Move the import oh html2text outside of misc

modules/adecco/pages.py

@@ -19,7 +19,7 @@
 
 
 from weboob.tools.browser import BasePage
-from weboob.tools.misc import html2text
+from weboob.tools.html import html2text
 from .job import AdeccoJobAdvert
 import datetime
 import re

modules/apec/pages.py

@@ -19,7 +19,7 @@
 
 
 from weboob.tools.browser import BasePage
-from weboob.tools.misc import html2text
+from weboob.tools.html import html2text
 import dateutil.parser
 import re
 

modules/arte/pages.py

@@ -19,7 +19,7 @@
 
 
 from weboob.tools.browser import BasePage
-from weboob.tools.misc import html2text
+from weboob.tools.html import html2text
 from weboob.capabilities import NotAvailable
 from weboob.capabilities.image import BaseImage
 from weboob.capabilities.collection import Collection

modules/aum/contact.py

@@ -25,7 +25,7 @@ from dateutil.parser import parse as parse_dt
 
 from weboob.tools.ordereddict import OrderedDict
 from weboob.capabilities.contact import Contact as _Contact, ProfileNode
-from weboob.tools.misc import html2text
+from weboob.tools.html import html2text
 
 
 class FieldBase(object):

modules/champslibres/pages.py

@@ -21,7 +21,7 @@ from datetime import date
 from weboob.capabilities.library import Book, Renew
 from weboob.tools.browser import BasePage
 from weboob.tools.mech import ClientForm
-from weboob.tools.misc import html2text
+from weboob.tools.html import html2text
 
 
 class SkipPage(BasePage):

modules/dailymotion/pages.py

@@ -26,7 +26,7 @@ import mechanize
 
 from weboob.capabilities import NotAvailable
 from weboob.capabilities.image import BaseImage
-from weboob.tools.misc import html2text
+from weboob.tools.html import html2text
 from weboob.tools.browser import BasePage, BrokenPageError
 
 

modules/ehentai/pages.py

@@ -19,7 +19,7 @@
 
 
 from weboob.tools.browser import BasePage
-from weboob.tools.misc import html2text
+from weboob.tools.html import html2text
 from weboob.capabilities.image import BaseImage
 
 from datetime import datetime

modules/gazelle/pages/torrents.py

@@ -23,7 +23,8 @@ import urlparse
 from logging import warning, debug
 from urlparse import parse_qs
 
-from weboob.tools.misc import html2text, get_bytes_size
+from weboob.tools.misc import get_bytes_size
+from weboob.tools.html import html2text
 from weboob.capabilities.torrent import Torrent
 from weboob.capabilities.base import NotLoaded
 

modules/lefigaro/test.py

@@ -19,7 +19,7 @@
 
 
 from weboob.tools.test import BackendTest
-from weboob.tools.misc import html2text
+from weboob.tools.html import html2text
 
 
 __all__ = ['LeFigaroTest']

modules/monster/pages.py

@@ -19,7 +19,7 @@
 
 
 from weboob.tools.browser import BasePage
-from weboob.tools.misc import html2text
+from weboob.tools.html import html2text
 import re
 from datetime import datetime, time, timedelta
 from .job import MonsterJobAdvert

modules/okc/pages.py

@@ -23,7 +23,7 @@ from datetime import datetime
 from weboob.tools.browser import BasePage
 from weboob.tools.ordereddict import OrderedDict
 from weboob.capabilities.contact import ProfileNode
-from weboob.tools.misc import html2text
+from weboob.tools.html import html2text
 from weboob.tools.date import local2utc
 
 class LoginPage(BasePage):

modules/popolemploi/pages.py

@@ -17,7 +17,7 @@
 # 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 weboob.tools.misc import html2text
+from weboob.tools.html import html2text
 from weboob.tools.browser import BasePage
 import dateutil.parser
 import re

modules/senscritique/pages.py

@@ -17,7 +17,7 @@
 # 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 weboob.tools.misc import html2text
+from weboob.tools.html import html2text
 from .calendar import SensCritiquenCalendarEvent
 
 from datetime import date, datetime, time, timedelta

weboob/applications/boobmsg/boobmsg.py

@@ -32,7 +32,7 @@ from weboob.capabilities.account import CapAccount
 from weboob.capabilities.contact import CapContact
 from weboob.tools.application.repl import ReplApplication, defaultcount
 from weboob.tools.application.formatters.iformatter import IFormatter
-from weboob.tools.misc import html2text
+from weboob.tools.html import html2text
 
