CleanChars is now an option of CleanText

modules/dresdenwetter/pages.py

@@ -18,7 +18,7 @@
 # along with weboob. If not, see <http://www.gnu.org/licenses/>.
 
 from weboob.tools.browser2.page import HTMLPage, method, ListElement, ItemElement
-from weboob.tools.browser2.filters import CleanText, Env, Regexp, Attr, CleanChars
+from weboob.tools.browser2.filters import CleanText, Env, Regexp, Attr
 from weboob.capabilities.gauge import GaugeMeasure, GaugeSensor
 from weboob.capabilities.base import NotAvailable
 
@@ -36,7 +36,7 @@ class StartPage(HTMLPage):
             klass = GaugeSensor
 
             obj_name = Regexp(CleanText('.'), '(.*?) {0,}: .*', "\\1")
-            obj_id = CleanChars(Regexp(Attr('name'), '(.*)', "dd-\\1"), " .():")
+            obj_id = CleanText(Regexp(Attr('name'), '(.*)', "dd-\\1"), " .():")
             obj_unit = Env('unit')
             obj_lastvalue = Env('lastvalue')
             obj_gaugeid = u"wetter"

weboob/tools/browser2/filters.py

@@ -121,14 +121,20 @@ class CleanText(Filter):
     """
     Get a cleaned text from an element.
 
-    It replaces all tabs and multiple spaces to one space and strip the result
+    It first replaces all tabs and multiple spaces to one space and strip the result
     string.
+    Second, it replaces all symbols given in second argument.
     """
+    def __init__(self, selector, symbols=''):
+        super(CleanText, self).__init__(selector)
+        self.symbols = symbols
+
     def filter(self, txt):
         if isinstance(txt, (tuple,list)):
             txt = ' '.join(map(self.clean, txt))
 
-        return self.clean(txt)
+        txt = self.clean(txt)
+        return self.remove(txt, self.symbols)
 
     @classmethod
     def clean(self, txt):
@@ -138,6 +144,12 @@ class CleanText(Filter):
         txt = re.sub(u'[\s\xa0\t]+', u' ', txt)   # 'foo bar'
         return txt.strip()
 
+    @classmethod
+    def remove(self, txt, symbols):
+        for symbol in symbols:
+            txt = txt.replace(symbol, '')
+        return txt
+
 class CleanDecimal(CleanText):
     """
     Get a cleaned Decimal value from an element.
@@ -168,21 +180,6 @@ class Attr(_Filter):
     def __call__(self, item):
         return item.use_selector(getattr(item, 'obj_%s' % self.name))
 
-class CleanChars(Filter):
-    """
-    Remove chars.
-    """
-    def __init__(self, selector, symbols):
-        super(CleanChars, self).__init__(selector)
-        self.symbols = symbols
-
-    def filter(self, txt):
-        if isinstance(txt, (tuple,list)):
-            txt = ' '.join([t.strip() for t in txt.itertext()])
-
-        for symbol in self.symbols:
-            txt = txt.replace(symbol, '')
-        return txt
 
 class Regexp(Filter):
     """