Pyflakes and pep8 validation

9 files changed, 151 insertions, 90 deletions

diff --git a/cli.py b/cli.py
index b9c8a5c..bfedbf6 100755
--- a/cli.py
+++ b/cli.py
@@ -10,10 +10,11 @@ import hachoir_core
 
 __version__ = '0.1'
 
+
 def parse():
     parser = optparse.OptionParser(usage='%prog [options] filename')
-    parser.add_option('--add2archive', '-a', action='store_true', default=False,
-        help='Add to outputed archive non-supported filetypes')
+    parser.add_option('--add2archive', '-a', action='store_true',
+        default=False, help='Add to outputed archive non-supported filetypes')
     parser.add_option('--backup', '-b', action='store_true', default=False,
         help='Keep a backup copy')
     parser.add_option('--check', '-c',  action='store_true', default=False,
@@ -31,15 +32,17 @@ def parse():
         sys.exit(0)
     return values, arguments
 
+
 def display_version(*args):
     print('Metadata Anonymisation Toolkit version %s') % mat.__version__
     print('CLI version %s') % __version__
     print('Hachoir version %s') % hachoir_core.__version__
     sys.exit(0)
 
+
 def list_meta(class_file, filename):
     '''
-        Print all the meta of 'filename' on stdout
+        Print all the meta of 'filename' on stdout
     '''
     print('[+] File %s :' % filename)
     if class_file.is_clean():
@@ -48,18 +51,20 @@ def list_meta(class_file, filename):
         for key, value in class_file.get_meta().iteritems():
             print(key + ' : ' + str(value))
 
+
 def is_clean(class_file, filename):
     '''
-        Say if 'filename' is clean or not
+        Say if 'filename' is clean or not
     '''
     if class_file.is_clean():
         print('[+] %s is clean' % filename)
     else:
         print('[+] %s is not clean' % filename)
 
+
 def clean_meta(class_file, filename):
     '''
-        Clean the file 'filename'
+        Clean the file 'filename'
     '''
     print('[+] Cleaning %s' % filename)
     if class_file.is_clean():
@@ -68,9 +73,10 @@ def clean_meta(class_file, filename):
         class_file.remove_all()
         print('%s cleaned !' % filename)
 
+
 def clean_meta_ugly(class_file, filename):
     '''
-        Clean the file 'filename', ugly way
+        Clean the file 'filename', ugly way
     '''
     print('[+] Cleaning %s' % filename)
     if class_file.is_clean():
@@ -79,17 +85,18 @@ def clean_meta_ugly(class_file, filename):
         class_file.remove_all_ugly()
         print('%s cleaned' % filename)
 
+
 def main():
     args, filenames = parse()
 
     #func receive the function correponding to the options given as parameters
-    if args.display is True: #only print metadatas
+    if args.display is True:  # only print metadatas
         func = list_meta
-    elif args.check is True: #only check if the file is clean
+    elif args.check is True:  # only check if the file is clean
         func = is_clean
-    elif args.ugly is True: #destructive anonymisation method
+    elif args.ugly is True:  # destructive anonymisation method
         func = clean_meta_ugly
-    else: #clean the file
+    else:  # clean the file
         func = clean_meta
 
     for filename in filenames:
diff --git a/gui.py b/gui.py
index 978bd4b..550010a 100644
--- a/gui.py
+++ b/gui.py
@@ -1,21 +1,21 @@
 #!/usr/bin/env python
 
-from gi.repository import Gtk, GObject, Gdk
+from gi.repository import Gtk, GObject
 import os
-import glob
 import logging
 from lib import mat
 
 __version__ = '0.1'
 __author__ = 'jvoisin'
 
-logging.basicConfig(level = mat.LOGGING_LEVEL)
+logging.basicConfig(level=mat.LOGGING_LEVEL)
 
 SUPPORTED = (('image/png', 'image/jpeg', 'image/gif',
             'misc/pdf'),
             ('*.jpg', '*.jpeg', '*.png', '*.bmp', '*.pdf',
             '*.tar', '*.tar.bz2', '*.tar.gz', '*.mp3'))
 
