creation of Apec : module that uses ICapJob in order to find adverts on apec website

This commit is contained in:
Bezleputh 2013-06-18 12:52:23 +02:00 committed by Florent
commit 57bd31edc0
6 changed files with 250 additions and 0 deletions

24
modules/apec/__init__.py Normal file
View 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 ApecBackend
__all__ = ['ApecBackend']

46
modules/apec/backend.py Normal file
View 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.backend import BaseBackend
from weboob.capabilities.job import ICapJob
from .browser import ApecBrowser
__all__ = ['ApecBackend']
class ApecBackend(BaseBackend, ICapJob):
NAME = 'apec'
DESCRIPTION = u'apec website'
MAINTAINER = u'Bezleputh'
EMAIL = 'carton_ben@yahoo.fr'
VERSION = '0.g'
BROWSER = ApecBrowser
def search_job(self, pattern=None):
with self.browser:
for job_advert in self.browser.search_job(pattern):
yield job_advert
def get_job_advert(self, _id, advert=None):
with self.browser:
return self.browser.get_job_advert(_id, advert)

51
modules/apec/browser.py Normal file
View file

@ -0,0 +1,51 @@
# -*- 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.decorators import id2url
from weboob.tools.browser import BaseBrowser
from .pages import SearchPage, AdvertPage
from .job import ApecJobAdvert
__all__ = ['ApecBrowser']
class ApecBrowser(BaseBrowser):
PROTOCOL = 'http'
DOMAIN = 'www.apec.fr'
ENCODING = None
PAGES = {
'http://cadres.apec.fr/MesOffres/RechercheOffres/ApecRechercheOffre.jsp\?keywords=(.*?)': SearchPage,
'http://cadres.apec.fr/offres-emploi-cadres/offres-emploi-cadres/\d*_\d*_\d*_(.*?)________(.*?).html(.*?)': AdvertPage,
}
def search_job(self, pattern):
if pattern is not None:
self.location('http://cadres.apec.fr/MesOffres/RechercheOffres/ApecRechercheOffre.jsp?keywords=%s' % pattern.replace(' ','+'))
assert self.is_on_page(SearchPage)
return self.page.iter_job_adverts()
else:
return []
@id2url(ApecJobAdvert.id2url)
def get_job_advert(self, url, advert):
self.location(url)
assert self.is_on_page(AdvertPage)
return self.page.get_job_advert(url, advert)

27
modules/apec/job.py Normal file
View file

@ -0,0 +1,27 @@
# -*- coding: utf-8 -*-
# Copyright(C) 2010-2011 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])

70
modules/apec/pages.py Normal file
View file

@ -0,0 +1,70 @@
# -*- 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 BasePage
import dateutil.parser
import re
from .job import ApecJobAdvert
__all__ = ['SearchPage', 'AdvertPage']
class SearchPage(BasePage):
def iter_job_adverts(self):
adverts = []
re_id_title = re.compile('/offres-emploi-cadres/\d*_\d*_\d*_(.*?)________(.*?).html(.*?)', re.DOTALL)
divs = self.document.getroot().xpath("//div[@class='boxContent offre']") + self.document.getroot().xpath("//div[@class='boxContent offre even']")
for div in divs:
a = self.parser.select(div, 'div/h3/a', 1, method='xpath')
_id = u'%s/%s' % (re_id_title.search(a.attrib['href']).group(1), re_id_title.search(a.attrib['href']).group(2))
advert = ApecJobAdvert(_id)
advert.title = u'%s' % re_id_title.search(a.attrib['href']).group(2).replace('-', ' ')
l = self.parser.select(div, 'h4', 1).text.split('-')
advert.society_name = u'%s' % l[0].strip()
advert.place = u'%s' % l[-1].strip()
date = self.parser.select(div, 'div/div/div', 1, method='xpath')
advert.publication_date = dateutil.parser.parse(date.text_content().strip()[8:]).date()
adverts.append(advert)
return adverts
class AdvertPage(BasePage):
def get_job_advert(self, url, advert):
re_id_title = re.compile('/offres-emploi-cadres/\d*_\d*_\d*_(.*?)________(.*?).html(.*?)', re.DOTALL)
if advert is None:
_id = u'%s/%s' % (re_id_title.search(url).group(1), re_id_title.search(url).group(2))
advert = ApecJobAdvert(_id)
advert.title = re_id_title.search(url).group(2).replace('-', ' ')
advert.description = self.document.getroot().xpath("//div[@class='contentWithDashedBorderTop marginTop boxContent']/div")[0].text_content()
td = self.document.getroot().xpath("//table[@class='noFieldsTable']/tr/td")
advert.job_name = advert.title
advert.publication_date = dateutil.parser.parse(td[2].text_content()).date()
society_name = td[3].text_content()
a = self.parser.select(td[3], 'a', 1, method='xpath').text_content()
advert.society_name = u'%s' % society_name.replace(a, '').strip()
advert.contract_type = u'%s' % td[4].text_content().strip()
advert.place = u'%s' % td[5].text_content()
advert.pay = u'%s' % td[7].text_content()
advert.experience = u'%s' % td[8].text_content()
advert.url = url
return advert

32
modules/apec/test.py Normal file
View 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 ApecTest(BackendTest):
BACKEND = 'apec'
def test_apec(self):
l = list(self.backend.search_job(u'maitre brasseur'))
assert len(l)
advert = self.backend.get_job_advert(l[0].id, None)
print advert.__repr__()
self.assertTrue(advert.url, 'URL for announce "%s" not found: %s' % (advert.id, advert.url))