1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
|
import os
import mimetypes
import subprocess
import tempfile
import glob
import logging
import zipfile
import re
import shutil
from xml.etree import ElementTree
import pdfrw
import mat
import parser
import archive
class OpenDocumentStripper(archive.GenericArchiveStripper):
'''
An open document file is a zip, with xml file into.
The one that interest us is meta.xml
'''
def get_meta(self):
zipin = zipfile.ZipFile(self.filename, 'r')
metadata = {}
try:
content = zipin.read('meta.xml')
zipin.close()
tree = ElementTree.fromstring(content)
for node in tree.iter():
key = re.sub('{.*}', '', node.tag)
metadata[key] = node.text
except KeyError: # no meta.xml file found
logging.debug('%s has no opendocument metadata' % self.filename)
return metadata
def _remove_all(self, method):
'''
FIXME ?
There is a patch implementing the Zipfile.remove()
method here : http://bugs.python.org/issue6818
'''
zipin = zipfile.ZipFile(self.filename, 'r')
zipout = zipfile.ZipFile(self.output, 'w',
allowZip64=True)
for item in zipin.namelist():
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
zipin.extract(item, self.tempdir)
zipout.write(name, item)
mat.secure_remove(name)
elif item.endswith('manifest.xml'):
zipin.extract(item, self.tempdir)
#remove line meta.xml
zipout.write(name, item)
mat.secure_remove(name)
else:
zipin.extract(item, self.tempdir)
if os.path.isfile(name):
try:
cfile = mat.create_class_file(name, False,
self.add2archive)
if method == 'normal':
cfile.remove_all()
else:
cfile.remove_all_ugly()
logging.debug('Processing %s from %s' % (item,
self.filename))
zipout.write(name, item)
except:
logging.info('%s\' fileformat is not supported' % item)
if self.add2archive:
zipout.write(name, item)
mat.secure_remove(name)
zipout.comment = ''
logging.info('%s treated' % self.filename)
zipin.close()
zipout.close()
self.do_backup()
def is_clean(self):
zipin = zipfile.ZipFile(self.filename, 'r')
try:
zipin.getinfo('meta.xml')
return False
except KeyError: # no meta.xml in the file
zipin.close()
czf = archive.ZipStripper(self.filename, self.parser,
'application/zip', self.backup, self.add2archive)
if czf.is_clean():
return True
else:
return False
return True
class PdfStripper(parser.GenericParser):
'''
Represent a pdf file, with the help of pdfrw
'''
def __init__(self, filename, parser, mime, backup, add2archive):
name, ext = os.path.splitext(filename)
self.output = name + '.cleaned' + ext
self.filename = filename
self.backup = backup
self.realname = realname
self.shortname = os.path.basename(filename)
self.mime = mime
self.tempdir = tempfile.mkdtemp()
self.trailer = pdfrw.PdfReader(self.filename)
self.writer = pdfrw.PdfWriter()
self.convert = 'gm convert -antialias -enhance %s %s'
def __del__(self):
'''
Remove the temp dir
'''
shutil.rmtree(self.tempdir)
def remove_all(self):
'''
Remove all the meta fields that are compromizing
'''
self.trailer.Info.Title = ''
self.trailer.Info.Author = ''
self.trailer.Info.Producer = ''
self.trailer.Info.Creator = ''
self.trailer.Info.CreationDate = ''
self.trailer.Info.ModDate = ''
self.writer.trailer = self.trailer
self.writer.write(self.output)
self.do_backup()
def remove_all_ugly(self):
'''
Transform each pages into a jpg, clean them,
then re-assemble them into a new pdf
'''
subprocess.call(self.convert % (self.filename, self.tempdir +
'temp.jpg'), shell=True) # Convert pages to jpg
for current_file in glob.glob(self.tempdir + 'temp*'):
#Clean every jpg image
class_file = mat.create_class_file(current_file, False, False)
class_file.remove_all()
subprocess.call(self.convert % (self.tempdir +
'temp.jpg*', self.output), shell=True) # Assemble jpg into pdf
for current_file in glob.glob(self.tempdir + '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
name = self.realname
else:
name = self.output
class_file = mat.create_class_file(name, False, False)
class_file.remove_all()
def is_clean(self):
'''
Check if the file is clean from harmful metadatas
'''
for field in self.trailer.Info:
if field != '':
return False
return True
def get_meta(self):
'''
return a dict with all the meta of the file
'''
metadata = {}
for key, value in self.trailer.Info.iteritems():
metadata[key[1:]] = value[1:-1]
return metadata
|
