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

lcl: website change, rewrite with browser2

Browse source
This commit is contained in:
Romain Bignon 2014-12-03 23:22:29 +01:00
commit 446bb3416c
4 changed files with 157 additions and 320 deletions
Download patch file Download diff file Expand all files Collapse all files

130
modules/lcl/browser.py
View file

@ -18,12 +18,13 @@
# along with weboob. If not, see <http://www.gnu.org/licenses/>. # along with weboob. If not, see <http://www.gnu.org/licenses/>.
import urllib
from urlparse import urlsplit, parse_qsl from urlparse import urlsplit, parse_qsl
from mechanize import Cookie
from weboob.deprecated.browser import Browser, BrowserIncorrectPassword from weboob.exceptions import BrowserIncorrectPassword
from weboob.browser import LoginBrowser, URL, need_login
from .pages import SkipPage, LoginPage, AccountsPage, AccountHistoryPage, \ from .pages import LoginPage, AccountsPage, AccountHistoryPage, \
CBListPage, CBHistoryPage, ContractsPage CBListPage, CBHistoryPage, ContractsPage
@ -31,67 +32,49 @@ __all__ = ['LCLBrowser','LCLProBrowser']
# Browser # Browser
class LCLBrowser(Browser): class LCLBrowser(LoginBrowser):
PROTOCOL = 'https' BASEURL = 'https://particuliers.secure.lcl.fr'
DOMAIN = 'particuliers.secure.lcl.fr'
CERTHASH = ['825a1cda9f3c7176af327013a20145ad587d1f7e2a7e226a1cb5c522e6e00b84']
ENCODING = 'utf-8'
USER_AGENT = Browser.USER_AGENTS['wget']
PAGES = {
'https://particuliers.secure.lcl.fr/outil/UAUT/Authentication/authenticate': LoginPage,
'https://particuliers.secure.lcl.fr/outil/UAUT\?from=.*': LoginPage,
'https://particuliers.secure.lcl.fr/outil/UAUT/Accueil/preRoutageLogin': LoginPage,
'https://particuliers.secure.lcl.fr//outil/UAUT/Contract/routing': LoginPage,
'https://particuliers.secure.lcl.fr/outil/UWER/Accueil/majicER': LoginPage,
'https://particuliers.secure.lcl.fr/outil/UWER/Enregistrement/forwardAcc': LoginPage,
'https://particuliers.secure.lcl.fr/outil/UAUT/Contrat/choixContrat.*': ContractsPage,
'https://particuliers.secure.lcl.fr/outil/UAUT/Contract/getContract.*': ContractsPage,
'https://particuliers.secure.lcl.fr/outil/UAUT/Contract/selectContracts.*': ContractsPage,
'https://particuliers.secure.lcl.fr/outil/UWSP/Synthese': AccountsPage,
'https://particuliers.secure.lcl.fr/outil/UWLM/ListeMouvements.*/accesListeMouvements.*': AccountHistoryPage,
'https://particuliers.secure.lcl.fr/outil/UWCB/UWCBEncours.*/listeCBCompte.*': CBListPage,
'https://particuliers.secure.lcl.fr/outil/UWCB/UWCBEncours.*/listeOperations.*': CBHistoryPage,
'https://particuliers.secure.lcl.fr/outil/UAUT/Contrat/selectionnerContrat.*': SkipPage,
'https://particuliers.secure.lcl.fr/index.html': SkipPage
}
def is_logged(self): login = URL('/outil/UAUT/Authentication/authenticate',
return not self.is_on_page(LoginPage) '/outil/UAUT\?from=.*',
'/outil/UAUT/Accueil/preRoutageLogin',
'.*outil/UAUT/Contract/routing',
'/outil/UWER/Accueil/majicER',
'/outil/UWER/Enregistrement/forwardAcc',
LoginPage)
contracts = URL('/outil/UAUT/Contrat/choixContrat.*',
'/outil/UAUT/Contract/getContract.*',
'/outil/UAUT/Contract/selectContracts.*',
ContractsPage)
accounts = URL('/outil/UWSP/Synthese', AccountsPage)
history = URL('/outil/UWLM/ListeMouvements.*/accesListeMouvements.*', AccountHistoryPage)
cb_list = URL('/outil/UWCB/UWCBEncours.*/listeCBCompte.*', CBListPage)
cb_history = URL('/outil/UWCB/UWCBEncours.*/listeOperations.*', CBHistoryPage)
skip = URL('/outil/UAUT/Contrat/selectionnerContrat.*',
'/index.html')
