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
|
import os
import re
import shutil
import tempfile
import datetime
import zipfile
from typing import Dict, Set
from . import abstract, parser_factory
assert Set # make pyflakes happy
class ArchiveBasedAbstractParser(abstract.AbstractParser):
whitelist = set() # type: Set[str]
def _clean_zipinfo(self, zipinfo: zipfile.ZipInfo) -> zipfile.ZipInfo:
zipinfo.compress_type = zipfile.ZIP_DEFLATED
zipinfo.create_system = 3 # Linux
zipinfo.comment = b''
zipinfo.date_time = (1980, 1, 1, 0, 0, 0)
return zipinfo
def _get_zipinfo_meta(self, zipinfo: zipfile.ZipInfo) -> Dict[str, str]:
metadata = {}
if zipinfo.create_system == 3:
#metadata['create_system'] = 'Linux'
pass
elif zipinfo.create_system == 2:
metadata['create_system'] = 'Windows'
else:
metadata['create_system'] = 'Weird'
if zipinfo.comment:
metadata['comment'] = zipinfo.comment # type: ignore
if zipinfo.date_time != (1980, 1, 1, 0, 0, 0):
metadata['date_time'] =str(datetime.datetime(*zipinfo.date_time))
return metadata
def _clean_internal_file(self, item: zipfile.ZipInfo, temp_folder: str,
zin: zipfile.ZipFile, zout: zipfile.ZipFile) -> bool:
output = ''
zin.extract(member=item, path=temp_folder)
if item.filename not in self.whitelist:
full_path = os.path.join(temp_folder, item.filename)
tmp_parser, mtype = parser_factory.get_parser(full_path) # type: ignore
if not tmp_parser:
print("%s's format (%s) isn't supported" % (item.filename, mtype))
return False
tmp_parser.remove_all()
output = tmp_parser.output_filename
else:
output = os.path.join(temp_folder, item.filename)
zinfo = zipfile.ZipInfo(item.filename) # type: ignore
clean_zinfo = self._clean_zipinfo(zinfo)
with open(output, 'rb') as f:
zout.writestr(clean_zinfo, f.read())
return True
class MSOfficeParser(ArchiveBasedAbstractParser):
mimetypes = {
'application/vnd.openxmlformats-officedocument.wordprocessingml.document',
'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet',
'application/vnd.openxmlformats-officedocument.presentationml.presentation'
}
files_to_keep = {'_rels/.rels', 'word/_rels/document.xml.rels'}
def get_meta(self):
"""
Yes, I know that parsing xml with regexp ain't pretty,
be my guest and fix it if you want.
"""
metadata = {}
zipin = zipfile.ZipFile(self.filename)
for item in zipin.infolist():
if item.filename.startswith('docProps/') and item.filename.endswith('.xml'):
content = zipin.read(item).decode('utf-8')
try:
results = re.findall(r"<(.+)>(.+)</\1>", content, re.I|re.M)
for (key, value) in results:
metadata[key] = value
except TypeError: # We didn't manage to parse the xml file
pass
if not metadata: # better safe than sorry
metadata[item] = 'harmful content'
for key, value in self._get_zipinfo_meta(item).items():
metadata[key] = value
zipin.close()
return metadata
def remove_all(self):
zin = zipfile.ZipFile(self.filename, 'r')
zout = zipfile.ZipFile(self.output_filename, 'w')
temp_folder = tempfile.mkdtemp()
for item in zin.infolist():
if item.filename[-1] == '/':
continue # `is_dir` is added in Python3.6
elif item.filename.startswith('docProps/'):
continue # don't keep metadata files
if item.filename in self.files_to_keep:
item = self._clean_zipinfo(item)
zout.writestr(item, zin.read(item))
continue
if self._clean_internal_file(item, temp_folder, zin, zout) is False:
zout.close()
os.remove(self.output_filename)
return False
shutil.rmtree(temp_folder)
zout.close()
zin.close()
return True
class LibreOfficeParser(ArchiveBasedAbstractParser):
mimetypes = {
'application/vnd.oasis.opendocument.text',
'application/vnd.oasis.opendocument.spreadsheet',
'application/vnd.oasis.opendocument.presentation',
'application/vnd.oasis.opendocument.graphics',
'application/vnd.oasis.opendocument.chart',
'application/vnd.oasis.opendocument.formula',
'application/vnd.oasis.opendocument.image',
}
whitelist = {'mimetype', 'manifest.rdf'}
def get_meta(self):
"""
Yes, I know that parsing xml with regexp ain't pretty,
be my guest and fix it if you want.
"""
metadata = {}
zipin = zipfile.ZipFile(self.filename)
for item in zipin.infolist():
if item.filename == 'meta.xml':
content = zipin.read(item).decode('utf-8')
try:
results = re.findall(r"<((?:meta|dc|cp).+?)>(.+)</\1>", content, re.I|re.M)
for (key, value) in results:
metadata[key] = value
except TypeError: # We didn't manage to parse the xml file
pass
if not metadata: # better safe than sorry
metadata[item] = 'harmful content'
for key, value in self._get_zipinfo_meta(item).items():
metadata[key] = value
zipin.close()
return metadata
def remove_all(self):
zin = zipfile.ZipFile(self.filename, 'r')
zout = zipfile.ZipFile(self.output_filename, 'w')
temp_folder = tempfile.mkdtemp()
for item in zin.infolist():
if item.filename[-1] == '/':
continue # `is_dir` is added in Python3.6
elif item.filename == 'meta.xml':
continue # don't keep metadata files
if self._clean_internal_file(item, temp_folder, zin, zout) is False:
os.remove(self.output_filename)
return False
shutil.rmtree(temp_folder)
zout.close()
zin.close()
return True
|