+
 class cfile(GObject.GObject):
     '''
         Contain the class-file of the file "path"
@@ -29,6 +29,7 @@ class cfile(GObject.GObject):
         except:
             self.file = None
 
+
 class ListStoreApp:
     '''
         Main GUI class
@@ -40,7 +41,8 @@ class ListStoreApp:
         self.add2archive = True
 
         self.window = Gtk.Window()
-        self.window.set_title('Metadata Anonymisation Toolkit %s' % __version__)
+        self.window.set_title('Metadata Anonymisation Toolkit %s' %
+            __version__)
         self.window.connect('destroy', Gtk.main_quit)
         self.window.set_default_size(800, 600)
 
@@ -55,13 +57,12 @@ class ListStoreApp:
         vbox.pack_start(content, True, True, 0)
 
         #parser.class - name - type - cleaned
-        self.liststore= Gtk.ListStore(cfile ,str, str, str)
+        self.liststore= Gtk.ListStore(cfile, str, str, str)
 
         treeview = Gtk.TreeView(model=self.liststore)
-        treeview.set_search_column(1) #name column is searchable
-        treeview.set_rules_hint(True) #alternate colors for rows
-        treeview.set_rubber_banding(True) #mouse selection
-        treeview.drag_dest_set(Gtk.DestDefaults.ALL, None, Gdk.DragAction.COPY)
+        treeview.set_search_column(1)  # name column is searchable
+        treeview.set_rules_hint(True)  # alternate colors for rows
+        treeview.set_rubber_banding(True)  # mouse selection
         self.add_columns(treeview)
         self.selection = treeview.get_selection()
         self.selection.set_mode(Gtk.SelectionMode.MULTIPLE)
@@ -80,12 +81,12 @@ class ListStoreApp:
         '''
         toolbar = Gtk.Toolbar()
 
-        toolbutton = Gtk.ToolButton(label = 'Add', stock_id=Gtk.STOCK_ADD)
+        toolbutton = Gtk.ToolButton(label='Add', stock_id=Gtk.STOCK_ADD)
         toolbutton.connect('clicked', self.add_files)
         toolbutton.set_tooltip_text('Add files')
         toolbar.add(toolbutton)
 
-        toolbutton = Gtk.ToolButton(label = 'Clean',
+        toolbutton = Gtk.ToolButton(label='Clean',
             stock_id=Gtk.STOCK_PRINT_REPORT)
         toolbutton.connect('clicked', self.mat_clean)
         toolbutton.set_tooltip_text('Clean selected files without data loss')
@@ -93,7 +94,8 @@ class ListStoreApp:
 
         toolbutton = Gtk.ToolButton(label='Brute Clean',
             stock_id=Gtk.STOCK_PRINT_WARNING)
-        toolbutton.set_tooltip_text('Clean selected files with possible data loss')
+        toolbutton.set_tooltip_text('Clean selected files with possible data \
+            loss')
         toolbar.add(toolbutton)
 
         toolbutton = Gtk.ToolButton(label='Check', stock_id=Gtk.STOCK_FIND)
@@ -117,8 +119,8 @@ class ListStoreApp:
 
         for i, j in enumerate(colname):
             filenameColumn = Gtk.CellRendererText()
-            column = Gtk.TreeViewColumn(j, filenameColumn, text=i+1)
-            column.set_sort_column_id(i+1)
+            column = Gtk.TreeViewColumn(j, filenameColumn, text=i + 1)
+            column.set_sort_column_id(i + 1)
             treeview.append_column(column)
 
     def create_menu_item(self, name, func, menu, pix):
@@ -156,8 +158,8 @@ class ListStoreApp:
             Gtk.STOCK_QUIT)
 
         edit_menu = self.create_sub_menu('Edit', menubar)
-        self.create_menu_item('Clear the filelist', self.clear_model, edit_menu,
-            Gtk.STOCK_REMOVE)
+        self.create_menu_item('Clear the filelist', self.clear_model,
+            edit_menu, Gtk.STOCK_REMOVE)
         self.create_menu_item('Preferences', self.preferences, edit_menu,
             Gtk.STOCK_PREFERENCES)
 
