add new lxmlsoup parser

weboob/tools/parsers/__init__.py

@@ -30,6 +30,10 @@ def load_lxml():
     from .lxmlparser import LxmlHtmlParser
     return LxmlHtmlParser
 
+def load_lxmlsoup():
+    from .lxmlsoupparser import LxmlSoupParser
+    return LxmlSoupParser
+
 def load_html5lib():
     from .html5libparser import Html5libParser
     return Html5libParser
@@ -42,7 +46,7 @@ def load_builtin():
     from .htmlparser import HTMLParser
     return HTMLParser
 
-def get_parser(preference_order=('lxml', 'html5lib', 'elementtidy', 'builtin')):
+def get_parser(preference_order=('lxml', 'lxmlsoup', 'html5lib', 'elementtidy', 'builtin')):
     """
     Get a parser from a preference order list.
     This allows Weboob to run on systems without lxml, which is the default parser.

weboob/tools/parsers/lxmlsoupparser.py

@@ -0,0 +1,38 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010  Christophe Benz
+# 
+# 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 lxml.html
+import lxml.html.soupparser
+
+from .iparser import IParser
+
+
+__all__ = ['LxmlHtmlParser']
+
+
+class LxmlSoupParser(IParser):
+    """
+    Parser using lxml elementsoup.
+
+    Note that it is not available on every systems.
+    """
+
+    def parse(self, data, encoding=None):
+        return lxml.html.soupparser.parse(data)
+
+    def tostring(self, element):
+        return lxml.html.tostring(element, encoding=unicode)