def iter_payment_details(self, sub):
if sub._id.isdigit():
idx = 0
else:
idx = sub._id.replace('AFFILIE', '')
if len(self.document.xpath('//div[@class="centrepage"]/h2')) > idx or self.document.xpath('//table[@id="DetailPaiement3"]') > idx:
id_str = self.document.xpath('//div[@class="centrepage"]/h2')[idx].text.strip()
m = re.match('.*le (.*) pour un montant de.*', id_str)
if m:
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 = self.document.xpath('//table[@class="tableau"]')[idx].xpath('.//tr')
line = 1
last_date = None
for tr in table:
tds = tr.xpath('.//td')
if len(tds) == 0:
continue
date_str = tds[0].text
det = Detail()
det.id = id + "." + str(line)
det.label = unicode(tds[1].text.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,-]+', '', tds[2].text)) + u'€ / Base ' + unicode(re.sub('[^\d,-]+', '', tds[3].text)) + u'€ / Taux ' + unicode(re.sub('[^\d,-]+', '', tds[4].text)) + '%'
det.datetime = datetime.strptime(date_str, '%d/%m/%Y').date()
last_date = det.datetime
det.price = Decimal(re.sub('[^\d,-]+', '', tds[5].text).replace(',', '.'))
line = line + 1
yield det
def get_details(self, sub):
det = Detail()
det.id = sub.id
det.label = sub.label
det.infos = ''
det.price = Decimal('0.0')
return det
def iter_history(self):
tables = self.doc.xpath('//table[contains(concat(" ", @class, " "), " cTableauTriable ")]')
if len(tables) > 0:
lines = tables[0].xpath('.//tr')
sno = 0
for tr in lines:
list_a = tr.xpath('.//a')
if len(list_a) == 0:
continue
date = tr.xpath('.//td')[0].text.strip()
lot = list_a[0].text.replace('(*)', '').strip()
if lot == 'SNL':
sno = sno + 1
lot = lot + str(sno)
factures = tr.xpath('.//div[@class="cAlignGauche"]/a')
factures_lbl = ''
for a in factures:
factures_lbl = factures_lbl + a.text.replace('(**)', '').strip() + ' '
montant = tr.xpath('.//div[@class="cAlignDroite"]')[0].text.strip()
det = Detail()
det.id = u''+lot
det.label = u''+lot
det.infos = u''+factures_lbl
det.datetime = datetime.strptime(date, "%d/%m/%Y").date()
det.price = Decimal(montant.replace(',', '.'))
yield det
def do_details(self, id):
"""
details [ID]
Get details of subscriptions.
If no ID given, display all details of all backends.
"""
l = []
id, backend_name = self.parse_id(id)
if not id:
for subscrib in self.get_object_list('iter_subscription'):
l.append((subscrib.id, subscrib.backend))
else:
l.append((id, backend_name))
for id, backend in l:
names = (backend,) if backend is not None else None
# XXX: should be generated by backend? -Flo
# XXX: no, but you should do it in a specific formatter -romain
# TODO: do it, and use exec_method here. Code is obsolete
mysum = Detail()
mysum.label = u"Sum"
mysum.infos = u"Generated by boobill"
mysum.price = Decimal("0.")
self.start_format()
for detail in self.do('get_details', id, backends=names):
self.format(detail)
mysum.price = detail.price + mysum.price
self.format(mysum)
def get_details(self, sub):
det = Detail()
det.id = sub.id
det.label = sub.label
det.infos = ""
det.price = Decimal("0.0")
return det
def iter_details(self, sub):
det = Detail()
det.id = sub.id
det.label = sub.label
det.infos = ""
det.price = Decimal("0.0")
yield det
def iter_details(self, sub):
det = Detail()
det.id = sub.id
det.label = sub.label
det.infos = ''
det.price = Decimal('0.0')
yield det
def iter_details(self, sub):
self.logger.debug('call Browser.iter_details')
det = Detail()
det.id = sub.id
det.label = sub.label
det.infos = ''
det.price = Decimal('0.0')
yield det
def iter_payment_details(self, sub):
if sub._id.isdigit():
idx = 0
else:
idx = sub._id.replace("AFFILIE", "")
if (
len(self.document.xpath('//div[@class="centrepage"]/h3')) > idx
or self.document.xpath('//table[@id="DetailPaiement3"]') > idx
):
id_str = self.document.xpath('//div[@class="centrepage"]/h3')[idx].text.strip()
m = re.match(".*le (.*) pour un montant de.*", id_str)
if m:
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 = self.document.xpath('//table[@id="DetailPaiement3"]')[idx].xpath(".//tr")
line = 1
last_date = None
for tr in table:
tds = tr.xpath(".//td")
if len(tds) == 0:
continue
date_str = tds[0].text
det = Detail()
det.id = id + "." + str(line)
det.label = unicode(tds[1].text.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,-]+", "", tds[2].text))
+ u"€ / Base "
+ unicode(re.sub("[^\d,-]+", "", tds[3].text))
+ u"€ / Taux "
+ unicode(re.sub("[^\d,-]+", "", tds[4].text))
+ "%"
)
det.datetime = datetime.strptime(date_str, "%d/%m/%Y").date()
last_date = det.datetime
det.price = Decimal(re.sub("[^\d,-]+", "", tds[5].text).replace(",", "."))
