split filters into several files

modules/banqueaccord/pages.py

@@ -26,9 +26,10 @@ from cStringIO import StringIO
 from weboob.capabilities.bank import Account
 from weboob.tools.browser2.page import HTMLPage, method, LoggedPage
 from weboob.tools.browser2.elements import ListElement, ItemElement
-from weboob.tools.browser2.filters import ParseError, CleanText, Regexp, Attr, CleanDecimal, Env
+from weboob.tools.browser2.filters import CleanText, Regexp, Attr, CleanDecimal, Env
 from weboob.tools.captcha.virtkeyboard import MappedVirtKeyboard, VirtKeyboardError
 from weboob.tools.capabilities.bank.transactions import FrenchTransaction
+from weboob.tools.exceptions import ParseError
 
 
 __all__ = ['LoginPage', 'IndexPage', 'AccountsPage', 'OperationsPage']

modules/oney/pages.py

@@ -27,7 +27,8 @@ from weboob.tools.captcha.virtkeyboard import MappedVirtKeyboard, VirtKeyboardEr
 
 from weboob.tools.browser2.page import HTMLPage, method, LoggedPage, pagination
 from weboob.tools.browser2.elements import ListElement, ItemElement
-from weboob.tools.browser2.filters import Env, CleanDecimal, ParseError
+from weboob.tools.browser2.filters import Env, CleanDecimal
+from weboob.tools.exceptions import ParseError
 
 __all__ = ['LoginPage', 'IndexPage', 'OperationsPage']
 

weboob/tools/browser2/elements.py

@@ -20,11 +20,18 @@
 import re
 import sys
 from copy import deepcopy
-from .filters import _Filter, CleanText, AttributeNotFound, XPathNotFound
+
 from weboob.tools.log import getLogger
 from weboob.tools.ordereddict import OrderedDict
 from weboob.tools.browser2.page import NextPage
 
+from .filters.standard import _Filter, CleanText
+from .filters.html import AttributeNotFound, XPathNotFound
+
+
+__all__ = ['DataError', 'AbstractElement', 'ListElement', 'ItemElement', 'TableElement', 'SkipItem']
+
+
 class DataError(Exception):
     """
     Returned data from pages are incoherent.

weboob/tools/browser2/filters/__init__.py

@@ -0,0 +1,22 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2014 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 .standard import * # NOQA
+from .html import * # NOQA
+from .json import * # NOQA

weboob/tools/browser2/filters/html.py

@@ -0,0 +1,67 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2014 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 .standard import _Selector, _NO_DEFAULT, Filter, FilterError
+
+
+__all__ = ['CSS', 'XPath', 'XPathNotFound', 'AttributeNotFound', 'Attr', 'Link']
+
+
+class XPathNotFound(FilterError):
+    pass
+
+
+class AttributeNotFound(FilterError):
+    pass
+
+
+class CSS(_Selector):
+    @classmethod
+    def select(cls, selector, item):
+        return item.cssselect(selector)
+
+
+class XPath(_Selector):
+    pass
+
+
+class Attr(Filter):
+    def __init__(self, selector, attr, default=_NO_DEFAULT):
+        super(Attr, self).__init__(selector, default=default)
+        self.attr = attr
+
+    def filter(self, el):
+        try:
+            return u'%s' % el[0].attrib[self.attr]
+        except IndexError:
+            return self.default_or_raise(XPathNotFound('Unable to find link %s' % self.selector))
+        except KeyError:
+            return self.default_or_raise(AttributeNotFound('Link %s does not has attribute %s' % (el[0], self.attr)))
+
+
+class Link(Attr):
+    """
+    Get the link uri of an element.
+
+    If the <a> tag is not found, an exception IndexError is raised.
+    """
+
+    def __init__(self, selector=None, default=_NO_DEFAULT):
+        super(Link, self).__init__(selector, 'href', default=default)