@@ -181,9 +183,9 @@ class ListStoreApp:
         '''
         filter = Gtk.FileFilter()
         filter.set_name('Supported files')
-        for item in SUPPORTED[0]: #add by mime
+        for item in SUPPORTED[0]:  # add by mime
             filter.add_mime_type(item)
-        for item in SUPPORTED[1]: #add by extension
+        for item in SUPPORTED[1]:  # add by extension
             filter.add_pattern(item)
         return filter
 
@@ -195,8 +197,7 @@ class ListStoreApp:
             title='Choose files',
             parent=None,
             action=Gtk.FileChooserAction.OPEN,
-            buttons=(Gtk.STOCK_OK, 0, Gtk.STOCK_CANCEL, 1)
-            )
+            buttons=(Gtk.STOCK_OK, 0, Gtk.STOCK_CANCEL, 1))
         chooser.set_default_response(0)
         chooser.set_select_multiple(True)
 
@@ -208,15 +209,15 @@ class ListStoreApp:
 
         response = chooser.run()
 
-        if response is 0: #Gtk.STOCK_OK
+        if response is 0:  # Gtk.STOCK_OK
             filenames = chooser.get_filenames()
             chooser.destroy()
             for item in filenames:
-                if os.path.isdir(item): #directory
+                if os.path.isdir(item):  # directory
                     for root, dirs, files in os.walk(item):
                         for name in files:
                             self.populate(os.path.join(root, name))
-                else: #regular file
+                else:  # regular file
                     self.populate(item)
         chooser.destroy()
 
@@ -226,7 +227,8 @@ class ListStoreApp:
         '''
         cf = cfile(item, self.backup, self.add2archive)
         if cf.file is not None:
-            self.liststore.append([cf, cf.file.filename, cf.file.mime,'unknow'])
+            self.liststore.append([cf, cf.file.filename,
+                cf.file.mime, 'unknow'])
 
     def about(self, button=None):
         w = Gtk.AboutDialog()
@@ -235,7 +237,7 @@ class ListStoreApp:
         w.set_comments('This software was coded during the GSoC 2011')
         w.set_website('https://gitweb.torproject.org/user/jvoisin/mat.git')
         w.set_website_label('Website')
-        w.set_authors(['Julien (jvoisin) Voisin',])
+        w.set_authors(['Julien (jvoisin) Voisin', ])
         w.set_program_name('Metadata Anonymistion Toolkit')
         click = w.run()
         if click:
@@ -250,29 +252,30 @@ class ListStoreApp:
         hbox = Gtk.HBox()
         content_area.pack_start(hbox, False, False, 0)
         icon = Gtk.Image(stock=Gtk.STOCK_PREFERENCES,
-            icon_size=Gtk.IconSize.DIALOG)#the little picture on the left
+            icon_size=Gtk.IconSize.DIALOG)  # the little picture on the left
 
         hbox.pack_start(icon, False, False, 0)
 
-        table = Gtk.Table(3, 2, False)#nb rows, nb lines
+        table = Gtk.Table(3, 2, False)  # nb rows, nb lines
         table.set_row_spacings(4)
         table.set_col_spacings(4)
         hbox.pack_start(table, True, True, 0)
 
         force = Gtk.CheckButton('Force Clean', False)
         force.connect('toggled', self.invert, 'force')
-        force.set_tooltip_text('Do not check if already clean before cleaning.')
+        force.set_tooltip_text('Do not check if already clean before cleaning')
         force.set_active(self.force)
 
         backup = Gtk.CheckButton('Backup', False)
         backup.connect('toggled', self.invert, 'backup')
-        backup.set_tooltip_text('Keep a backup copy.')
+        backup.set_tooltip_text('Keep a backup copy')
         backup.set_active(self.backup)
 
