first step in python3 support

weboob/tools/browser2/browser.py

@@ -17,10 +17,13 @@
 # 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 __future__ import absolute_import
+from __future__ import absolute_import, print_function
 
 import re
-from urlparse import urlparse, urljoin
+try:
+    from urllib.parse import urlparse, urljoin
+except ImportError:
+    from urlparse import urlparse, urljoin
 import mimetypes
 import os
 import tempfile
@@ -157,7 +160,7 @@ class BaseBrowser(object):
     def _save(self, response, warning=False, **kwargs):
         if self.responses_dirname is None:
             self.responses_dirname = tempfile.mkdtemp(prefix='weboob_session_')
-            print >>sys.stderr, 'Debug data will be saved in this directory: %s' % self.responses_dirname
+            print('Debug data will be saved in this directory: %s' % self.responses_dirname, file=sys.stderr)
         elif not os.path.isdir(self.responses_dirname):
             os.makedirs(self.responses_dirname)
 

weboob/tools/browser2/cookies.py

@@ -17,7 +17,10 @@
 # along with weboob. If not, see <http://www.gnu.org/licenses/>.
 
 import requests.cookies
-import cookielib
+try:
+    import cookielib
+except ImportError:
+    import http.cookiejar as cookielib
 
 
 __all__ = ['WeboobCookieJar']

weboob/tools/browser2/filters.py

@@ -26,6 +26,7 @@ import re
 import lxml.html as html
 
 from weboob.tools.misc import html2text
+from weboob.tools.compat import basestring
 from weboob.capabilities.base import empty
 
 
@@ -258,7 +259,7 @@ class CleanDecimal(CleanText):
         if self.replace_dots:
             text = text.replace('.','').replace(',','.')
         try:
-            return Decimal(re.sub(ur'[^\d\-\.]', '', text))
+            return Decimal(re.sub(r'[^\d\-\.]', '', text))
         except InvalidOperation as e:
             return self.default_or_raise(e)
 
@@ -388,7 +389,7 @@ class DateGuesser(Filter):
 
 class Time(Filter):
     klass = datetime.time
-    regexp = re.compile(ur'(?P<hh>\d+):?(?P<mm>\d+)(:(?P<ss>\d+))?')
+    regexp = re.compile(r'(?P<hh>\d+):?(?P<mm>\d+)(:(?P<ss>\d+))?')
     kwargs = {'hour': 'hh', 'minute': 'mm', 'second': 'ss'}
 
     def __init__(self, selector, default=_NO_DEFAULT):
@@ -407,7 +408,7 @@ class Time(Filter):
 
 class Duration(Time):
     klass = datetime.timedelta
-    regexp = re.compile(ur'((?P<hh>\d+)[:;])?(?P<mm>\d+)[;:](?P<ss>\d+)')
+    regexp = re.compile(r'((?P<hh>\d+)[:;])?(?P<mm>\d+)[;:](?P<ss>\d+)')
     kwargs = {'hours': 'hh', 'minutes': 'mm', 'seconds': 'ss'}
 
 

weboob/tools/browser2/page.py

@@ -19,18 +19,22 @@
 
 from __future__ import absolute_import
 
-from urllib import unquote
+try:
+    from urllib.parse import unquote
+except ImportError:
+    from urllib import unquote
 import requests
 import re
 import sys
 from copy import deepcopy
-from cStringIO import StringIO
+from io import BytesIO
 import lxml.html as html
 import lxml.etree as etree
 
 from weboob.tools.json import json
 from weboob.tools.ordereddict import OrderedDict
 from weboob.tools.regex_helper import normalize
+from weboob.tools.compat import basestring
 
 from weboob.tools.log import getLogger
 
@@ -527,7 +531,7 @@ class XMLPage(BasePage):
     def __init__(self, browser, response, *args, **kwargs):
         super(XMLPage, self).__init__(browser, response, *args, **kwargs)
         parser = etree.XMLParser(encoding=self.ENCODING or response.encoding)
-        self.doc = etree.parse(StringIO(response.content), parser)
+        self.doc = etree.parse(BytesIO(response.content), parser)
 
 
 class RawPage(BasePage):
@@ -551,7 +555,7 @@ class HTMLPage(BasePage):
     def __init__(self, browser, response, *args, **kwargs):
         super(HTMLPage, self).__init__(browser, response, *args, **kwargs)
         parser = html.HTMLParser(encoding=self.ENCODING or response.encoding)
-        self.doc = html.parse(StringIO(response.content), parser)
+        self.doc = html.parse(BytesIO(response.content), parser)
 
     def get_form(self, xpath='//form', name=None, nr=None):
         """