weboob/tools/browser2/filters/json.py

@@ -0,0 +1,60 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2014 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 .standard import _Selector, _NO_DEFAULT
+
+
+__all__ = ['Dict']
+
+
+class _DictMeta(type):
+    def __getitem__(cls, name):
+        return cls(name)
+
+
+class Dict(_Selector):
+    __metaclass__ = _DictMeta
+
+    def __init__(self, selector=None, default=_NO_DEFAULT):
+        super(Dict, self).__init__(self, default=default)
+        self.selector = selector.split('/') if selector is not None else []
+
+    def __getitem__(self, name):
+        self.selector.append(name)
+        return self
+
+
+    @classmethod
+    def select(cls, selector, item):
+        if isinstance(item, dict):
+            content = item
+        else:
+            content = item.el
+
+        for el in selector:
+            if el not in content:
+                return None
+
+            content = content.get(el)
+
+        return content
+
+
+

weboob/tools/browser2/filters/standard.py

@@ -33,22 +33,21 @@ from weboob.tools.html import html2text
 _NO_DEFAULT = object()
 
 
+__all__ = ['FilterError', 'ColumnNotFound', 'RegexpError', 'ItemNotFound',
+           'Filter', 'Base', 'Env', 'TableCell', 'CleanHTML', 'RawText',
+           'CleanText', 'Lower', 'CleanDecimal', 'Field', 'Regexp', 'Map',
+           'DateTime', 'Date', 'Time', 'DateGuesser', 'Duration',
+           'MultiFilter', 'CombineDate', 'Format', 'Join']
+
+
 class FilterError(ParseError):
     pass
 
 
-class XPathNotFound(FilterError):
-    pass
-
-
 class ColumnNotFound(FilterError):
     pass
 
 
-class AttributeNotFound(FilterError):
-    pass
-
-
 class RegexpError(FilterError):
     pass
 
@@ -127,49 +126,6 @@ class _Selector(Filter):
             return self.default_or_raise(ParseError('Element %r not found' % self.selector))
 
 
-class _DictMeta(type):
-    def __getitem__(cls, name):
-        return cls(name)
-
-
-class Dict(_Selector):
-    __metaclass__ = _DictMeta
-
-    def __init__(self, selector=None, default=_NO_DEFAULT):
-        super(Dict, self).__init__(self, default=default)
-        self.selector = selector.split('/') if selector is not None else []
-
-    def __getitem__(self, name):
-        self.selector.append(name)
-        return self
-
-
-    @classmethod
-    def select(cls, selector, item):
-        if isinstance(item, dict):
-            content = item
-        else:
-            content = item.el
-
-        for el in selector:
-            if el not in content:
-                return None
-
-            content = content.get(el)
-
-        return content
-
-
-class CSS(_Selector):
-    @classmethod
-    def select(cls, selector, item):
-        return item.cssselect(selector)
-
-
-class XPath(_Selector):
-    pass
-
-
 class Base(Filter):
     """
     Change the base element used in filters.
@@ -343,31 +299,6 @@ class CleanDecimal(CleanText):
             return self.default_or_raise(e)
 
 
-class Attr(Filter):
-    def __init__(self, selector, attr, default=_NO_DEFAULT):
-        super(Attr, self).__init__(selector, default=default)
-        self.attr = attr
-
-    def filter(self, el):
-        try:
-            return u'%s' % el[0].attrib[self.attr]
-        except IndexError:
-            return self.default_or_raise(XPathNotFound('Unable to find link %s' % self.selector))
-        except KeyError:
-            return self.default_or_raise(AttributeNotFound('Link %s does not has attribute %s' % (el[0], self.attr)))
-
-
-class Link(Attr):
-    """
-    Get the link uri of an element.
-
-    If the <a> tag is not found, an exception IndexError is raised.
-    """
-
-    def __init__(self, selector=None, default=_NO_DEFAULT):
-        super(Link, self).__init__(selector, 'href', default=default)
-
-
 class Field(_Filter):
     """
     Get the attribute of object.