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

[regionsjob] fix: site changed

Browse source
This commit is contained in:
Bezleputh 2014-10-22 18:10:32 +02:00
commit 6deaa846f9
3 changed files with 170 additions and 133 deletions
Download patch file Download diff file Expand all files Collapse all files

76
modules/regionsjob/pages.py
View file

@ -17,30 +17,45 @@
# 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.browser.pages import HTMLPage
from weboob.browser.elements import ItemElement, SkipItem, ListElement, method
from weboob.browser.filters.standard import CleanText, Regexp, Format, Env, DateGuesser, DateTime
from weboob.browser.filters.html import Link, CleanHTML
from weboob.tools.date import LinearDateGuesser
from weboob.browser.pages import HTMLPage, pagination
from weboob.browser.elements import ItemElement, ListElement, method
from weboob.browser.filters.standard import CleanText, Regexp, Format, Env, Date, BrowserURL, Join
from weboob.browser.filters.html import CleanHTML, Link
from weboob.capabilities.job import BaseJobAdvert
from weboob.exceptions import ParseError
from datetime import date, timedelta
class SearchPage(HTMLPage):
@pagination
@method
class iter_job_adverts(ListElement):
item_xpath = '//div[@id="liste_offres"]/ul/li'
item_xpath = '//section[@class="annonce"]'
def next_page(self):
return Link('//a[@class="picto picto-nextsmall"]')(self)
class item(ItemElement):
klass = BaseJobAdvert
obj_id = Format(u'%s#%s',
Env('domain'),
Regexp(Link('div/span[@class="offres_poste"]/a'), '.*?numoffre=(.*?)&de=consultation'))
obj_title = CleanText('div/span[@class="offres_poste"]/a')
obj_society_name = CleanText('div/span[@class="offres_entreprise"]/span/a')
obj_place = CleanText('div/span[@class="offres_ville"]/span/span/span')
obj_contract_type = CleanText('div/span[@class="offres_poste"]/span')
obj_publication_date = DateGuesser(CleanText('div/span[@class="offres_date"]'), LinearDateGuesser())
Regexp(Env('domain'), 'http://www\.(.*)\.com'),
Regexp(CleanText('h1/a[2]/@href'), '/emplois/(.*)\.html'))
obj_title = CleanText('h1/a[2]')
obj_society_name = CleanText('figure/span[@itemprop="name"]')
obj_place = CleanText('p[@class="inlineblock max-width-75"]')
obj_contract_type = CleanText('p[@class="max-width-75"]')
def obj_publication_date(self):
_date = CleanText('p[@class="infos"]')
try:
return Date(_date)(self)
except ParseError:
str_date = _date(self)
if 'hier' in str_date:
return date.today() - timedelta(days=1)
else:
return date.today()
class AdvertPage(HTMLPage):
@ -48,28 +63,15 @@ class AdvertPage(HTMLPage):
class get_job_advert(ItemElement):
klass = BaseJobAdvert
def parse(self, el):
if self.obj.id:
advert = self.obj
advert.url = self.page.url
advert.description = Format(u'%s\r\n%s',
CleanHTML('//div[@id="annonce"]/p[@id="description_annonce"]'),
CleanHTML('//div[@id="annonce"]/p[@id="description_annonce"]/following-sibling::p[1]'))(el)
advert.pay = CleanText('//div[@id="annonce"]/p[@class="rubrique_annonce"]/following-sibling::p[1]')(el)
raise SkipItem()
self.env['url'] = self.page.url
obj_description = Format(u'%s%s',
CleanHTML('//div[@id="annonce"]/p[@id="description_annonce"]'),
CleanHTML('//div[@id="annonce"]/p[@id="description_annonce"]/following-sibling::p[1]'))
obj_description = Join('\n%s', '//div[@id="annonce-detail"]/p[@class="text"]', textCleaner=CleanHTML)
obj_id = Env('_id')
obj_url = Env('url')
obj_publication_date = DateTime(Regexp(CleanText('//div[@id="annonce"]/p[@class="date_ref"]'),
'(\d{2}/\d{2}/\d{4})'))
obj_title = CleanText('//div[@id="annonce"]/h1')
obj_society_name = CleanText('//div[@id="annonce"]/p[@class="contrat_loc"]/strong[1]')
obj_contract_type = CleanText('//div[@id="annonce"]/p[@class="contrat_loc"]/strong[2]')
obj_place = CleanText('//div[@id="annonce"]/p[@class="contrat_loc"]/strong[3]')
obj_pay = CleanText('//div[@id="annonce"]/p[@class="rubrique_annonce"]/following-sibling::p[1]')
obj_url = BrowserURL('advert_page', _id=Env('_id'))
obj_publication_date = Date(Regexp(CleanText('//div[@id="annonce-detail"]/p[@class="infos"]'),
'(\d{2}/\d{2}/\d{4})'))
obj_title = CleanText('//div[@id="annonce"]/div/div/h1')
obj_society_name = CleanText('//section[@class="entp-resume"]/h1/a')
obj_contract_type = CleanText('//dl[@class="infos-annonce"]/dt[span[@class="picto picto-contrat-grey"]]/following-sibling::dd[1]')
obj_place = CleanText('//dl[@class="infos-annonce"]/dt[span[@class="picto picto-geolocalisation-grey"]]/following-sibling::dd[1]')
obj_pay = CleanText('//div[@id="annonce-detail"]/p[@class="infos"]/preceding-sibling::p[1]',
replace=[('Salaire : ', '')])