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
|
'''
Care about office's formats
'''
import os
import mimetypes
import subprocess
import tempfile
import glob
import logging
import zipfile
import re
import shutil
from xml.etree import ElementTree
try:
import cairo
import poppler
except ImportError:
pass
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):
'''
Return a dict with all the meta of the file
'''
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):
'''
Check if the file is clean from harmful metadatas
'''
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
'''
def is_clean(self):
#FIXME
return False
def remove_all(self):
#FIXME
self.remove_all_ugly()
def remove_all_ugly(self):
'''
Opening the pdf with poppler, then doing a render
on a cairo pdfsurface.
'''
uri = 'file://' + self.filename
password = None
document = poppler.document_new_from_file(uri, password)
page = document.get_page(0)
page_width, page_height = page.get_size()
surface = cairo.PDFSurface(self.output, page_width, page_height)
context = cairo.Context(surface)
for i in xrange(document.get_n_pages()):
page = document.get_page(i)
context.translate(0, 0)
page.render(context)
context.show_page()
surface.finish()
def get_meta(self):
metadata={}
meta_list=('title', 'author', 'subject', 'keywords', 'creator',
'producer', 'creation-date', 'mod-date', 'metadata')
uri = 'file://' + self.filename
password = None
document = poppler.document_new_from_file(uri, password)
for key in meta_list:
self._get_meta(document, metadata, key)
return metadata
def _get_meta(self, document, metadata, key):
if document.get_property(key) is not None:
metadata[key] = document.get_property(key)
|
