# -*- coding: utf-8 -*- # Copyright(C) 2010 Romain Bignon # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by # the Free Software Foundation, version 3 of the License. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; if not, write to the Free Software # Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. import re from weboob.capabilities.bank import Account from .base import CragrBasePage from weboob.capabilities.bank import Operation class AccountsList(CragrBasePage): def get_list(self): l = [] for div in self.document.getiterator('div'): if div.attrib.get('class', '') == 'dv' and div.getchildren()[0].tag in ('a', 'br'): account = Account() if div.getchildren()[0].tag == 'a': # This is at least present on CA Nord-Est account.label = ' '.join(div.find('a').text.split()[:-1]) account.link_id = div.find('a').get('href', '') account.id = div.find('a').text.split()[-1] s = div.find('div').find('b').find('span').text else: # This is at least present on CA Toulouse account.label = div.find('a').text.strip() account.link_id = div.find('a').get('href', '') account.id = div.findall('br')[1].tail.strip() s = div.find('div').find('span').find('b').text balance = u'' for c in s: if c.isdigit(): balance += c if c == ',': balance += '.' account.balance = float(balance) l.append(account) return l def is_account_page(self): # tested on CA Lorraine, Paris, Toulouse title_spans = self.document.xpath('/html/body/div[@class="dv"]/span') for title_span in title_spans: title_text = title_span.text_content().strip().replace("\n", '') if (re.match('.*Compte.*n.[0-9]+.*au.*', title_text)): return True return False def next_page_url(self): # tested on CA Lorraine, Paris, Toulouse a = self.document.xpath('/html/body//div[@class="navlink"]//a[contains(text(), "Suite")]') if not a: return False else: return a[0].get('href', '') def is_right_aligned_div(self, div_elmt): return(re.match('.*text-align: ?right.*', div_elmt.get('style', ''))) def extract_text(self, xml_elmt): data = u'' for text in xml_elmt.itertext(): data = data + u'%s ' % text data = re.sub(' +', ' ', data.replace("\n", ' ').strip()) return data def get_history(self, start_index = 0): # tested on CA Lorraine, Paris, Toulouse # avoir parsing the page as an account-dedicated page if it is not the case if not self.is_account_page(): return index = start_index operation = False body_elmt_list = self.document.xpath('/html/body/*') # type of separator used in the page separators = 'hr' # How many