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

This commit is contained in:
Bezleputh 2013-06-18 12:52:57 +02:00 committed by Florent
commit 5b9f40dfea
6 changed files with 260 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 AdeccoBackend
__all__ = ['AdeccoBackend']

45
modules/adecco/backend.py Normal file
View file

@ -0,0 +1,45 @@
# -*- 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 AdeccoBrowser
__all__ = ['AdeccoBackend']
class AdeccoBackend(BaseBackend, ICapJob):
NAME = 'adecco'
DESCRIPTION = u'adecco website'
MAINTAINER = u'Bezleputh'
EMAIL = 'carton_ben@yahoo.fr'
VERSION = '0.g'
BROWSER = AdeccoBrowser
def search_job(self, pattern=None):
with self.browser:
for advert in self.browser.search_job(pattern):
yield advert
def get_job_advert(self, _id, advert):
with self.browser:
return self.browser.get_job_advert(_id, advert)

51
modules/adecco/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 .job import AdeccoJobAdvert
from .pages import SearchPage, AdvertPage
__all__ = ['AdeccoBrowser']
class AdeccoBrowser(BaseBrowser):
PROTOCOL = 'http'
DOMAIN = 'www.adecco.fr'
ENCODING = None
PAGES = {
'%s://%s/trouver-un-emploi/Pages/Offres-d-emploi.aspx\?keywords=(.*?)' % (PROTOCOL, DOMAIN): SearchPage,
'%s://%s/trouver-un-emploi/Pages/Details-de-l-Offre/(.*?)/(.*?).aspx\?IOF=(.*?)?$' % (PROTOCOL, DOMAIN): AdvertPage,
}
def search_job(self, pattern):
if pattern is not None:
self.location('%s://%s/trouver-un-emploi/Pages/Offres-d-emploi.aspx?keywords=%s' % (self.PROTOCOL, self.DOMAIN, pattern.replace(' ','+')))
assert self.is_on_page(SearchPage)
return self.page.iter_job_adverts()
else:
return []
@id2url(AdeccoJobAdvert.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/adecco/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 AdeccoJobAdvert(BaseJobAdvert):
@classmethod
def id2url(cls, _id):
splitted_id = _id.split('/')
return 'http://www.adecco.fr/trouver-un-emploi/Pages/Details-de-l-Offre/%s/%s.aspx?IOF=%s' % (splitted_id[0], splitted_id[1], splitted_id[2])

81
modules/adecco/pages.py Normal file
View file

@ -0,0 +1,81 @@
# -*- 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
from .job import AdeccoJobAdvert
from datetime import datetime
import locale
import re
__all__ = ['SearchPage', 'AdvertPage']
class SearchPage(BasePage):
def iter_job_adverts(self):
locale.setlocale(locale.LC_TIME, 'fr_FR.UTF-8')
re_id = re.compile('http://www.adecco.fr/trouver-un-emploi/Pages/Details-de-l-Offre/(.*?)/(.*?).aspx\?IOF=(.*?)?$', re.DOTALL)
adverts = []
divs = self.document.getroot().xpath("//div[@class='resultContain right']") + self.document.getroot().xpath("//div[@class='resultContain left']")
for div in divs:
a = self.parser.select(div, 'div/a', 1, method='xpath').attrib['href']
if re_id.match(a):
_id = u'%s/%s/%s' % (re_id.search(a).group(1), re_id.search(a).group(2), re_id.search(a).group(3))
advert = AdeccoJobAdvert(_id)
date = u'%s' % self.parser.select(div, "div/span[@class='offreDatePublication']", 1, method='xpath').text
advert.publication_date = datetime.strptime(date, "%d %B %Y").date()
advert.title = u'%s' % self.parser.select(div, "div/h3/a", 1, method='xpath').text_content()
advert.place = u'%s' % self.parser.select(div, "div/h3/span[@class='offreLocalisation']", 1, method='xpath').text
adverts.append(advert)
return adverts
class AdvertPage(BasePage):
def get_job_advert(self, url, advert):
re_id = re.compile('http://www.adecco.fr/trouver-un-emploi/Pages/Details-de-l-Offre/(.*?)/(.*?).aspx\?IOF=(.*?)?$', re.DOTALL)
if advert is None:
_id = u'%s/%s/%s' % (re_id.search(url).group(1), re_id.search(url).group(2), re_id.search(url).group(3))
advert = AdeccoJobAdvert(_id)
advert.contract_type = re_id.search(url).group(1)
div = self.document.getroot().xpath("//div[@class='contain_MoreResults']")[0]
date = u'%s' % self.parser.select(div, "div[@class='dateResult']", 1, method='xpath').text.strip()
advert.publication_date = datetime.strptime(date, "%d %B %Y").date()
title = self.parser.select(div, "h1", 1, method='xpath').text_content().strip()
town = self.parser.select(div, "h1/span[@class='town']", 1, method='xpath').text_content()
page_title = self.parser.select(div, "h1/span[@class='pageTitle']", 1, method='xpath').text_content()
advert.title = u'%s' % title.replace(town, '').replace(page_title, '')
spans = self.document.getroot().xpath("//div[@class='jobGreyContain']/table/tr/td/span[@class='value']")
advert.job_name = u'%s' % spans[0].text
advert.place = u'%s' % spans[1].text
advert.pay = u'%s' % spans[2].text
advert.contract_type = u'%s' % spans[3].text
advert.url = url
advert.description = self.document.getroot().xpath("//div[@class='descriptionContainer']/p")[0].text_content()
return advert

32
modules/adecco/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 AdeccoTest(BackendTest):
BACKEND = 'adecco'
def test_adecco(self):
l = list(self.backend.search_job(u'valet de chambre'))
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))