-        add2archive = Gtk.CheckButton('Add unsupported file to archives', False)
+        add2archive = Gtk.CheckButton('Add unsupported file to archives',
+            False)
         add2archive.connect('toggled', self.invert, 'add2archive')
-        add2archive.set_tooltip_text('Add non-supported (and so non-anonymised)\
- file to outputed archive.')
+        add2archive.set_tooltip_text('Add non-supported (and so \
+non-anonymised) file to outputed archive')
         add2archive.set_active(self.add2archive)
 
         table.attach_defaults(force, 0, 1, 0, 1)
@@ -281,10 +284,10 @@ class ListStoreApp:
 
         hbox.show_all()
         response = dialog.run()
-        if response is 0:#Gtk.STOCK_OK
+        if response is 0:  # Gtk.STOCK_OK
             dialog.destroy()
 
-    def invert(self, button, name): #Still not better :/
+    def invert(self, button, name):  # still not better :/
         if name is 'force':
             self.force = not self.force
         elif name is 'ugly':
@@ -338,8 +341,9 @@ class ListStoreApp:
                         self.liststore[i][0].file.remove_all_ugly()
             self.liststore[i][3] = 'clean'
 
+
 def main():
-    app = ListStoreApp()
+    ListStoreApp()
     Gtk.main()
 
 if __name__ == '__main__':
diff --git a/lib/archive.py b/lib/archive.py
index f22af39..f11506a 100644
--- a/lib/archive.py
+++ b/lib/archive.py
@@ -9,11 +9,13 @@ import tempfile
 import parser
 import mat
 
+
 class GenericArchiveStripper(parser.Generic_parser):
     '''
         Represent a generic archive
     '''
-    def __init__(self, realname, filename, parser, editor, backup, add2archive):
+    def __init__(self, realname, filename, parser, editor, backup,
+        add2archive):
         super(GenericArchiveStripper, self).__init__(realname,
             filename, parser, editor, backup, add2archive)
         self.compression = ''
@@ -32,6 +34,7 @@ class GenericArchiveStripper(parser.Generic_parser):
     def remove_all_ugly(self):
         self._remove_all('ugly')
 
+
 class ZipStripper(GenericArchiveStripper):
     '''
         Represent a zip file
@@ -94,7 +97,6 @@ harmless format' % item.filename)
         zipin.close()
         return metadata
 
-
     def _remove_all(self, method):
         '''
             So far, the zipfile module does not allow to write a ZipInfo
@@ -150,7 +152,7 @@ class TarStripper(GenericArchiveStripper):
         for item in tarin.getmembers():
             tarin.extract(item, self.tempdir)
             name = os.path.join(self.tempdir, item.name)
-            if item.type is '0': #is item a regular file ?
+            if item.type is '0':  # is item a regular file ?
                 #no backup file
                 try:
                     cfile = mat.create_class_file(name, False,
@@ -164,7 +166,7 @@ class TarStripper(GenericArchiveStripper):
                     logging.info('%s\' format is not supported' %
                         item.name)
                     if self.add2archive:
-                        tarout.add(name, item.name,filter=self._remove)
+                        tarout.add(name, item.name, filter=self._remove)
                 mat.secure_remove(name)
         tarin.close()
         tarout.close()
@@ -194,7 +196,7 @@ class TarStripper(GenericArchiveStripper):
                 return False
             tarin.extract(item, self.tempdir)
             name = os.path.join(self.tempdir, item.name)
-            if item.type is '0': #is item a regular file ?
+            if item.type is '0':  # is item a regular file ?
                 #no backup file
                 try:
                     class_file = mat.create_class_file(name,
@@ -216,7 +218,7 @@ class TarStripper(GenericArchiveStripper):
         metadata = {}
         for current_file in tarin.getmembers():
             if current_file.type is '0':
-                if not self.is_file_clean(current_file):#if there is meta
+                if not self.is_file_clean(current_file):  # if there is meta
                     current_meta = {}
                     current_meta['mtime'] = current_file.mtime
                     current_meta['uid'] = current_file.uid
@@ -229,14 +231,16 @@ class TarStripper(GenericArchiveStripper):
 
