nojhan/weboob-devel
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

[monster] improve page parsing

Browse source
This commit is contained in:
Bezleputh 2015-02-23 09:38:01 +01:00 • committed by Romain Bignon
commit 4d59d1f9ea
2 changed files with 5 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

4
modules/monster/pages.py
View file

@ -71,8 +71,8 @@ class AdvertPage(HTMLPage):
obj_id = Env('_id')
obj_url = BrowserURL('advert', _id=Env('_id'))
obj_title = CleanText('//div[@id="jobcopy"]/h1[@itemprop="title"]')
obj_description = CleanHTML('//div[@id="jobBodyContent"]')
obj_title = CleanText('//div[@id="jobcopy"]/h1[@itemprop="title"]|//div[@itemprop="title"]/h1')
obj_description = CleanHTML('//div[@id="jobBodyContent"]|//div[@itemprop="description"]')
obj_contract_type = Join('%s ', '//dd[starts-with(@class, "multipledd")]')
obj_society_name = CleanText('//dd[@itemprop="hiringOrganization"]')
obj_place = CleanText('//span[@itemprop="jobLocation"]')

6
modules/monster/test.py
View file

@ -17,7 +17,7 @@
# 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 itertools
from weboob.tools.test import BackendTest
@ -25,13 +25,13 @@ class MonsterTest(BackendTest):
MODULE = 'monster'
def test_monster_search(self):
l = list(self.backend.search_job(u'marketing'))
l = list(itertools.islice(self.backend.search_job(u'marketing'), 0, 20))
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))
def test_monster_advanced_search(self):
l = list(self.backend.advanced_search_job())
l = list(itertools.islice(self.backend.advanced_search_job(), 0, 20))
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))