class get_job_advert(ItemElement):
klass = BaseJobAdvert
obj_id = Env('id')
obj_url = BrowserURL('advert', id=Env('id'))
obj_title = CleanText('//div[@class="modal-body"]/h2')
obj_job_name = CleanText('//div[@class="modal-body"]/h2')
obj_description = CleanText('//div[has-class("description")]/p')
obj_society_name = CleanText('//div[@class="media-body"]/h4')
obj_experience = Join(
u'- ',
'//h4[contains(text(), "Exp")]/following-sibling::ul[has-class("skill-list")][1]/li',
newline=True,
addBefore='\n- ')
obj_formation = Join(
u'- ',
'//h4[contains(text(), "For")]/following-sibling::ul[has-class("skill-list")][1]/li',
newline=True,
addBefore='\n- ')
obj_place = CleanText(
'//div[@class="modal-body"]/h2/following-sibling::p[1]')
obj_publication_date = PoleEmploiDate(
CleanText('//div[@class="modal-body"]/h2/following-sibling::p[2]'))
def parse(self, el):
for el in XPath('//dl[@class="icon-group"]/dt')(el):
dt = CleanText('.')(el)
if dt == u'Type de contrat':
self.obj.contract_type = CleanText(
'./following-sibling::dd[1]')(el)
elif dt == u'Salaire':
self.obj.pay = Regexp(
CleanText('./following-sibling::dd[1]'),
u'Salaire : (.*)')(el)
class get_job_advert(ItemElement):
klass = BaseJobAdvert
obj_id = Env('_id')
obj_url = BrowserURL('advert_page', _id=Env('_id'))
obj_title = CleanText('//div[@class="infos-lieu"]/h1')
obj_place = CleanText('//div[@class="infos-lieu"]/h2')
obj_publication_date = Date(
Regexp(CleanText('//div[@class="info-agency"]'),
'.*Date de l\'annonce :(.*)',
default=''))
obj_job_name = CleanText('//div[@class="infos-lieu"]/h1')
obj_description = Format(
'\n%s%s', CleanHTML('//article[@id="post-description"]/div'),
CleanHTML('//article[@id="poste"]'))
obj_contract_type = Regexp(
CleanText('//article[@id="poste"]/div/ul/li'),
'Contrat : (\w*)',
default=NotAvailable)
obj_pay = Regexp(CleanText('//article[@id="poste"]/div/ul/li'),
'Salaire : (.*) par mois',
default=NotAvailable)
obj_experience = Regexp(CleanText('//article[@id="poste"]/div/ul/li'),
u'Expérience : (.* ans)',
default=NotAvailable)
class item(ItemElement):
klass = Bill
obj_date = Date(Dict('dueDate'),
parse_func=parse_french_date,
default=NotAvailable)
obj_price = CleanDecimal(Dict('amountIncludingTax'))
obj_format = 'pdf'
def obj_label(self):
return 'Facture du %s' % Field('date')(self)
def obj_id(self):
return '%s_%s' % (Env('subid')(self),
Field('date')(self).strftime('%d%m%Y'))
def get_params(self):
params = {
'billid': Dict('id')(self),
'billDate': Dict('dueDate')(self)
}
return urlencode(params)
obj_url = BrowserURL('doc_api_pro',
subid=Env('subid'),
dir=Dict('documents/0/mainDir'),
fact_type=Dict('documents/0/subDir'),
billparams=get_params)
obj__is_v2 = False
def obj_coming(self):
page = self.page.browser.open(
BrowserURL('account_coming',
identifiant=Field('iban'))(self)).page
coming = Eval(
lambda x, y: x / 10**y,
CleanDecimal(
Dict('infoOperationsAvenir/cumulTotal/montant',
default='0')),
CleanDecimal(
Dict('infoOperationsAvenir/cumulTotal/nb_dec',
default='0')))(page.doc)
# this so that card coming transactions aren't accounted twice in the total incoming amount
for el in Dict('infoOperationsAvenir/natures')(page.doc):
if Dict('nature/libelle')(
el) == "Factures / Retraits cartes":
coming_carte = Eval(
lambda x, y: x / 10**y,
CleanDecimal(
Dict('cumulNatureMere/montant', default='0')),
CleanDecimal(
Dict('cumulNatureMere/nb_dec',
default='0')))(el)
coming -= coming_carte