 
 __all__ = ['Boobmsg']

weboob/applications/boobtracker/boobtracker.py

@@ -32,7 +32,7 @@ from weboob.capabilities.base import empty, BaseObject
 from weboob.capabilities.bugtracker import CapBugTracker, Query, Update, Project, Issue, IssueError
 from weboob.tools.application.repl import ReplApplication, defaultcount
 from weboob.tools.application.formatters.iformatter import IFormatter, PrettyFormatter
-from weboob.tools.misc import html2text
+from weboob.tools.html import html2text
 from weboob.tools.date import parse_french_date
 
 

weboob/applications/comparoob/comparoob.py

@@ -23,7 +23,7 @@
 import sys
 
 from weboob.capabilities.pricecomparison import CapPriceComparison
-from weboob.tools.misc import html2text
+from weboob.tools.html import html2text
 from weboob.tools.application.repl import ReplApplication
 from weboob.tools.application.formatters.iformatter import IFormatter, PrettyFormatter
 

weboob/applications/monboob/monboob.py

@@ -36,7 +36,9 @@ from weboob.core import Weboob, CallErrors
 from weboob.core.scheduler import Scheduler
 from weboob.capabilities.messages import CapMessages, CapMessagesPost, Thread, Message
 from weboob.tools.application.repl import ReplApplication
-from weboob.tools.misc import html2text, get_backtrace, utc2local, to_unicode
+from weboob.tools.date import utc2local
+from weboob.tools.html import html2text
+from weboob.tools.misc import get_backtrace, to_unicode
 
 
 __all__ = ['Monboob']

weboob/tools/browser2/filters.py

@@ -28,7 +28,7 @@ from dateutil.parser import parse as parse_date
 from weboob.capabilities.base import empty
 from weboob.tools.compat import basestring
 from weboob.tools.exceptions import ParseError
-from weboob.tools.misc import html2text
+from weboob.tools.html import html2text
 
 _NO_DEFAULT = object()
 

weboob/tools/html.py

@@ -0,0 +1,35 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2010-2014 Romain Bignon
+#
+# This file is part of weboob.
+#
+# weboob is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# weboob 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 Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with weboob. If not, see <http://www.gnu.org/licenses/>.
+
+import warnings
+
+__all__ = ['html2text']
+
+
+try:
+    import html2text as h2t
+    h2t.UNICODE_SNOB = 1
+    h2t.SKIP_INTERNAL_LINKS = True
+    h2t.INLINE_LINKS = False
+    h2t.LINKS_EACH_PARAGRAPH = True
+    html2text = h2t.html2text
+except ImportError:
+    def html2text(html):
+        warnings.warn('python-html2text is not present. HTML pages are not converted into text.', stacklevel=2)
+        return html

weboob/tools/misc.py

@@ -18,7 +18,6 @@
 # along with weboob. If not, see <http://www.gnu.org/licenses/>.
 
 
-import warnings
 from time import time, sleep
 import os
 import sys
@@ -28,7 +27,7 @@ import types
 from .compat import unicode
 
 
-__all__ = ['get_backtrace', 'get_bytes_size', 'html2text', 'iter_fields',
+__all__ = ['get_backtrace', 'get_bytes_size', 'iter_fields',
             'to_unicode', 'limit']
 
 
@@ -58,18 +57,6 @@ def get_bytes_size(size, unit_name):
         }
     return float(size * unit_data.get(unit_name, 1))
 
-try:
-    import html2text as h2t
-    h2t.UNICODE_SNOB = 1
-    h2t.SKIP_INTERNAL_LINKS = True
-    h2t.INLINE_LINKS = False
-    h2t.LINKS_EACH_PARAGRAPH = True
-    html2text = h2t.html2text
-except ImportError:
-    def html2text(html):
-        warnings.warn('python-html2text is not present. HTML pages are not converted into text.', stacklevel=2)
-        return html
-
 
 def iter_fields(obj):
     for attribute_name in dir(obj):