def login(self): def deinit(self):
pass
def do_login(self):
assert isinstance(self.username, basestring) assert isinstance(self.username, basestring)
assert isinstance(self.password, basestring) assert isinstance(self.password, basestring)
assert self.password.isdigit() assert self.password.isdigit()
if not self.is_on_page(LoginPage): self.login.stay_or_go()
self.location('%s://%s/outil/UAUT/Authentication/authenticate'
% (self.PROTOCOL, self.DOMAIN),
no_login=True)
if not self.page.login(self.username, self.password) or \ if not self.page.login(self.username, self.password) or \
(self.is_on_page(LoginPage) and self.page.is_error()) : (self.login.is_here() and self.page.is_error()) :
raise BrowserIncorrectPassword("invalid login/password.\nIf you did not change anything, be sure to check for password renewal request\non the original web site.\nAutomatic renewal will be implemented later.") raise BrowserIncorrectPassword("invalid login/password.\nIf you did not change anything, be sure to check for password renewal request\non the original web site.\nAutomatic renewal will be implemented later.")
self.location('%s://%s/outil/UWSP/Synthese'
% (self.PROTOCOL, self.DOMAIN),
no_login=True)
self.accounts.stay_or_go()
@need_login
def get_accounts_list(self): def get_accounts_list(self):
if not self.is_on_page(AccountsPage): self.accounts.stay_or_go()
self.location('%s://%s/outil/UWSP/Synthese'
% (self.PROTOCOL, self.DOMAIN))
return self.page.get_list() return self.page.get_list()
def get_account(self, id): @need_login
assert isinstance(id, basestring)
l = self.get_accounts_list()
for a in l:
if a.id == id:
return a
return None
def get_history(self, account): def get_history(self, account):
self.location(account._link_id) self.location(account._link_id)
for tr in self.page.get_operations(): for tr in self.page.get_operations():
@ -100,6 +83,7 @@ class LCLBrowser(Browser):
for tr in self.get_cb_operations(account, 1): for tr in self.get_cb_operations(account, 1):
yield tr yield tr
@need_login
def get_cb_operations(self, account, month=0): def get_cb_operations(self, account, month=0):
""" """
Get CB operations. Get CB operations.
@ -112,7 +96,7 @@ class LCLBrowser(Browser):
args = dict(parse_qsl(v.query)) args = dict(parse_qsl(v.query))
args['MOIS'] = month args['MOIS'] = month
self.location(self.buildurl(v.path, **args)) self.location('%s?%s' % (v.path, urllib.urlencode(args)))
for tr in self.page.get_operations(): for tr in self.page.get_operations():
yield tr yield tr
@ -124,45 +108,11 @@ class LCLBrowser(Browser):
class LCLProBrowser(LCLBrowser): class LCLProBrowser(LCLBrowser):
PROTOCOL = 'https' BASEURL = 'https://professionnels.secure.lcl.fr'
DOMAIN = 'professionnels.secure.lcl.fr'
CERTHASH = ['6ae7053ef30f7c7810673115b021a42713f518f3a87b2e73ef565c16ead79f81']
ENCODING = 'utf-8'
USER_AGENT = Browser.USER_AGENTS['wget']
PAGES = {
'https://professionnels.secure.lcl.fr/outil/UAUT?from=/outil/UWHO/Accueil/': LoginPage,
'https://professionnels.secure.lcl.fr/outil/UAUT\?from=.*': LoginPage,
'https://professionnels.secure.lcl.fr/outil/UAUT/Accueil/preRoutageLogin': LoginPage,
'https://professionnels.secure.lcl.fr//outil/UAUT/Contract/routing': LoginPage,
'https://professionnels.secure.lcl.fr/outil/UWER/Accueil/majicER': LoginPage,
'https://professionnels.secure.lcl.fr/outil/UWER/Enregistrement/forwardAcc': LoginPage,
'https://professionnels.secure.lcl.fr/outil/UAUT/Contrat/choixContrat.*': ContractsPage,
'https://professionnels.secure.lcl.fr/outil/UAUT/Contract/getContract.*': ContractsPage,
