def get_session_storage(self):
sessionContent = Regexp(
CleanText('//script[@type="text/javascript"]'),
'sessionStorage.setItem\((.*)\)'
)(self.doc)
key, value = map(lambda x: x.strip("'").strip(), sessionContent.split(",", 1))
return key, json.decoder.JSONDecoder().decode(value)
def filter(self, el):
duration = Regexp(CleanText('.'), r'.+\|(.+)')(el[0])
if duration[-1:] == "'":
t = [0, int(duration[:-1])]
else:
t = map(int, duration.split(':'))
return timedelta(hours=t[0], minutes=t[1])
def filter(self, el):
duration = Regexp(CleanText('.'), r'.+\|(.+)')(el[0])
if duration[-1:] == "'":
t = [0, int(duration[:-1])]
else:
t = map(int, duration.split(':'))
return timedelta(hours=t[0], minutes=t[1])
def next_page(self):
str_results = Regexp(
CleanText('//div[@class="m_resultats_recherche_titre"]'),
'.* - (\d* / \d*) .*')(self)
results = str_results.split('/')
if int(results[0]) - int(results[1]) < 10:
return BrowserURL('search',
pattern=Env('pattern'),
start=int(results[0]))(self)
def iter_payment_details(self, sub):
id_str = self.doc.xpath('//div[@class="entete container"]/h2')[0].text.strip()
m = re.match('.*le (.*) pour un montant de.*', id_str)
if m:
blocs_benes = self.doc.xpath('//span[contains(@id,"nomBeneficiaire")]')
blocs_prestas = self.doc.xpath('//table[@id="tableauPrestation"]')
i = 0
last_bloc = len(blocs_benes)
for i in range(0, last_bloc):
bene = blocs_benes[i].text;
id_str = m.group(1)
id_date = datetime.strptime(id_str, '%d/%m/%Y').date()
id = sub._id + "." + datetime.strftime(id_date, "%Y%m%d")
table = blocs_prestas[i].xpath('.//tr')
line = 1
last_date = None
for tr in table:
tds = tr.xpath('.//td')
if len(tds) == 0:
continue
det = Detail()
# TO TEST : Indemnités journalières : Pas pu tester de cas de figure similaire dans la nouvelle mouture du site
if len(tds) == 4:
date_str = Regexp(pattern=r'.*<br/>(\d+/\d+/\d+)\).*').filter(tds[0].text)
det.id = id + "." + str(line)
det.label = tds[0].xpath('.//span')[0].text.strip()
jours = tds[1].text
if jours is None:
jours = '0'
montant = tds[2].text
if montant is None:
montant = '0'
price = tds[3].text
if price is None:
price = '0'
if date_str is None or date_str == '':
det.infos = u''
det.datetime = last_date
else:
det.infos = '%s (%sj) * %s€' % (date_str, re.sub(r'[^\d,-]+', '', jours), re.sub(r'[^\d,-]+', '', montant))
det.datetime = datetime.strptime(date_str.split(' ')[3], '%d/%m/%Y').date()
last_date = det.datetime
det.price = Decimal(re.sub('[^\d,-]+', '', price).replace(',', '.'))
if len(tds) == 5:
date_str = Regexp(pattern=r'\w*(\d{2})/(\d{2})/(\d{4}).*', template='\\1/\\2/\\3', default="").filter("".join(tds[0].itertext()))
det.id = id + "." + str(line)
det.label = '%s - %s' % (bene, tds[0].xpath('.//span')[0].text.strip())
paye = tds[1].text
if paye is None:
paye = '0'
base = tds[2].text
if base is None:
base = '0'
tdtaux = tds[3].xpath('.//span')[0].text
if tdtaux is None:
taux = '0'
else:
taux = tdtaux.strip()
tdprice = tds[4].xpath('.//span')[0].text
if tdprice is None:
price = '0'
else:
price = tdprice.strip()
if date_str is None or date_str == '':
det.infos = u''
det.datetime = last_date
else:
det.infos = u' Payé %s€ / Base %s€ / Taux %s%%' % (re.sub(r'[^\d,-]+', '', paye), re.sub(r'[^\d,-]+', '', base), re.sub('[^\d,-]+', '', taux))
det.datetime = datetime.strptime(date_str, '%d/%m/%Y').date()
last_date = det.datetime
det.price = Decimal(re.sub('[^\d,-]+', '', price).replace(',', '.'))