break
return coming
def next_page(self):
page = Regexp(CleanText('//link[@rel="next"]/@href', default=''),
'.*pg=(\d*)',
default=None)(self)
return BrowserURL('adv_search',
search=Env('search'),
page=int(page))(self)
class get_housing(ItemElement):
klass = Housing
obj_id = Env('_id')
obj_title = CleanText(CleanHTML('//meta[@itemprop="name"]/@content'))
obj_area = CleanDecimal(Regexp(
CleanText(CleanHTML('//meta[@itemprop="name"]/@content')),
'(.*?)(\d*) m\xb2(.*?)', '\\2'),
default=NotAvailable)
obj_cost = CleanDecimal('//*[@itemprop="price"]')
obj_currency = Regexp(CleanText('//*[@itemprop="price"]'),
'.*([%s%s%s])' % (u'€', u'$', u'£'),
default=u'€')
obj_date = Date(
Regexp(
CleanText(
'//p[@class="offer-description-notes"]|//p[has-class("darkergrey")]'
), u'.* Mis à jour : (\d{2}/\d{2}/\d{4}).*'))
obj_text = CleanHTML(
'//div[@class="offer-description-text"]|//div[has-class("offer-description")]'
)
obj_location = CleanText('//*[@itemprop="address"]')
obj_url = BrowserURL('housing', _id=Env('_id'))
def obj_photos(self):
photos = []
for img in XPath(
'//div[@class="carousel-content"]/ul/li/a/img/@src|//div[@class="carousel"]/ul/li/a/img/@src'
)(self):
photos.append(HousingPhoto(u'%s' % img))
return photos
def obj_details(self):
details = {}
energy = CleanText(
'//div[has-class("energy-summary")]/span[@class="section-label"]|//div[has-class("energy-summary")]/div/span[@class="section-label"]',
default='')(self)
energy_value = CleanText(
'//div[has-class("energy-summary")]/span[@class="energy-msg"]',
default='')(self)
if energy and energy_value:
details[energy] = energy_value
greenhouse = CleanText(
'//div[has-class("greenhouse-summary")]/span[@class="section-label"]|//div[has-class("greenhouse-summary")]/div/span[@class="section-label"]',
default='')(self)
greenhouse_value = CleanText(
'//div[has-class("greenhouse-summary")]/span[@class="energy-msg"]',
default='')(self)
if greenhouse and greenhouse_value:
details[greenhouse] = greenhouse_value
for li in XPath('//ul[@itemprop="description"]/li')(self):
label = CleanText('./div[has-class("criteria-label")]')(li)
value = CleanText('./div[has-class("criteria-value")]')(li)
details[label] = value
return details
def next_page(self):
link = Link('//a[@title="Page suivante" and @href]',
default=None)(self)
if link:
form = self.page.get_form('//form')
form['__EVENTTARGET'] = re.search(
'PostBackOptions[^\w]+([^"]+)', link).group(1)
return requests.Request("POST", BrowserURL('investment', \
page=None)(self).replace('None', form.url), data=dict(form))
def next_page(self):
page = Regexp(CleanText('//a[@data-action="fetch"]/@href',
default=''),
'.*page=(\d*)',
default=None)(self)
if page:
return BrowserURL('adv_search',
search=Env('search'),
page=int(page))(self)
def next_page(self):
page_nb = Dict('navigation/pagination/page')(self)
max_results = Dict('navigation/pagination/maxResults')(self)
results_per_page = Dict('navigation/pagination/resultsPerPage')(
self)
if int(max_results) / int(results_per_page) > int(page_nb):
return BrowserURL('search',
query=Env('query'),
page_number=int(page_nb) + 1)(self)
def obj_coming(self):
page = self.page.browser.open(
BrowserURL('account_coming',
identifiant=Field('iban'))(self)).page
return Eval(
lambda x, y: x / 10**y,
CleanDecimal(
Dict('infoOperationsAvenir/cumulTotal/montant',
default='0')),
CleanDecimal(
Dict('infoOperationsAvenir/cumulTotal/nb_dec',
default='0')))(page.doc)