'https://professionnels.secure.lcl.fr/outil/UAUT/Contract/selectContracts.*': ContractsPage,
'https://professionnels.secure.lcl.fr/outil/UWSP/Synthese': AccountsPage,
'https://professionnels.secure.lcl.fr/outil/UWLM/ListeMouvements.*/accesListeMouvements.*': AccountHistoryPage,
'https://professionnels.secure.lcl.fr/outil/UWCB/UWCBEncours.*/listeCBCompte.*': CBListPage,
'https://professionnels.secure.lcl.fr/outil/UWCB/UWCBEncours.*/listeOperations.*': CBHistoryPage,
'https://professionnels.secure.lcl.fr/outil/UAUT/Contrat/selectionnerContrat.*': SkipPage,
'https://professionnels.secure.lcl.fr/index.html': SkipPage
}
#We need to add this on the login form #We need to add this on the login form
IDENTIFIANT_ROUTING = 'CLA' IDENTIFIANT_ROUTING = 'CLA'
def add_cookie(self, name, value):
c = Cookie(0, name, value,
None, False,
'.' + self.DOMAIN, True, True,
'/', False,
False,
None,
False,
None,
None,
{})
cookiejar = self._ua_handlers["_cookies"].cookiejar
cookiejar.set_cookie(c)
def __init__(self, *args, **kwargs): def __init__(self, *args, **kwargs):
Browser.__init__(self, *args, **kwargs) super(LCLProBrowser, self).__init__(*args, **kwargs)
self.add_cookie("lclgen","professionnels") self.session.cookies.set("lclgen","professionnels")

3
modules/lcl/enterprise/browser.py
View file

@ -118,6 +118,9 @@ class LCLEnterpriseBrowser(Browser):
for tr in self.page.get_operations(): for tr in self.page.get_operations():
yield tr yield tr
def get_cb_operations(self, account):
raise NotImplementedError()
class LCLEspaceProBrowser(LCLEnterpriseBrowser): class LCLEspaceProBrowser(LCLEnterpriseBrowser):
BASEURL = 'https://espacepro.secure.lcl.fr' BASEURL = 'https://espacepro.secure.lcl.fr'

35
modules/lcl/module.py
View file

@ -21,6 +21,7 @@
from weboob.capabilities.bank import CapBank, AccountNotFound from weboob.capabilities.bank import CapBank, AccountNotFound
from weboob.tools.backend import Module, BackendConfig from weboob.tools.backend import Module, BackendConfig
from weboob.tools.value import ValueBackendPassword, Value from weboob.tools.value import ValueBackendPassword, Value
from weboob.capabilities.base import find_object
from .browser import LCLBrowser, LCLProBrowser from .browser import LCLBrowser, LCLProBrowser
from .enterprise.browser import LCLEnterpriseBrowser, LCLEspaceProBrowser from .enterprise.browser import LCLEnterpriseBrowser, LCLEspaceProBrowser
@ -64,36 +65,20 @@ class LCLModule(Module, CapBank):
if not self._browser: if not self._browser:
return return
try: self.browser.deinit()
deinit = self.browser.deinit
except AttributeError:
pass
else:
deinit()
def iter_accounts(self): def iter_accounts(self):
for account in self.browser.get_accounts_list(): return self.browser.get_accounts_list()
yield account
def get_account(self, _id): def get_account(self, _id):
with self.browser: return find_object(self.browser.get_accounts_list(), id=_id, error=AccountNotFound)
account = self.browser.get_account(_id)
if account:
return account
else:
raise AccountNotFound()
def iter_coming(self, account): def iter_coming(self, account):
if self.BROWSER != LCLBrowser: transactions = list(self.browser.get_cb_operations(account))
raise NotImplementedError() transactions.sort(key=lambda tr: tr.rdate, reverse=True)
return transactions
with self.browser:
transactions = list(self.browser.get_cb_operations(account))
transactions.sort(key=lambda tr: tr.rdate, reverse=True)
return transactions
def iter_history(self, account): def iter_history(self, account):