line = line + 1
yield det
def _iter_divs(self, divs, num, inter=False):
for div in divs:
detail = Detail()
detail.label = CleanText('div[@class="titre"]/p')(div)
detail.id = "-" + detail.label.split(' ')[1].lower()
if inter:
detail.label = detail.label + u" (international)"
detail.id = detail.id + "-inter"
detail.infos = CleanText('div[@class="conso"]/p')(div)
detail.price = CleanDecimal('div[@class="horsForfait"]/p/span', default=Decimal(0), replace_dots=True)(div)
self.details[num].append(detail)
def _iter_divs(self, divs, num, inter=False):
for div in divs:
detail = Detail()
detail.label = CleanText('div[@class="titre"]/p')(div)
detail.id = "-" + detail.label.split(' ')[1].lower()
if inter:
detail.label = detail.label + u" (international)"
detail.id = detail.id + "-inter"
detail.infos = CleanText('div[@class="conso"]/p')(div)
detail.price = CleanDecimal('div[@class="horsForfait"]/p/span', default=Decimal(0), replace_dots=True)(div)
self.details[num].append(detail)
def iter_divs(self, divs, num, inter=False):
for div in divs:
detail = Detail()
detail.label = unicode(div.find('div[@class="titre"]/p').text_content())
detail.id = "-" + detail.label.split(' ')[1].lower()
if inter:
detail.label = detail.label + u" (international)"
detail.id = detail.id + "-inter"
detail.infos = unicode(div.find('div[@class="conso"]/p').text_content().lstrip())
detail.price = convert_price(div)
self.details[num].append(detail)
def parse_voice(self, div, string, num, inter=False):
voice = Detail()
voice.id = "-voice"
voice.label = unicode(div.find('div[@class="titre"]/p').text_content())
if inter:
voice.label = voice.label + " (international)"
voice.id = voice.id + "-inter"
voice.price = convert_price(div)
voice1 = div.xpath('div[@class="conso"]/p/span')[0].text
voice2 = div.xpath('div[@class="conso"]/p/span')[1].text
voice.infos = unicode(string) % (voice1, voice2)
return voice
def _parse_voice(self, div, string, num, inter=False):
voicediv = div.xpath('div[@class="conso"]')[0]
voice = Detail()
voice.id = "-voice"
voice.label = CleanText('div[@class="titre"]/p')(div)
if inter:
voice.label = voice.label + " (international)"
voice.id = voice.id + "-inter"
voice.price = CleanDecimal('div[@class="horsForfait"]/p/span', default=Decimal(0), replace_dots=True)(div)
voice1 = CleanText('.//span[@class="actif"][1]')(voicediv)
voice2 = CleanText('.//span[@class="actif"][2]')(voicediv)
voice.infos = unicode(string) % (voice1, voice2)
return voice
def _parse_voice(self, div, string, num, inter=False):
voicediv = div.xpath('div[@class="conso"]')[0]
voice = Detail()
voice.id = "-voice"
voice.label = CleanText('div[@class="titre"]/p')(div)
if inter:
voice.label = voice.label + " (international)"
voice.id = voice.id + "-inter"
voice.price = CleanDecimal('div[@class="horsForfait"]/p/span', default=Decimal(0), replace_dots=True)(div)
voice1 = CleanText('.//span[@class="actif"][1]')(voicediv)
voice2 = CleanText('.//span[@class="actif"][2]')(voicediv)
voice.infos = unicode(string) % (voice1, voice2)
return voice
def get_details(self):
txt = self._parse_pdf()
page = txt.split('CONSOMMATION')[2].split('ACTIVITE DETAILLEE')[0]
lines = page.split('\n')
lines = [x for x in lines if len(x) > 0] # Remove empty lines
details = []
detail = None
lines.pop(0) # MENSUELLE
lines.pop(-1) # Line to describes pictures
twolines = False
for line in lines:
if "Votre consommation" in line:
line = line.split(": ", 1)[1]
if twolines:
twolines = False
detail.infos = unicode(line, encoding='utf-8')
elif re.match('[A-Za-z]', line[0]):
# We have a new element, return the other one
if detail is not None:
