add an xml parser

weboob/tools/parsers/__init__.py

@@ -38,6 +38,11 @@ def load_lxmlsoup():
     return LxmlSoupParser
 
 
+def load_xml():
+    from .lxmlparser import LxmlXmlParser
+    return LxmlXmlParser
+
+
 def load_html5lib():
     from .html5libparser import Html5libParser
     return Html5libParser
@@ -82,6 +87,7 @@ def get_parser(preference_order=('lxml', 'lxmlsoup')):
     """
     if not isinstance(preference_order, (tuple, list)):
         preference_order = [preference_order]
+
     for kind in preference_order:
         if not 'load_%s' % kind in globals():
             continue

weboob/tools/parsers/lxmlparser.py

@@ -19,31 +19,35 @@
 
 
 import re
-import lxml.html
+import lxml.html as html
+import lxml.etree as etree
 
 from .iparser import IParser
 from ..browser import BrokenPageError
 
 
-__all__ = ['LxmlHtmlParser']
+__all__ = ['LxmlHtmlParser', 'LxmlXmlParser']
 
 
-class LxmlHtmlParser(IParser):
+class LxmlParser(IParser):
     """
     Parser using lxml.
 
     Note that it is not available on every systems.
     """
 
+    def get_parser(encoding=None):
+        pass
+
     def parse(self, data, encoding=None):
         if encoding is None:
             parser = None
         else:
-            parser = lxml.html.HTMLParser(encoding=encoding)
+            parser = self.get_parser(encoding=encoding)
-        return lxml.html.parse(data, parser)
+        return self.module.parse(data, parser)
 
     def tostring(self, element):
-        return lxml.html.tostring(element, encoding=unicode)
+        return self.module.tostring(element, encoding=unicode)
 
     def tocleanstring(self, element):
         txt = [txt.strip() for txt in element.itertext()]
@@ -52,7 +56,7 @@ class LxmlHtmlParser(IParser):
         return txt.strip()
 
     def strip(self, s):
-        doc = lxml.html.fromstring(s)   # parse html string
+        doc = self.module.fromstring(s)   # parse html/xml string
         return self.tocleanstring(doc)
 
     @classmethod
@@ -97,3 +101,29 @@ class LxmlHtmlParser(IParser):
                 return results[0] if nb == 1 else results
         else:
             raise Exception('Unhandled value for kwarg "nb": %s' % nb)
+
+
+class LxmlHtmlParser(LxmlParser):
+    """
+    Parser using lxml.
+
+    Note that it is not available on every systems.
+    """
+    def __init__(self, *args, **kwargs):
+        self.module = html
+
+    def get_parser(self, encoding=None):
+        return html.HTMLParser(encoding=encoding)
+
+
+class LxmlXmlParser(LxmlParser):
+    """
+    Parser using lxml.
+
+    Note that it is not available on every systems.
+    """
+    def __init__(self, *args, **kwargs):
+        self.module = etree
+
+    def get_parser(self, encoding=None):
+        return etree.XMLParser(encoding=encoding, strip_cdata=False)