with self.browser: transactions = list(self.browser.get_history(account))
transactions = list(self.browser.get_history(account)) transactions.sort(key=lambda tr: tr.rdate, reverse=True)
transactions.sort(key=lambda tr: tr.rdate, reverse=True) return transactions
return transactions

295
modules/lcl/pages.py
View file

@ -20,15 +20,20 @@
import re import re
import base64 import base64
from decimal import Decimal from decimal import Decimal
from logging import error
import math import math
import random import random
from cStringIO import StringIO
from weboob.capabilities.bank import Account from weboob.capabilities.bank import Account
from weboob.deprecated.browser import Page, BrowserUnavailable from weboob.browser.elements import method, ListElement, ItemElement, SkipItem
from weboob.tools.captcha.virtkeyboard import MappedVirtKeyboard, VirtKeyboardError from weboob.exceptions import ParseError
from weboob.browser.pages import LoggedPage, HTMLPage, FormNotFound
from weboob.browser.filters.standard import CleanText, Field, Regexp, Format, \
CleanDecimal, Map
from weboob.exceptions import BrowserUnavailable
from weboob.tools.capabilities.bank.transactions import FrenchTransaction from weboob.tools.capabilities.bank.transactions import FrenchTransaction
from weboob.tools.captcha.virtkeyboard import MappedVirtKeyboard, VirtKeyboardError
class LCLVirtKeyboard(MappedVirtKeyboard): class LCLVirtKeyboard(MappedVirtKeyboard):
@ -48,169 +53,140 @@ class LCLVirtKeyboard(MappedVirtKeyboard):
color=(255,255,255,255) color=(255,255,255,255)
def __init__(self,basepage): def __init__(self, basepage):
img=basepage.document.find("//img[@id='idImageClavier']") img=basepage.doc.find("//img[@id='idImageClavier']")
random.seed() random.seed()
self.url+="%s"%str(long(math.floor(long(random.random()*1000000000000000000000)))) self.url += "%s"%str(long(math.floor(long(random.random()*1000000000000000000000))))
MappedVirtKeyboard.__init__(self,basepage.browser.openurl(self.url), super(LCLVirtKeyboard, self).__init__(StringIO(basepage.browser.open(self.url).content), basepage.doc,img,self.color, "id")
basepage.document,img,self.color,"id")
self.check_symbols(self.symbols,basepage.browser.responses_dirname) self.check_symbols(self.symbols,basepage.browser.responses_dirname)
def get_symbol_code(self,md5sum): def get_symbol_code(self, md5sum):
code=MappedVirtKeyboard.get_symbol_code(self,md5sum) code=MappedVirtKeyboard.get_symbol_code(self, md5sum)
return code[-2:] return code[-2:]
def get_string_code(self,string): def get_string_code(self, string):
code='' code=''
for c in string: for c in string:
code+=self.get_symbol_code(self.symbols[c]) code += self.get_symbol_code(self.symbols[c])
return code return code
class SkipPage(Page): class LoginPage(HTMLPage):
pass def on_load(self):
class LoginPage(Page):
def on_loaded(self):
try: try:
self.browser.select_form(name='form') form = self.get_form(xpath='//form[@id="setInfosCGS" or @name="form"]')
except: except FormNotFound:
try: return
self.browser.select_form(predicate=lambda x: x.attrs.get('id','')=='setInfosCGS')
except:
return
self.browser.submit(nologin=True) form.submit()
def myXOR(self,value,seed): def myXOR(self,value,seed):
s='' s = ''
for i in xrange(len(value)): for i in xrange(len(value)):
s+=chr(seed^ord(value[i])) s += chr(seed^ord(value[i]))
return s return s
def login(self, login, passwd): def login(self, login, passwd):
try: try:
vk=LCLVirtKeyboard(self) vk = LCLVirtKeyboard(self)