details.append(detail)
detail = Detail()
split = re.split("(\d)", line, maxsplit=1)
detail.price = Decimal(0)
if len(split) > 2:
detail.infos = unicode(split[1] + split[2], encoding='utf-8')
else:
twolines = True
if '€' in line:
specialprice = split[1] + split[2]
detail.price = Decimal(specialprice.replace('€', ''))
detail.label = unicode(split[0], encoding='utf-8')
elif '€' in line:
detail.price = Decimal(line.replace('€', ''))
else:
detail.infos = unicode(line, encoding='utf-8')
details.append(detail)
return details
def on_loaded(self):
self.details = []
table = self.document.xpath('//table[@id="reportTable"]')[0]
for tr in table.xpath('tbody/tr'):
detail = Detail()
# Skip global category
if tr.find('td/a') is not None:
continue
if tr.attrib["class"] == "totalAmount":
continue
tds = tr.xpath('td')
detail.label = unicode(tds[0].text.strip())
detail.infos = unicode(tds[1].text.strip())
detail.price = Decimal(tds[2].text.split(' ')[0].replace(',', '.'))
self.details.append(detail)
def iter_history(self):
table = self.document.xpath('//table[contains(concat(" ", @class, " "), " cTableauTriable ")]')[0].xpath('.//tr')
for tr in table:
list_a = tr.xpath('.//a')
if len(list_a) == 0:
continue
date = tr.xpath('.//td')[0].text.strip()
lot = list_a[0].text
factures = tr.xpath('.//div[@class="cAlignGauche"]/a')
factures_lbl = ''
for a in factures:
factures_lbl = factures_lbl + a.text + ' '
montant = tr.xpath('.//div[@class="cAlignDroite"]')[0].text.strip()
det = Detail()
det.id = lot
det.label = lot
det.infos = factures_lbl
det.datetime = datetime.strptime(date, "%d/%m/%Y").date()
det.price = Decimal(montant.replace(',', '.'))
yield det
def get_details(self):
txt = self._parse_pdf()
page = txt.split('CONSOMMATION')[2].split('ACTIVITE DETAILLEE')[0]
lines = page.split('\n')
lines = [x for x in lines if len(x) > 0] # Remove empty lines
numitems = ((len(lines) + 1) / 3) - 1 # Each line has three columns, remove one element (pictures)
lines.insert(len(lines) - 1, '') # Add an empty column for "Prélèvement mensuel
lines.pop(0)
details = []
for i in range(numitems):
nature = i * 3
conso = nature + 1
price = conso + 1
detail = Detail()
detail.label = unicode(lines[nature], encoding='utf-8')
detail.infos = unicode(lines[conso], encoding='utf-8')
try:
detail.price = Decimal(lines[price].replace('€', ''))
except:
detail.price = Decimal(0)
details.append(detail)
return details
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 iter_payment_details(self, sub):
if CleanText('//div[@class="infoPrestationsAssure"]/span')(self.doc).startswith('Pour %s' % sub.subscriber):
id_str = self.doc.xpath('//div[@class="centrepage"]/h2')[0].text.strip()
m = re.match('.*le (.*) pour un montant de.*', id_str)
if m:
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 = self.doc.xpath('//div[@class="infoPrestationsAssure"]//table')[0].xpath('.//tr')
line = 1
last_date = None
for tr in table:
tds = tr.xpath('.//td')
if len(tds) == 0:
continue
det = Detail()
if len(tds) == 5:
date_str = tds[0].text
det.id = id + "." + str(line)
det.label = unicode(tds[1].text.strip())
jours = tds[2].text
if jours is None:
jours = '0'
montant = tds[3].text
if montant is None:
montant = '0'
price = tds[4].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) == 6:
date_str = tds[0].text
det.id = id + "." + str(line)
det.label = unicode(tds[1].text.strip())
paye = tds[2].text
if paye is None:
paye = '0'
base = tds[3].text
if base is None:
base = '0'
taux = tds[4].text
if taux is None:
taux = '0'
