add backend hsbc

modules/hsbc/__init__.py

@@ -0,0 +1,3 @@
+from .backend import HSBCBackend
+
+__all__ = ['HSBCBackend']

modules/hsbc/backend.py

@@ -0,0 +1,61 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2012 Romain Bignon
+#
+# This file is part of weboob.
+#
+# weboob is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# weboob 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 Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with weboob. If not, see <http://www.gnu.org/licenses/>.
+
+
+from weboob.capabilities.bank import ICapBank, AccountNotFound
+from weboob.tools.backend import BaseBackend, BackendConfig
+from weboob.tools.value import ValueBackendPassword
+
+from .browser import HSBC
+
+
+__all__ = ['HSBCBackend']
+
+
+class HSBCBackend(BaseBackend, ICapBank):
+    NAME = 'hsbc'
+    MAINTAINER = 'Romain Bignon'
+    EMAIL = 'romain@weboob.org'
+    VERSION = '0.a'
+    LICENSE = 'AGPLv3+'
+    DESCRIPTION = 'HSBC bank\' website'
+    CONFIG = BackendConfig(ValueBackendPassword('login',      label='Account ID', masked=False),
+                           ValueBackendPassword('password',   label='Password', regexp='^(\d+|)$'))
+    BROWSER = HSBC
+
+    def create_default_browser(self):
+        return self.create_browser(self.config['login'].get(),
+                                   self.config['password'].get())
+
+    def iter_accounts(self):
+        for account in self.browser.get_accounts_list():
+            yield account
+
+    def get_account(self, _id):
+        with self.browser:
+            account = self.browser.get_account(_id)
+        if account:
+            return account
+        else:
+            raise AccountNotFound()
+
+    def iter_history(self, account):
+        with self.browser:
+            for history in self.browser.get_history(account.link_id):
+                yield history

modules/hsbc/browser.py

@@ -0,0 +1,95 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2012  Romain Bignon
+#
+# This file is part of weboob.
+#
+# weboob is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# weboob 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 Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with weboob. If not, see <http://www.gnu.org/licenses/>.
+
+
+import urllib
+import re
+
+from weboob.tools.browser import BaseBrowser, BrowserIncorrectPassword, BasePage, BrokenPageError
+from .pages.accounts import AccountsListPage, HistoryPage
+
+
+__all__ = ['HSBC']
+
+
+class NotLoggedPage(BasePage):
+    pass
+
+class HSBC(BaseBrowser):
+    DOMAIN = 'client.hsbc.fr'
+    PROTOCOL = 'https'
+    ENCODING = None # refer to the HTML encoding
+    PAGES = {'https://client.hsbc.fr/session_absente.html':                 NotLoggedPage,
+             'https://client.hsbc.fr/cgi-bin/emcgi\?.*debr=COMPTES_PAN':    AccountsListPage,
+             'https://client.hsbc.fr/cgi-bin/emcgi\?.*CPT_IdPrestation=.*': HistoryPage
+            }
+
+    _session = None
+
+    def home(self):
+        self.login()
+
+    def is_logged(self):
+        return self._session is not None and not self.is_on_page(NotLoggedPage)
+
+    def login(self):
+        assert isinstance(self.username, basestring)
+        assert isinstance(self.password, basestring)
+        assert self.password.isdigit()
+
+        data = {'Ident': self.username}
+        r = self.readurl('https://client.hsbc.fr/cgi-bin/emcgi?Appl=WEBACC', urllib.urlencode(data))
+        m = re.search('sessionid=([^ "]+)', r, flags=re.MULTILINE)
+        if not m:
+            raise BrowserIncorrectPassword()
+
+        self._session = m.group(1)
+
+        data = {'Secret': self.password}
+        r = self.readurl('https://client.hsbc.fr/cgi-bin/emcgi?sessionid=%s' % self._session, urllib.urlencode(data))
+        if r.find('Erreur Identification') >= 0:
+            raise BrowserIncorrectPassword()
+
+        m = re.search('url = "/cgi-bin/emcgi\?sessionid=([^& "]+)&debr="', r, flags=re.MULTILINE)
+        if not m:
+            raise BrokenPageError('Unable to find session token')
+        self._session = m.group(1)
+
+    def get_accounts_list(self):
+        self.location(self.buildurl('/cgi-bin/emcgi', sessionid=self._session, debr='COMPTES_PAN'))
+
+        return self.page.get_list()
+
+    def get_account(self, id):
+        assert isinstance(id, basestring)
+
+        if not self.is_on_page(AccountsListPage):
+            l = self.get_accounts_list()
+        else:
+            l = self.page.get_list()
+
+        for a in l:
+            if a.id == id:
+                return a
+
+        return None
+
+    def get_history(self, link):
+        self.location(link)
+        return self.page.get_operations()

modules/hsbc/pages/accounts.py

@@ -0,0 +1,66 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2012  Romain Bignon
+#
+# This file is part of weboob.
+#
+# weboob is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# weboob 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 Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with weboob. If not, see <http://www.gnu.org/licenses/>.
+
+
+import re
+from datetime import date
+
+from weboob.tools.browser import BasePage
+from weboob.capabilities.bank import Account, Operation
+from weboob.capabilities.base import NotAvailable
+
+
+__all__ = ['AccountsListPage']
+
+
+class AccountsListPage(BasePage):
+    def get_list(self):
+        for tr in self.document.getiterator('tr'):
+            tds = tr.findall('td')
+            if len(tds) != 3 or tds[0].attrib.get('class', '') != 'txt' or tds[0].attrib.get('valign', '') == 'center':
+                continue
+
+            account = Account()
+            account.id = tds[1].text.strip()
+
+            a = tds[0].findall('a')[-1]
+            account.label = a.text.strip()
+            account.link_id = a.attrib['href']
+
+            tag = tds[2].find('font')
+            if tag is None:
+                tag = tds[2]
+            account.balance = float(tag.text.replace('.','').replace(',','.').replace(' ', '').strip(u' \t\u20ac\xa0€\n\r'))
+            account.coming = NotAvailable
+
+            yield account
+
+class HistoryPage(BasePage):
+    def get_operations(self):
+        for script in self.document.getiterator('script'):
+            if script.text is None or script.text.find('\nCL(0') < 0:
+                continue
+
+            for m in re.finditer(r"CL\((\d+),'(.+)','(.+)','(.+)','([\d -\.,]+)','([\d -\.,]+)','\d+','\d+','[\w\s]+'\);", script.text, flags=re.MULTILINE):
+                op = Operation(m.group(1))
+                op.label = m.group(4)
+                op.amount = float(m.group(5).replace('.','').replace(',','.').replace(' ', '').strip(u' \t\u20ac\xa0€\n\r'))
+                op.date = date(*reversed([int(x) for x in m.group(3).split('/')]))
+                op.category = NotAvailable
+                yield op