 
 class GzipStripper(TarStripper):
-    def __init__(self, realname, filename, parser, editor, backup, add2archive):
+    def __init__(self, realname, filename, parser, editor, backup,
+        add2archive):
         super(GzipStripper, self).__init__(realname,
             filename, parser, editor, backup, add2archive)
         self.compression = ':gz'
 
 
 class Bzip2Stripper(TarStripper):
-    def __init__(self, realname, filename, parser, editor, backup, add2archive):
+    def __init__(self, realname, filename, parser, editor, backup,
+        add2archive):
         super(Bzip2Stripper, self).__init__(realname,
             filename, parser, editor, backup, add2archive)
         self.compression = ':bz2'
diff --git a/lib/audio.py b/lib/audio.py
index 6d653bc..35d4fde 100644
--- a/lib/audio.py
+++ b/lib/audio.py
@@ -1,6 +1,10 @@
 import parser
 
+
 class MpegAudioStripper(parser.Generic_parser):
+    '''
+        mpeg audio file (mp3, ...)
+    '''
     def _should_remove(self, field):
         if field.name in ("id3v1", "id3v2"):
             return True
diff --git a/lib/images.py b/lib/images.py
index 4441b70..bab0bfb 100644
--- a/lib/images.py
+++ b/lib/images.py
@@ -1,8 +1,5 @@
 import parser
 
-class BmpStripper(parser.Generic_parser):
-    def _should_remove(self, field):
-        return False
 
 class JpegStripper(parser.Generic_parser):
     def _should_remove(self, field):
@@ -13,6 +10,7 @@ class JpegStripper(parser.Generic_parser):
         else:
             return False
 
+
 class PngStripper(parser.Generic_parser):
     def _should_remove(self, field):
         if field.name.startswith("text["):
diff --git a/lib/mat.py b/lib/mat.py
index ccf653f..e4371ce 100644
--- a/lib/mat.py
+++ b/lib/mat.py
@@ -23,12 +23,11 @@ __author__ = 'jvoisin'
 
 LOGGING_LEVEL = logging.DEBUG
 
-logging.basicConfig(level = LOGGING_LEVEL)
+logging.basicConfig(level=LOGGING_LEVEL)
 
 strippers = {
     hachoir_parser.image.JpegFile: images.JpegStripper,
     hachoir_parser.image.PngFile: images.PngStripper,
-    hachoir_parser.image.bmp.BmpFile: images.BmpStripper,
     hachoir_parser.audio.MpegAudioFile: audio.MpegAudioStripper,
     hachoir_parser.misc.PDFDocument: office.PdfStripper,
     hachoir_parser.archive.TarFile: archive.TarStripper,
@@ -37,6 +36,7 @@ strippers = {
     hachoir_parser.archive.zip.ZipFile: archive.ZipStripper,
 }
 
+
 def secure_remove(filename):
     '''
         securely remove the file
@@ -52,10 +52,11 @@ def is_secure(filename):
         Prevent shell injection
     '''
 
-    if not(os.path.isfile(filename)): #check if the file exist
+    if not(os.path.isfile(filename)):  # check if the file exist
         logging.error('Error: %s is not a valid file' % filename)
         return False
 
+
 def create_class_file(name, backup, add2archive):
     '''
         return a $FILETYPEStripper() class,
@@ -68,7 +69,7 @@ def create_class_file(name, backup, add2archive):
     realname = name
     try:
         filename = hachoir_core.cmd_line.unicodeFilename(name)
-    except TypeError:# get rid of "TypeError: decoding Unicode is not supported"
+    except TypeError:  # get rid of "decoding Unicode is not supported"
         filename = name
     parser = hachoir_parser.createParser(filename)
     if not parser:
@@ -88,22 +89,22 @@ def create_class_file(name, backup, add2archive):
         logging.info('Don\'t have stripper for format %s' % editor.description)
         return
 