price = tds[5].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 = 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 _parse_page(self, page):
# Regexp
footnote = re.compile(r'\([0-9]\) ') # (f)
ht = re.compile('HT par mois')
base = re.compile('la base de')
enddate = re.compile('\d\d\/\d\d\/\d\d') # YY/MM/DD
endwithdigit = re.compile('\d+$') # blah blah 42
textwithcoma = re.compile('([a-z]|\d{4})\,') # blah 2012, blah blah
# Parsing
details = []
for title in ['Abonnement',
'Consommation',
'Contributions et taxes liées à l\'énergie']:
section = page.split(title, 1)[1].split('Total ')[0]
# When a line holds '(0)', a newline is missing.
section = re.sub(footnote, '\n', section)
lines = section.split('\n')
lines = [x for x in lines if len(x) > 0] # Remove empty lines
detail = None
for line in lines:
if re.match('[A-Za-z]', line[0]):
# Things we want to merge with the one just before
if 'facturées' in line:
# Long lines are sometimes split, so we try to join them
# That is the case for:
# 'Déduction du montant des consommations
# estimées facturées du 00/00/00 au 00/00/00'
detail.label = detail.label + u' ' + unicode(line, encoding='utf-8')
# Things for which we want a new detail
else:
# Entering here, we will instantiate a new detail.
# We hadn't so before because of fragmented lines.
if detail is not None and detail.label is not NotAvailable:
# We have a new element, return the other one
details.append(detail)
detail = Detail()
detail.price = Decimal(0)
# If the coma is not a decimal separator, then
# this is is probably a loooong sentence.
# When it comes to jokes, keep it short and sweet.
line = re.split(textwithcoma, line)[0]
# Things we want for sure
if re.findall(enddate, line):
# When a line has been badly split after a date,
# We want the label to end after the date, and maybe
# the second part to be the info
mydate = re.search(enddate, line).group(0)
mylist = line.rpartition(mydate)
label = mylist[0] + mylist[1]
detail.label = unicode(label, encoding='utf-8')
elif re.findall(endwithdigit, line):
# What is this stupid number at the end of the line?
# Line should have been split before the number
detail.label = unicode(re.split(endwithdigit, line)[0], encoding='utf-8')
# Things we don't want for sure
elif ')' in line and '(' not in line:
# First part of the parenthesis should have been drop before
# Avoid to create a new empty detail
detail.label = NotAvailable
elif re.match(base, line):
# This string should come always after a date,
# usually, it will match one of the cases above.
# Sometimes, it appears on a new line we don't need.
detail.label = NotAvailable
elif re.match(ht, line):
# '00,00 € HT par mois' may have been split after HT
# We don't need of the second line
detail.label = NotAvailable
# Things we probably want to keep
else:
# Well, maybe our line is correct, after all.
# Not much to do.
detail.label = unicode(line, encoding='utf-8')
detail.infos = NotAvailable
elif ' %' in line:
if isinstance(detail, Detail):
# Sometimes the vat is not on a new line:
# '00,00 00,0 %' instead of '00,0 %'
vat = line.split()[line.count(' ')-1].replace(',', '.')
detail.infos = unicode('TVA: ' + vat)
elif ' €' in line:
price = line.replace(',', '.')
if isinstance(detail, Detail):
detail.price = Decimal(price.strip(' €'))
elif re.match(enddate, line):
# Line holding dates may have been mixed up
label = detail.label.split(' au ')[0] + u' au ' + unicode(line, encoding='utf-8')
detail.label = label
if detail.label is not NotAvailable:
# Do not append empty details to the list
# It seemed easier to create details anyway than dealing
# with None objects
details.append(detail)
return details
