yield job_advert
|
||||
|
||||
def advanced_search_job(self):
|
||||
return []
|
||||
|
||||
def get_job_advert(self, _id, advert=None):
|
||||
with self.browser:
|
||||
return self.browser.get_job_advert(_id, advert)
|
||||
|
||||
def fill_obj(self, advert, fields):
|
||||
self.get_job_advert(advert.id, advert)
|
||||
|
||||
OBJECTS = {BaseJobAdvert: fill_obj}
|
||||
46
modules/cci/browser.py
Normal file
46
modules/cci/browser.py
Normal file
|
|
@ -0,0 +1,46 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
# Copyright(C) 2013 Bezleputh
|
||||
#
|
||||
# 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/>.
|
||||
|
||||
|
||||
from weboob.tools.browser import BaseBrowser
|
||||
|
||||
from .pages import SearchPage
|
||||
|
||||
|
||||
__all__ = ['CciBrowser']
|
||||
|
||||
|
||||
class CciBrowser(BaseBrowser):
|
||||
PROTOCOL = 'http'
|
||||
DOMAIN = 'www.cci.fr/web/recrutement/les-offres-d-emploi'
|
||||
ENCODING = None
|
||||
|
||||
PAGES = {
|
||||
'%s://%s' % (PROTOCOL, DOMAIN): SearchPage,
|
||||
}
|
||||
|
||||
def search_job(self):
|
||||
self.location('%s://%s' % (self.PROTOCOL, self.DOMAIN))
|
||||
assert self.is_on_page(SearchPage)
|
||||
return self.page.iter_job_adverts()
|
||||
|
||||
def get_job_advert(self, _id, advert):
|
||||
self.location('%s://%s' % (self.PROTOCOL, self.DOMAIN))
|
||||
assert self.is_on_page(SearchPage)
|
||||
return self.page.get_job_advert(_id, advert)
|
||||
27
modules/cci/job.py
Normal file
27
modules/cci/job.py
Normal file
|
|
@ -0,0 +1,27 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
# Copyright(C) 2013 Bezleputh
|
||||
#
|
||||
# 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/>.
|
||||
|
||||
from weboob.capabilities.job import BaseJobAdvert
|
||||
|
||||
|
||||
class ApecJobAdvert(BaseJobAdvert):
|
||||
@classmethod
|
||||
def id2url(cls, _id):
|
||||
splitted_id = _id.split('/')
|
||||
return 'http://cadres.apec.fr/offres-emploi-cadres/offres-emploi-cadres/0_0_0_%s________%s.html' % (splitted_id[0], splitted_id[1])
|
||||
86
modules/cci/pages.py
Normal file
86
modules/cci/pages.py
Normal file
|
|
@ -0,0 +1,86 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
# Copyright(C) 2013 Bezleputh
|
||||
#
|
||||
# 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 dateutil.parser
|
||||
|
||||
from weboob.tools.browser import BasePage
|
||||
from weboob.capabilities.job import BaseJobAdvert
|
||||
|
||||
__all__ = ['SearchPage']
|
||||
|
||||
|
||||
class SearchPage(BasePage):
|
||||
def iter_job_adverts(self):
|
||||
trs = self.document.getroot().xpath("//tr[@class='texteCol2TableauClair']") \
|
||||
+ self.document.getroot().xpath("//tr[@class='texteCol2TableauFonce']")
|
||||
|
||||
for tr in trs:
|
||||
tds = self.parser.select(tr, 'td', method='xpath')
|
||||
a = self.parser.select(tds[2], 'a', 1, method='xpath')
|
||||
advert = BaseJobAdvert(a.attrib['href'].replace('#', ''))
|
||||
advert.title = u'%s' % a.text_content()
|
||||
advert.society_name = u'CCI %s' % tds[3].text
|
||||
advert.place = u'%s' % tds[0].text
|
||||
advert.job_name = u'%s' % tds[1].text
|
||||
yield advert
|
||||
|
||||
def get_job_advert(self, _id, advert):
|
||||
if advert is None:
|
||||
advert = BaseJobAdvert(_id)
|
||||
|
||||
items = self.document.getroot().xpath("//div[@id='divrecueil']")[0]
|
||||
keep_next = False
|
||||
for item in items:
|
||||
|
||||
if keep_next:
|
||||
if item.tag == 'div' and item.attrib['id'] == u'offre':
|
||||
first_div = self.parser.select(item, 'div/span', 2, method='xpath')
|
||||
advert.society_name = u'CCI %s' % first_div[0].text_content()
|
||||
advert.job_name = u'%s' % first_div[1].text_content()
|
||||
|
||||
second_div = self.parser.select(item, 'div/fieldset', 2, method='xpath')
|
||||
description = ""
|
||||
ps_1 = self.parser.select(second_div[0], 'p[@class="normal"]', method='xpath')
|
||||
h2s_1 = self.parser.select(second_div[0], 'h2[@class="titreParagraphe"]', method='xpath')
|
||||
if len(ps_1) == 5 and len(h2s_1) == 5:
|
||||
for i in range(0, 5):
|
||||
description += "\r\n-- %s --\r\n" % h2s_1[i].text
|
||||
description += "%s\r\n" % ps_1[i].text_content()
|
||||
|
||||
ps_2 = self.parser.select(second_div[1], 'p[@class="normal"]', method='xpath')
|
||||
h2s_2 = self.parser.select(second_div[1], 'h2[@class="titreParagraphe"]', method='xpath')
|
||||
if len(ps_2) == 3 and len(h2s_2) == 2:
|
||||
description += "\r\n-- %s --\r\n" % h2s_2[0].text
|
||||
a = self.parser.select(ps_2[0], 'a', 1, method='xpath')
|
||||
description += "%s\r\n" % a.text_content()
|
||||
|
||||
description += "\r\n-- %s --\r\n" % h2s_2[1].text
|
||||
description += "%s\r\n" % ps_2[1].text_content()
|
||||
description += "%s\r\n" % ps_2[2].text_content()
|
||||
|
||||
advert.description = description
|
||||
advert.url = self.url + '#' + advert.id
|
||||
date = self.parser.select(item, 'div/fieldset/p[@class="dateOffre"]', 1, method='xpath')
|
||||
advert.publication_date = dateutil.parser.parse(date.text_content()).date()
|
||||
break
|
||||
|
||||
if item.tag == 'a' and u'%s' % item.attrib['name'] == u'%s' % _id:
|
||||
keep_next = True
|
||||
|
||||
return advert
|
||||
32
modules/cci/test.py
Normal file
32
modules/cci/test.py
Normal file
|
|
@ -0,0 +1,32 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
# Copyright(C) 2013 Bezleputh
|
||||
#
|
||||
# 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/>.
|
||||
|
||||
|
||||
from weboob.tools.test import BackendTest
|
||||
|
||||
|
||||
class CciTest(BackendTest):
|
||||
BACKEND = 'cci'
|
||||
|
||||
def test_cci_search(self):
|
||||
l = list(self.backend.search_job())
|
||||
assert len(l)
|
||||
advert = self.backend.get_job_advert(l[0].id, None)
|
||||
self.assertTrue(advert.url, 'URL for announce "%s" not found: %s' % (advert.id, advert.url))
|
||||
|
||||
Loading…
Add table
Add a link
Reference in a new issue