except VirtKeyboardError as err: except VirtKeyboardError as err:
error("Error: %s"%err) self.logger.exception(err)
return False return False
password=vk.get_string_code(passwd) password = vk.get_string_code(passwd)
seed=-1 seed = -1
str="var aleatoire = " s = "var aleatoire = "
for script in self.document.findall("//script"): for script in self.doc.findall("//script"):
if(script.text is None or len(script.text)==0): if script.text is None or len(script.text) == 0:
continue continue
offset=script.text.find(str) offset = script.text.find(s)
if offset!=-1: if offset != -1:
seed=int(script.text[offset+len(str)+1:offset+len(str)+2]) seed = int(script.text[offset+len(s)+1:offset+len(s)+2])
break break
if seed==-1: if seed==-1:
error("Variable 'aleatoire' not found") raise ParseError("Variable 'aleatoire' not found")
return False
self.browser.select_form( form = self.get_form('//form[@id="formAuthenticate"]')
predicate=lambda x: x.attrs.get('id','')=='formAuthenticate') form['identifiant'] = login
self.browser.form.set_all_readonly(False) form['postClavierXor'] = base64.b64encode(self.myXOR(password,seed))
self.browser['identifiant'] = login.encode('utf-8')
self.browser['postClavierXor'] = base64.b64encode(self.myXOR(password,seed))
try: try:
self.browser['identifiantRouting'] = self.browser.IDENTIFIANT_ROUTING form['identifiantRouting'] = self.browser.IDENTIFIANT_ROUTING
except AttributeError: except AttributeError:
pass pass
try: try:
self.browser.submit(nologin=True) form.submit()
except BrowserUnavailable: except BrowserUnavailable:
# Login is not valid # Login is not valid
return False return False
return True return True
def is_error(self): def is_error(self):
errors = self.document.xpath(u'//div[@class="erreur" or @class="messError"]') errors = self.doc.xpath(u'//div[@class="erreur" or @class="messError"]')
return len(errors) > 0 return len(errors) > 0
class ContractsPage(Page): class ContractsPage(LoggedPage, HTMLPage):
def on_loaded(self): def on_load(self):
self.select_contract() self.select_contract()
def select_contract(self): def select_contract(self):
# XXX We select automatically the default contract in list. We should let user # XXX We select automatically the default contract in list. We should let user
# ask what contract he wants to see, or display accounts for all contracts. # ask what contract he wants to see, or display accounts for all contracts.
self.browser.select_form(nr=0) form = self.get_form(nr=0)
self.browser.submit(nologin=True) form.submit()
class AccountsPage(Page): class AccountsPage(LoggedPage, HTMLPage):
def on_loaded(self): def on_load(self):
warn = self.document.xpath('//div[@id="attTxt"]') warn = self.doc.xpath('//div[@id="attTxt"]')
if len(warn) > 0: if len(warn) > 0:
raise BrowserUnavailable(warn[0].text) raise BrowserUnavailable(warn[0].text)
def get_list(self): @method
l = [] class get_list(ListElement):
ids = set() item_xpath = '//tr[contains(@onclick, "redirect")]'
for a in self.document.getiterator('a'): flush_at_end = True
link=a.attrib.get('href')
if link is None:
continue
if link.startswith("/outil/UWLM/ListeMouvements"):
account = Account()
#by default the website propose the last 7 days or last 45 days but we can force to have the last 55days
account._link_id=link+"&mode=55"
account._coming_links = []
parameters=link.split("?").pop().split("&")
for parameter in parameters:
list=parameter.split("=")
value=list.pop()
name=list.pop()
if name=="agence":
account.id=value
elif name=="compte":
account.id+=value
elif name=="nature":