-    if editor.input.__class__ == hachoir_parser.misc.PDFDocument:#pdf
+    if editor.input.__class__ == hachoir_parser.misc.PDFDocument:  # pdf
         return stripper_class(filename, realname, backup)
 
     elif editor.input.__class__ == hachoir_parser.archive.zip.ZipFile:
         #zip based format
         mime = mimetypes.guess_type(filename)[0]
-        try:#Ugly workaround, cleaning open document delete mime (wtf?)
+        try:  # ugly workaround, cleaning open document delete mime (wtf?)
             if mime.startswith('application/vnd.oasis.opendocument'):
                 return office.OpenDocumentStripper(realname, filename, parser,
                     editor, backup, add2archive)
-            else:#normal zip
+            else:  # normal zip
                 return stripper_class(realname, filename, parser, editor,
                     backup, add2archive)
-        except:#normal zip file
+        except:  # normal zip
             return stripper_class(realname, filename, parser, editor, backup,
                 add2archive)
-    else:#normal handling
+    else:  # normal handling
         return stripper_class(realname, filename, parser, editor, backup,
             add2archive)
diff --git a/lib/misc.py b/lib/misc.py
new file mode 100644
index 0000000..ce14313
--- /dev/null
+++ b/lib/misc.py
@@ -0,0 +1,48 @@
+import hachoir_core
+import parser
+
+
+class TorrentStripper(parser.Generic_parser):
+    '''
+        A torrent file looks like:
+        -root
+            -start
+            -announce
+            -announce-list
+            -comment
+            -created_by
+            -creation_date
+            -encoding
+            -info
+            -end
+    '''
+    def remove_all(self):
+        for field in self.editor['root']:
+            if self._should_remove(field):
+                #FIXME : hachoir does not support torrent metadata editing :<
+                del self.editor['/root/' + field.name]
+        hachoir_core.field.writeIntoFile(self.editor,
+            self.filename + parser.POSTFIX)
+        self.do_backup()
+
+    def is_clean(self):
+        for field in self.editor['root']:
+            if self._should_remove(field):
+                return False
+        return True
+
+    def get_meta(self):
+        metadata = {}
+        for field in self.editor['root']:
+            if self._should_remove(field):
+                try:  # FIXME
+                    metadata[field.name] = field.value
+                except:
+                    metadata[field.name] = 'harmful content'
+        return metadata
+
+    def _should_remove(self, field):
+        if field.name in ('comment', 'created_by', 'creation_date', 'info'):
+            return True
+        else:
+            return False
diff --git a/lib/office.py b/lib/office.py
index 27677d2..432bc0b 100644
--- a/lib/office.py
+++ b/lib/office.py
@@ -5,17 +5,16 @@ import tempfile
 import glob
 import logging
 import zipfile
-import shutil
 import re
 from xml.etree import ElementTree
 
-import hachoir_core
 
 import pdfrw
 import mat
 import parser
 import archive
 
+
 class OpenDocumentStripper(archive.GenericArchiveStripper):
     '''
         An open document file is a zip, with xml file into.
@@ -32,11 +31,10 @@ class OpenDocumentStripper(archive.GenericArchiveStripper):
             for node in tree.iter():
                 key = re.sub('{.*}', '', node.tag)
                 metadata[key] = node.text
-        except KeyError:#no meta.xml file found
+        except KeyError:  # no meta.xml file found
             logging.debug('%s has no opendocument metadata' % self.filename)
         return metadata
 
