add a 'raw' parser

weboob/tools/parsers/__init__.py

@@ -59,6 +59,12 @@ def load_json():
     from .jsonparser import JsonParser
     return JsonParser
 
+def load_raw():
+    # This parser doesn't read HTML, don't include it in the
+    # preference_order default value below.
+    from .iparser import RawParser
+    return RawParser
+
 
 def get_parser(preference_order=('lxml', 'lxmlsoup')):
     """

weboob/tools/parsers/iparser.py

@@ -21,7 +21,7 @@
 import re
 
 
-__all__ = ['IParser']
+__all__ = ['IParser', 'RawParser']
 
 
 class IParser(object):
@@ -53,3 +53,10 @@ class IParser(object):
         """
         p = re.compile(r'<.*?>')
         return p.sub(' ', data).strip()
+
+class RawParser(IParser):
+    def parse(self, data, encoding=None):
+        return data.read()
+
+    def tostring(self, elem):
+        return elem