# TODO parse this string to get the right Account.TYPE_* to
# store in account.type.
account._type=value
if account.id in ids: class account(ItemElement):
continue klass = Account
ids.add(account.id) def condition(self):
div = a.getparent().getprevious() return '/outil/UWLM/ListeMouvement' in self.el.attrib['onclick']
if not div.text.strip():
div = div.find('div')
account.label=u''+div.text.strip()
balance = FrenchTransaction.clean_amount(a.text)
if '-' in balance:
balance='-'+balance.replace('-', '')
account.balance=Decimal(balance)
account.currency = account.get_currency(a.text)
self.logger.debug('%s Type: %s' % (account.label, account._type))
l.append(account)
if link.startswith('/outil/UWCB/UWCBEncours'):
if len(l) == 0:
self.logger.warning('There is a card account but not any check account')
continue
account = l[-1] NATURE2TYPE = {'006': Account.TYPE_CHECKING,
'049': Account.TYPE_SAVINGS,
'068': Account.TYPE_MARKET,
'069': Account.TYPE_SAVINGS,
}
coming = FrenchTransaction.clean_amount(a.text) obj__link_id = Format('%s&mode=55', Regexp(CleanText('./@onclick'), "'(.*)'"))
if '-' in coming: obj_id = Regexp(Field('_link_id'), r'.*agence=(\w+).*compte=(\w+)', r'\1\2')
coming = '-'+coming.replace('-', '') obj__coming_links = []
obj_label = CleanText('.//div[@class="libelleCompte"]')
obj_balance = CleanDecimal('.//td[has-class("right")]', replace_dots=True)
obj_currency = FrenchTransaction.Currency('.//td[has-class("right")]')
obj_type = Map(Regexp(Field('_link_id'), r'.*nature=(\w+)'), NATURE2TYPE, default=Account.TYPE_UNKNOWN)
class card(ItemElement):
def condition(self):
return '/outil/UWCB/UWCBEncours' in self.el.attrib['onclick']
def parse(self, el):
link = Regexp(CleanText('./@onclick'), "'(.*)'")(el)
id = Regexp(CleanText('./@onclick'), r'.*AGENCE=(\w+).*COMPTE=(\w+).*CLE=(\w+)', r'\1\2\3')(el)
account = self.parent.objects[id]
if not account.coming: if not account.coming:
account.coming = Decimal('0') account.coming = Decimal('0')
account.coming += Decimal(coming)
account.coming += CleanDecimal('.//td[has-class("right")]', replace_dots=True)(el)
account._coming_links.append(link) account._coming_links.append(link)
raise SkipItem()
return l
class Transaction(FrenchTransaction): class Transaction(FrenchTransaction):
PATTERNS = [(re.compile('^(?P<category>CB) (?P<text>RETRAIT) DU (?P<dd>\d+)/(?P<mm>\d+)'), PATTERNS = [(re.compile('^(?P<category>CB) (?P<text>RETRAIT) DU (?P<dd>\d+)/(?P<mm>\d+)'),
FrenchTransaction.TYPE_WITHDRAWAL), FrenchTransaction.TYPE_WITHDRAWAL),
(re.compile('^(?P<category>(PRLV|PE)) (?P<text>.*)'), (re.compile('^(?P<category>(PRLV|PE)) (?P<text>.*)'),
FrenchTransaction.TYPE_ORDER), FrenchTransaction.TYPE_ORDER),
@ -235,103 +211,26 @@ class Transaction(FrenchTransaction):
] ]
class AccountHistoryPage(Page): class AccountHistoryPage(LoggedPage, HTMLPage):
def get_table(self): @method
tables=self.document.findall("//table[@class='tagTab pyjama']") class _get_operations(Transaction.TransactionsElement):
for table in tables: item_xpath = '//table[has-class("tagTab") and (not(@style) or @style="")]/tr'
# Look for the relevant table in the Pro version head_xpath = '//table[has-class("tagTab") and (not(@style) or @style="")]/tr/th'
header=table.getprevious()
while header is not None and str(header.tag) != 'div':
header=header.getprevious()
if header is not None:
header=header.find("div")
if header is not None:
