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
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
|
'''
Care about office's formats
'''
import os
import logging
import zipfile
import fileinput
import xml.dom.minidom as minidom
try:
import cairo
from gi.repository 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 by
trying to read the meta.xml file.
'''
zipin = zipfile.ZipFile(self.filename, 'r')
metadata = {}
try:
content = zipin.read('meta.xml')
dom1 = minidom.parseString(content)
elements = dom1.getElementsByTagName('office:meta')
for i in elements[0].childNodes:
if i.tagName != 'meta:document-statistic':
nodename = ''.join([k for k in i.nodeName.split(':')[1:]])
metadata[nodename] = ''.join([j.data for j in i.childNodes])
else:
# thank you w3c for not providing a nice
# method to get all attributes from a node
pass
zipin.close()
except KeyError: # no meta.xml file found
logging.debug('%s has no opendocument metadata' % self.filename)
return metadata
def remove_all(self):
'''
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)
_, ext = os.path.splitext(name)
if item.endswith('manifest.xml'):
# contain the list of all files present in the archive
zipin.extract(item, self.tempdir)
for line in fileinput.input(name, inplace=1):
#remove the line which contains "meta.xml"
line = line.strip()
if not 'meta.xml' in line:
print line
zipout.write(name, item)
elif ext in parser.NOMETA or item == 'mimetype':
#keep NOMETA files, and the "manifest" file
if item != 'meta.xml': # contains the metadata
zipin.extract(item, self.tempdir)
zipout.write(name, item)
else:
zipin.extract(item, self.tempdir)
if os.path.isfile(name):
try:
cfile = mat.create_class_file(name, False,
add2archive=self.add2archive)
cfile.remove_all()
logging.debug('Processing %s from %s' % (item,
self.filename))
zipout.write(name, item)
except:
logging.info('%s\'s fileformat is not supported' % item)
if self.add2archive:
zipout.write(name, item)
zipout.comment = ''
logging.info('%s processed' % self.filename)
zipin.close()
zipout.close()
self.do_backup()
return True
def is_clean(self):
'''
Check if the file is clean from harmful metadatas
'''
zipin = zipfile.ZipFile(self.filename, 'r')
try:
zipin.getinfo('meta.xml')
except KeyError: # no meta.xml in the file
czf = archive.ZipStripper(self.filename, self.parser,
'application/zip', False, add2archive=self.add2archive)
if czf.is_clean():
zipin.close()
return True
zipin.close()
return False
class PdfStripper(parser.GenericParser):
'''
Represent a PDF file
'''
def __init__(self, filename, parser, mime, backup, **kwargs):
super(PdfStripper, self).__init__(filename, parser, mime, backup, **kwargs)
uri = 'file://' + os.path.abspath(self.filename)
self.password = None
self.pdf_quality = kwargs['low_pdf_quality']
self.document = Poppler.Document.new_from_file(uri, self.password)
self.meta_list = frozenset(['title', 'author', 'subject', 'keywords', 'creator',
'producer', 'metadata'])
def is_clean(self):
'''
Check if the file is clean from harmful metadatas
'''
for key in self.meta_list:
if self.document.get_property(key):
return False
return True
def remove_all(self):
'''
Opening the PDF with poppler, then doing a render
on a cairo pdfsurface for each pages.
http://cairographics.org/documentation/pycairo/2/
python-poppler is not documented at all : have fun ;)
'''
page = self.document.get_page(0)
# assume that every pages are the same size
page_width, page_height = page.get_size()
surface = cairo.PDFSurface(self.output, page_width, page_height)
context = cairo.Context(surface) # context draws on the surface
logging.debug('PDF rendering of %s' % self.filename)
for pagenum in xrange(self.document.get_n_pages()):
page = self.document.get_page(pagenum)
context.translate(0, 0)
if self.pdf_quality:
page.render(context) # render the page on context
else:
page.render_for_printing(context) # render the page on context
context.show_page() # draw context on surface
surface.finish()
try:
import pdfrw # For now, poppler cannot write meta, so we must use pdfrw
logging.debug('Removing %s\'s superficial metadata' % self.filename)
trailer = pdfrw.PdfReader(self.output)
trailer.Info.Producer = None
trailer.Info.Creator = None
writer = pdfrw.PdfWriter()
writer.trailer = trailer
writer.write(self.output)
self.do_backup()
except:
print('Unable to remove all metadata from %s, please install\
pdfrw' % self.output)
return False
return True
def get_meta(self):
'''
Return a dict with all the meta of the file
'''
metadata = {}
for key in self.meta_list:
if self.document.get_property(key):
metadata[key] = self.document.get_property(key)
return metadata
class OpenXmlStripper(archive.GenericArchiveStripper):
'''
Represent an office openxml document, which is like
an opendocument format, with some tricky stuff added.
It contains mostly xml, but can have media blobs, crap, ...
(I don't like this format.)
'''
def remove_all(self):
'''
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)
_, ext = os.path.splitext(name)
if item.startswith('docProps/'): # metadatas
pass
elif ext in parser.NOMETA or item == '.rels':
#keep parser.NOMETA files, and the file named ".rels"
zipin.extract(item, self.tempdir)
zipout.write(name, item)
else:
zipin.extract(item, self.tempdir)
if os.path.isfile(name): # don't care about folders
try:
cfile = mat.create_class_file(name, False,
add2archive=self.add2archive)
cfile.remove_all()
logging.debug('Processing %s from %s' % (item,
self.filename))
zipout.write(name, item)
except:
logging.info('%s\'s fileformat is not supported' % item)
if self.add2archive:
zipout.write(name, item)
zipout.comment = ''
logging.info('%s processed' % self.filename)
zipin.close()
zipout.close()
self.do_backup()
return True
def is_clean(self):
'''
Check if the file is clean from harmful metadatas
'''
zipin = zipfile.ZipFile(self.filename, 'r')
for item in zipin.namelist():
if item.startswith('docProps/'):
return False
zipin.close()
czf = archive.ZipStripper(self.filename, self.parser,
'application/zip', False, add2archive=self.add2archive)
return czf.is_clean()
def get_meta(self):
'''
Return a dict with all the meta of the file
'''
zipin = zipfile.ZipFile(self.filename, 'r')
metadata = {}
for item in zipin.namelist():
if item.startswith('docProps/'):
metadata[item] = 'harmful content'
zipin.close()
return metadata
|
