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

modules/lolix/__init__.py

@@ -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 LolixBackend
+
+
+__all__ = ['LolixBackend']

modules/lolix/backend.py

@@ -0,0 +1,47 @@
+# -*- 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  #, BackendConfig
+#  from weboob.tools.value import Value
+
+from .browser import LolixBrowser
+
+from weboob.capabilities.job import ICapJob
+
+
+__all__ = ['LolixBackend']
+
+
+class LolixBackend(BaseBackend, ICapJob):
+    NAME = 'lolix'
+    DESCRIPTION = u'Lolix est un centre de compétences spécialisé dans les technologies à base de Logiciel Libre.'
+    MAINTAINER = u'Bezleputh'
+    EMAIL = 'carton_ben@yahoo.fr'
+    VERSION = '0.g'
+
+    BROWSER = LolixBrowser
+
+    def search_job(self, pattern=None):
+        with self.browser:
+            for advert in self.browser.search_job():
+                yield advert
+
+    def get_job_advert(self, _id, advert):
+        with self.browser:
+            return self.browser.get_job_advert(_id, advert)

modules/lolix/browser.py

@@ -0,0 +1,47 @@
+# -*- 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 LolixJobAdvert
+from .pages import SearchPage, AdvertPage
+
+__all__ = ['LolixBrowser']
+
+
+class LolixBrowser(BaseBrowser):
+    PROTOCOL = 'http'
+    DOMAIN = 'fr.lolix.org/search/offre'
+    ENCODING = 'iso-8859-1'
+
+    PAGES = {
+        '%s://%s/date.php' % (PROTOCOL, DOMAIN): SearchPage,
+        '%s://%s/offre.php\?id=(?P<id>.+)' % (PROTOCOL, DOMAIN): AdvertPage,
+    }
+
+    def search_job(self):
+        self.location('%s://%s/date.php' % (self.PROTOCOL, self.DOMAIN))
+        assert self.is_on_page(SearchPage)
+        return self.page.iter_job_adverts()
+
+    @id2url(LolixJobAdvert.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)

modules/lolix/job.py

@@ -0,0 +1,26 @@
+# -*- 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 LolixJobAdvert(BaseJobAdvert):
+    @classmethod
+    def id2url(cls, _id):
+        return 'http://fr.lolix.org/search/offre/offre.php?id=%s' % _id

modules/lolix/pages.py

@@ -0,0 +1,94 @@
+# -*- 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 LolixJobAdvert
+
+__all__ = ['SearchPage', 'AdvertPage']
+
+
+class AdvertPage(BasePage):
+    def get_job_advert(self, url, advert):
+        tables = self.document.getroot().xpath('//td[@class="Contenu"]/table')
+        rows = self.parser.select(tables[2], 'tr')
+
+        if not advert:
+            advert = LolixJobAdvert(self.group_dict['id'])
+
+        advert.url = url
+        advert.society_name = u'%s' % self.parser.select(tables[3], 'tr/td/a', 1, method='xpath').text
+        return self.fill_job_advert(rows, advert)
+
+    def fill_job_advert(self, rows, advert):
+        advert.title = u'%s' % self.parser.select(rows[0], 'td', 1).text_content()
+        isDescription = False
+        for row in rows:
+            cols = self.parser.select(row, 'td')
+            if isDescription:
+                advert.description = u'%s' % cols[0].text_content()
+                isDescription = False
+
+            elif cols[0].text == u'Poste :':
+                advert.job_name = u'%s' % cols[1].text_content()
+
+            elif cols[0].text == u'Contrat :':
+                advert.contract_type = u'%s' % cols[1].text_content()
+
+            elif cols[0].text and cols[0].text.find(u'Rémunération :') != -1:
+                advert.pay = u'%s' % cols[1].text_content()
+
+            elif cols[0].text and cols[0].text.find(u'Région :') != -1:
+                advert.place = u'%s' % cols[1].text_content()
+
+            elif cols[0].text == u'Détails :':
+                isDescription = True
+
+            #else:
+            #    print cols[0].text
+        return advert
+
+
+class SearchPage(BasePage):
+    def iter_job_adverts(self):
+        adverts = []
+        rows = self.document.getroot().xpath('//td[@class="Contenu"]/table/tr')
+        for row in rows:
+            cols = self.is_row_advert(row)
+            if cols is not None:
+                adverts.append(self.create_job_advert(cols))
+        return adverts
+
+    def is_row_advert(self, row):
+        cols = self.parser.select(row, 'td')
+        d = dict(cols[1].attrib)
+        if 'class' in d.keys():
+            if 'ListeDark' == d['class'] or 'ListeLight' == d['class']:
+                return cols
+
+    def create_job_advert(self, cols):
+        a = self.parser.select(cols[3], 'a')[0]
+        advert = LolixJobAdvert(re.match(r'offre.php\?id=(.*)', a.attrib['href']).group(1))
+        advert.publication_date = dateutil.parser.parse(cols[1].text).date()
+        advert.society_name = u'%s' % self.parser.select(cols[2], 'a')[0].text
+        advert.title = u'%s' % a.text
+        return advert

modules/lolix/test.py

@@ -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 LolixTest(BackendTest):
+    BACKEND = 'lolix'
+
+    def test_lolix(self):
+        l = list(self.backend.search_job())
+        assert len(l)
+        advert = self.backend.get_job_advert(l[0].id, l[0])
+        print advert.__repr__()
+        self.assertTrue(advert.url, 'URL for announce "%s" not found: %s' % (advert.id, advert.url))