move remove_html_tags function into weboob.tools.misc

weboob/backends/bp/pages/accounthistory.py

@@ -21,23 +21,13 @@
 import re
 
 from weboob.capabilities.bank import Operation
-
 from weboob.tools.browser import BasePage
+from weboob.tools.misc import remove_html_tags
 
 
 __all__ = ['AccountHistory']
 
 
-def remove_html_tags(data):
-    p = re.compile(r'<.*?>')
-    return p.sub(' ', data)
-
-
-def remove_extra_spaces(data):
-    p = re.compile(r'\s+')
-    return p.sub(' ', data)
-
-
 class AccountHistory(BasePage):
 
     def get_history(self):
@@ -50,10 +40,10 @@ class AccountHistory(BasePage):
             operation = Operation(len(operations))
             operation.date = mvt.xpath("./td/span")[0].text
             tmp = mvt.xpath("./td/span")[1]
-            operation.label = remove_extra_spaces(remove_html_tags(self.parser.tostring(tmp)))
+            operation.label = remove_html_tags(self.parser.tostring(tmp)).strip()
 
             r = re.compile(r'\d+')
-            
+
             tmp = mvt.xpath("./td/span/strong")
             if not tmp:
                 tmp = mvt.xpath("./td/span")

weboob/tools/browser/browser.py

@@ -346,7 +346,6 @@ class BaseBrowser(mechanize.Browser):
             self.page = None
             raise self.get_exception(e)(e)
         except (mechanize.BrowserStateError, BrowserRetry), e:
-            self.home()
             raise BrowserUnavailable(e)
 
     def is_on_page(self, pageCls):

weboob/tools/misc.py

@@ -24,6 +24,7 @@ from dateutil import tz
 from logging import warning
 from time import time, sleep
 from tempfile import gettempdir
+import re
 import os
 import sys
 import traceback
@@ -61,6 +62,9 @@ def get_bytes_size(size, unit_name):
         }
     return float(size * unit_data.get(unit_name, 1))
 
+def remove_html_tags(data):
+    p = re.compile(r'<.*?>')
+    return p.sub(' ', data)
 
 try:
     import html2text as h2t