header=header.find("span")
if header is not None and \ col_raw = [u'Vos opérations', u'Libellé']
header.text.strip().startswith("Opérations effectuées".decode('utf-8')):
return table
# Look for the relevant table in the Particulier version class item(Transaction.TransactionElement):
header=table.find("thead").find("tr").find("th[@class='titleTab titleTableft']") def condition(self):
if header is not None and\ return self.parent.get_colnum('date') is not None and len(self.el.findall('td')) >= 3
header.text.strip().startswith("Solde au"):
return table
def strip_label(self, s): def validate(self, obj):
return s return obj.category != 'RELEVE CB'
def get_operations(self): def get_operations(self):
table = self.get_table() return self._get_operations()
operations = []
if table is None:
return operations
for tr in table.iter('tr'):
# skip headers and empty rows
if len(tr.findall("th"))!=0 or\
len(tr.findall("td"))<=1:
continue
mntColumn = 0
date = None
raw = None
credit = ''
debit = ''
for td in tr.iter('td'):
value = td.attrib.get('id')
if value is None:
# if tag has no id nor class, assume it's a label
value = td.attrib.get('class', 'opLib')
if value.startswith("date") or value.endswith('center'):
# some transaction are included in a <strong> tag
date = u''.join([txt.strip() for txt in td.itertext()])
elif value.startswith("lib") or value.startswith("opLib"):
# misclosed A tag requires to grab text from td
tooltip = td.xpath('./div[@class="autoTooltip"]')
if len(tooltip) > 0:
td.remove(tooltip[0])
raw = self.parser.tocleanstring(td)
elif value.startswith("solde") or value.startswith("mnt") or \
value.startswith('debit') or value.startswith('credit'):
mntColumn += 1
amount = u''.join([txt.strip() for txt in td.itertext()])
if amount != "":
if value.startswith("soldeDeb") or value.startswith('debit') or mntColumn==1:
debit = amount
else:
credit = amount
if date is None:
# skip non-transaction
continue
operation = Transaction(len(operations))
operation.parse(date, raw)
operation.set_amount(credit, debit)
if operation.category == 'RELEVE CB':
# strip that transaction which is detailled in CBListPage.
continue
operations.append(operation)
return operations
class CBHistoryPage(AccountHistoryPage): class CBHistoryPage(AccountHistoryPage):
def get_table(self):
# there is only one table on the page
try:
return self.document.findall("//table[@class='tagTab pyjama']")[0]
except IndexError:
return None
def strip_label(self, label):
# prevent to be considered as a category if there are two spaces.
return re.sub(r'[ ]+', ' ', label).strip()
def get_operations(self): def get_operations(self):
for tr in AccountHistoryPage.get_operations(self): for tr in AccountHistoryPage.get_operations(self):
tr.type = tr.TYPE_CARD tr.type = tr.TYPE_CARD
@ -341,8 +240,8 @@ class CBHistoryPage(AccountHistoryPage):
class CBListPage(CBHistoryPage): class CBListPage(CBHistoryPage):
def get_cards(self): def get_cards(self):
cards = [] cards = []
for a in self.document.getiterator('a'): for tr in self.doc.getiterator('tr'):
link = a.attrib.get('href', '') link = Regexp(CleanText('./@onclick'), "'(.*)'", default=None)(tr)
if link.startswith('/outil/UWCB/UWCBEncours') and 'listeOperations' in link: if link is not None and link.startswith('/outil/UWCB/UWCBEncours') and 'listeOperations' in link:
cards.append(link) cards.append(link)
return cards return cards