-
     def _remove_all(self, method):
         '''
             FIXME ?
@@ -50,7 +48,7 @@ class OpenDocumentStripper(archive.GenericArchiveStripper):
             name = os.path.join(self.tempdir, item)
             if item.endswith('.xml') or item == 'mimetype':
                 #keep .xml files, and the "manifest" file
-                if item != 'meta.xml':#contains the metadata
+                if item != 'meta.xml':  # contains the metadata
                     zipin.extract(item, self.tempdir)
                     zipout.write(name, item)
                     mat.secure_remove(name)
@@ -73,7 +71,7 @@ class OpenDocumentStripper(archive.GenericArchiveStripper):
                             self.filename))
                         zipout.write(name, item)
                     except:
-                        logging.info('%s\' fileformat is not supported' %  item)
+                        logging.info('%s\' fileformat is not supported' % item)
                         if self.add2archive:
                             zipout.write(name, item)
                     mat.secure_remove(name)
@@ -88,7 +86,7 @@ class OpenDocumentStripper(archive.GenericArchiveStripper):
         try:
             zipin.getinfo('meta.xml')
             return False
-        except KeyError:#no meta.xml in the file
+        except KeyError:  # no meta.xml in the file
                 zipin.close()
                 czf = archive.ZipStripper(self.realname, self.filename,
                     self.parser, self.editor, self.backup, self.add2archive)
@@ -104,7 +102,7 @@ class PdfStripper(parser.Generic_parser):
         Represent a pdf file, with the help of pdfrw
     '''
     def __init__(self, filename, realname, backup):
-        name, path = os.path.splitext(filename)
+        name, ext = os.path.splitext(filename)
         self.output = name + '.cleaned' + ext
         self.filename = filename
         self.backup = backup
@@ -137,7 +135,7 @@ class PdfStripper(parser.Generic_parser):
         '''
         _, self.tmpdir = tempfile.mkstemp()
         subprocess.call(self.convert % (self.filename, self.tmpdir +
-            'temp.jpg'), shell=True)#Convert pages to jpg
+            'temp.jpg'), shell=True)  # Convert pages to jpg
 
         for current_file in glob.glob(self.tmpdir + 'temp*'):
         #Clean every jpg image
@@ -145,18 +143,18 @@ class PdfStripper(parser.Generic_parser):
             class_file.remove_all()
 
         subprocess.call(self.convert % (self.tmpdir +
-            'temp.jpg*', self.output), shell=True)#Assemble jpg into pdf
+            'temp.jpg*', self.output), shell=True)  # Assemble jpg into pdf
 
         for current_file in glob.glob(self.tmpdir + 'temp*'):
         #remove jpg files
             mat.secure_remove(current_file)
 
         if self.backup is False:
-            mat.secure_remove(self.filename) #remove the old file
-            os.rename(self.output, self.filename)#rename the new
+            mat.secure_remove(self.filename)  # remove the old file
+            os.rename(self.output, self.filename)  # rename the new
             name = self.realname
         else:
-            name = output_file
+            name = self.output
         class_file = mat.create_class_file(name, False)
         class_file.remove_all()
 
diff --git a/lib/parser.py b/lib/parser.py
index aa7e7f1..28e0849 100644
--- a/lib/parser.py
+++ b/lib/parser.py
@@ -2,27 +2,25 @@
     Parent class of all parser
 '''
 
-import hachoir_core.error
-import hachoir_parser
-import hachoir_editor
+import hachoir_core
 
-import sys
 import os
-import subprocess
 import mimetypes
 
 import mat
 
-NOMETA = ('.txt', '.bmp', '.py', '.xml', '.rdf')
+NOMETA = ('.bmp', 'html', '.py', '.rdf', '.txt', '.xml')
+
 
 class Generic_parser(object):
-    def __init__(self, realname, filename, parser, editor, backup, add2archive):
+    def __init__(self, realname, filename, parser, editor, backup,
+        add2archive):
         basename, ext = os.path.splitext(filename)
         self.output = basename + '.cleaned' + ext
-        self.filename = filename #path + filename
-        self.realname = realname #path + filename
-        self.basename = os.path.basename(filename) #only filename
-        self.mime = mimetypes.guess_type(filename)[0] #mimetype
+        self.filename = filename  # path + filename
+        self.realname = realname  # path + filename
+        self.basename = os.path.basename(filename)  # only filename
+        self.mime = mimetypes.guess_type(filename)[0]  # mimetype
         self.parser = parser
         self.editor = editor
         self.backup = backup
@@ -56,7 +54,6 @@ class Generic_parser(object):
         '''
         self.remove_all()
 
-
     def _remove(self, field):
         '''
             Delete the given field