line = line + 1
yield det
def get_session_storage(self):
sessionContent = Regexp(CleanText('//script[@type="text/javascript"]'),
'sessionStorage.setItem\((.*)\)')(self.doc)
key, value = map(lambda x: x.strip("'").strip(),
sessionContent.split(",", 1))
return key, json.decoder.JSONDecoder().decode(value)
def obj_split_path(self):
_id = Regexp(CleanText('./a/@href'), '/\w{2}/(.*)')(self)
return [SITE.CINEMA.get('id')] + _id.split('/')
def iter_payment_details(self, sub):
id_str = self.doc.xpath(
'//div[@class="entete container"]/h2')[0].text.strip()
m = re.match('.*le (.*) pour un montant de.*', id_str)
if m:
blocs_benes = self.doc.xpath(
'//span[contains(@id,"nomBeneficiaire")]')
blocs_prestas = self.doc.xpath('//table[@id="tableauPrestation"]')
i = 0
last_bloc = len(blocs_benes)
for i in range(0, last_bloc):
bene = blocs_benes[i].text
id_str = m.group(1)
id_date = datetime.strptime(id_str, '%d/%m/%Y').date()
id = sub._id + "." + datetime.strftime(id_date, "%Y%m%d")
table = blocs_prestas[i].xpath('.//tr')
line = 1
last_date = None
for tr in table:
tds = tr.xpath('.//td')
if len(tds) == 0:
continue
det = Detail()
# TO TEST : Indemnités journalières : Pas pu tester de cas de figure similaire dans la nouvelle mouture du site
if len(tds) == 4:
date_str = Regexp(r'.*<br/>(\d+/\d+/\d+)\).*',
'\\1')(tds[0].text)
det.id = id + "." + str(line)
det.label = unicode(
tds[0].xpath('.//span')[0].text.strip())
jours = tds[1].text
if jours is None:
jours = '0'
montant = tds[2].text
if montant is None:
montant = '0'
price = tds[3].text
if price is None:
price = '0'
if date_str is None or date_str == '':
det.infos = u''
det.datetime = last_date
else:
det.infos = date_str + u' (' + unicode(
re.sub('[^\d,-]+', '',
jours)) + u'j) * ' + unicode(
re.sub('[^\d,-]+', '',
montant)) + u'€'
det.datetime = datetime.strptime(
date_str.split(' ')[3], '%d/%m/%Y').date()
last_date = det.datetime
det.price = Decimal(
re.sub('[^\d,-]+', '', price).replace(',', '.'))
if len(tds) == 5:
date_str = Regexp(
pattern=r'\w*(\d{2})/(\d{2})/(\d{4}).*',
template='\\1/\\2/\\3',
default="").filter("".join(tds[0].itertext()))
det.id = id + "." + str(line)
det.label = bene + u' - ' + unicode(
tds[0].xpath('.//span')[0].text.strip())
paye = tds[1].text
if paye is None:
paye = '0'
base = tds[2].text
if base is None:
base = '0'
tdtaux = tds[3].xpath('.//span')[0].text
if tdtaux is None:
taux = '0'
else:
taux = tdtaux.strip()
tdprice = tds[4].xpath('.//span')[0].text
if tdprice is None:
price = '0'
else:
price = tdprice.strip()
if date_str is None or date_str == '':
det.infos = u''
det.datetime = last_date
else:
det.infos = u' Payé ' + unicode(
re.sub('[^\d,-]+', '',
paye)) + u'€ / Base ' + unicode(
re.sub('[^\d,-]+', '', base)
) + u'€ / Taux ' + unicode(
re.sub('[^\d,-]+', '', taux)) + '%'
det.datetime = datetime.strptime(
date_str, '%d/%m/%Y').date()
last_date = det.datetime
det.price = Decimal(
re.sub('[^\d,-]+', '', price).replace(',', '.'))
line = line + 1
yield det
def get_params(self):
a = Regexp(
CleanText('//script'),
'"algolia_app_id":"(.*)","algolia_api_key":"(.*)","algolia_api_index_taxonomy".*',
'\\1|\\2')(self.doc)
return a.split('|')
def get_params(self):
a = Regexp(CleanText('//script'),
'"algolia_app_id":"(.*)","algolia_api_key":"(.*)","algolia_api_index_taxonomy".*',
'\\1|\\2')(self.doc)
return a.split('|')
def obj_split_path(self):
_id = Regexp(CleanText('./a/@href'), '/\w{2}/(.*)')(self)
return [SITE.CINEMA.get('id')] + _id.split('/')
