add pole emploi module, advanced filters will come later

This commit is contained in:
Bezleputh 2013-07-24 13:00:47 +02:00 committed by Florent
commit f9192b1e6b
6 changed files with 267 additions and 0 deletions

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 PopolemploiBackend
__all__ = ['PopolemploiBackend']

View file

@ -0,0 +1,50 @@
# -*- 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 PopolemploiBrowser
from .job import PopolemploiJobAdvert
__all__ = ['PopolemploiBackend']
class PopolemploiBackend(BaseBackend, ICapJob):
NAME = 'popolemploi'
DESCRIPTION = u'Pole Emploi website'
MAINTAINER = u'Bezleputh'
EMAIL = 'carton_ben@yahoo.fr'
VERSION = '0.g'
BROWSER = PopolemploiBrowser
def search_job(self, pattern=None):
with self.browser:
return self.browser.search_job(pattern)
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 = {PopolemploiJobAdvert: fill_obj}

View file

@ -0,0 +1,50 @@
# -*- 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 PopolemploiJobAdvert
__all__ = ['PopolemploiBrowser']
class PopolemploiBrowser(BaseBrowser):
PROTOCOL = 'http'
DOMAIN = 'http://www.pole-emploi.fr/accueil/'
ENCODING = None
PAGES = {
'http://candidat.pole-emploi.fr/candidat/rechercheoffres/resultats(.*?)': SearchPage,
'http://candidat.pole-emploi.fr/candidat/rechercheoffres/detail/(?P<id>.+)': AdvertPage,
}
def search_job(self, pattern=None):
self.location('http://offre.pole-emploi.fr/resultat?offresPartenaires=true&libMetier=%s'
% pattern.replace(' ', '+'))
assert self.is_on_page(SearchPage)
return self.page.iter_job_adverts()
@id2url(PopolemploiJobAdvert.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)

View file

@ -0,0 +1,26 @@
# -*- 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 PopolemploiJobAdvert(BaseJobAdvert):
@classmethod
def id2url(cls, _id):
return 'http://candidat.pole-emploi.fr/candidat/rechercheoffres/detail/%s' % _id

View 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/>.
from weboob.tools.browser import BasePage
import dateutil.parser
from .job import PopolemploiJobAdvert
__all__ = ['SearchPage', 'AdvertPage']
class SearchPage(BasePage):
def iter_job_adverts(self):
rows = self.document.getroot().xpath('//table[@class="definition-table ordered"]/tbody/tr')
for row in rows:
advert = self.create_job_advert(row)
if advert:
yield advert
def create_job_advert(self, row):
a = self.parser.select(row, 'td[@headers="offre"]/a', 1, method='xpath')
_id = u'%s' % (a.attrib['href'][-7:])
if _id:
advert = PopolemploiJobAdvert(_id)
advert.contract_type = u'%s' % self.parser.select(row, 'td[@headers="contrat"]', 1, method='xpath').text
advert.title = u'%s' % a.text_content().strip()
society = self.parser.select(row, 'td/div/p/span[@class="company"]', method='xpath')
if society:
advert.society_name = society[0].text
advert.place = u'%s' % self.parser.select(row, 'td[@headers="lieu"]', 1, method='xpath').text_content()
date = self.parser.select(row, 'td[@headers="dateEmission"]', 1, method='xpath')
advert.publication_date = dateutil.parser.parse(date.text).date()
return advert
class AdvertPage(BasePage):
def get_job_advert(self, url, advert):
content = self.document.getroot().xpath('//div[@class="block-content"]/div')[0]
if not advert:
_id = self.parser.select(content, 'ul/li/ul/li/div[@class="value"]/span', 1, method='xpath').text
advert = PopolemploiJobAdvert(_id)
advert.title = u'%s' % self.parser.select(content, 'h4', 1, method='xpath').text.strip()
advert.job_name = u'%s' % self.parser.select(content, 'h4', 1, method='xpath').text.strip()
advert.description = u'%s' % self.parser.select(content, 'p[@itemprop="description"]', 1, method='xpath').text
advert.society_name = u'%s' % self.parser.select(content, 'div[@class="vcard"]/p[@class="title"]/span',
1, method='xpath').text
advert.url = url
advert.place = u'%s' % self.parser.select(content,
'ul/li/div[@class="value"]/ul/li[@itemprop="addressRegion"]',
1, method='xpath').text.strip()
advert.contract_type = u'%s' % self.parser.select(content,
'ul/li/div[@class="value"]/span[@itemprop="employmentType"]',
1, method='xpath').text.strip()
advert.experience = u'%s' % self.parser.select(content,
'ul/li/div[@class="value"]/span[@itemprop="experienceRequirements"]',
1, method='xpath').text.strip()
advert.formation = u'%s' % self.parser.select(content,
'ul/li/div[@class="value"]/span[@itemprop="qualifications"]',
1, method='xpath').text.strip()
advert.pay = u'%s' % self.parser.select(content,
'ul/li/div[@class="value"]/span[@itemprop="baseSalary"]',
1, method='xpath').text.strip()
return advert

View file

@ -0,0 +1,31 @@
# -*- 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 PopolemploiTest(BackendTest):
BACKEND = 'popolemploi'
def test_popolemploi(self):
l = list(self.backend.search_job('infographiste'))
assert len(l)
advert = self.backend.get_job_advert(l[0].id, l[0])
self.assertTrue(advert.url, 'URL for announce "%s" not found: %s' % (advert.id, advert.url))