def AddTags(self, pdfPath):
lstVal = self.getData()
trailer = PdfReader(pdfPath)
metadata = PdfDict(Id=lstVal[0],
Data_Registo=lstVal[1],
CentroPesca=lstVal[2],
Registador=lstVal[3],
Info=lstVal[4])
trailer.Info.update(metadata)
PdfWriter().write(pdfPath, trailer)
trailer = PdfReader(pdfPath)
pprint(trailer.Info)
def load(self, sourcename):
''' Load a Form XObject from a uri
'''
info = ViewInfo(sourcename)
fname = info.docname
pcache = self.cached_pdfs
doc = pcache.get(fname)
if doc is None:
doc = pcache[fname] = PdfReader(fname, decompress=self.decompress)
return docxobj(info, doc, allow_compressed=not self.decompress)
def run_count_pages_from_file(self, filefield):
count_pages = 0
try:
path = filefield.file.name
pdf = PdfReader(path)
count_pages += len(pdf.pages)
filefield.file.close()
except Exception as e:
pass
# print(e)
else:
return count_pages
def paginas(self):
if not self.FIELDFILE_NAME:
raise Exception
if not self.id:
raise Exception
if self._paginas > 0:
return self._paginas
elif self._paginas == -1:
return 0
count_pages = 0
try:
for field in self.FIELDFILE_NAME:
if not getattr(self, field):
return 0
path = getattr(self, field).file.name
if path.endswith('.pdf'):
pdf = PdfReader(path)
count_pages += len(pdf.pages)
getattr(self, field).file.close()
elif '.doc' in path:
return 0
except Exception as e:
count_pages = -1
finally:
self._paginas = count_pages
run_sql(
"""update {}
set _paginas = {}
where id = {};""".format(
'%s_%s' % (self._meta.app_label,
self._meta.model_name),
count_pages,
self.id
))
if count_pages == -1:
return 0
return count_pages
def docxobj(pageinfo, doc=None, allow_compressed=True):
''' docxobj creates and returns an actual Form XObject.
Can work standalone, or in conjunction with
the CacheXObj class (below).
'''
if not isinstance(pageinfo, ViewInfo):
pageinfo = ViewInfo(pageinfo)
# If we're explicitly passed a document,
# make sure we don't have one implicitly as well.
# If no implicit or explicit doc, then read one in
# from the filename.
if doc is not None:
assert pageinfo.doc is None
pageinfo.doc = doc
elif pageinfo.doc is not None:
doc = pageinfo.doc
else:
doc = pageinfo.doc = PdfReader(pageinfo.docname,
decompress=not allow_compressed)
assert isinstance(doc, PdfReader)
sourcepage = doc.pages[(pageinfo.page or 1) - 1]
return pagexobj(sourcepage, pageinfo, allow_compressed)
def run_bi_files(self):
models = [
{
'model': MateriaLegislativa,
'file_field': 'texto_original',
'hook': '', # 'run_bi_files_materias_legislativas'
},
{
'model': DocumentoAcessorio,
'file_field': 'arquivo',
'hook': ''
},
{
'model': NormaJuridica,
'file_field': 'texto_integral',
'hook': ''
},
{
'model': AnexoNormaJuridica,
'file_field': 'anexo_arquivo',
'hook': ''
},
{
'model': DocumentoAdministrativo,
'file_field': 'texto_integral',
'hook': ''
},
{
'model': DocumentoAcessorioAdministrativo,
'file_field': 'arquivo',
'hook': ''
},
{
'model': DiarioOficial,
'file_field': 'arquivo',
'hook': ''
},
{
'model': VersaoDeMidia,
'file_field': 'file',
'hook': 'run_bi_files_midias'
},
]
for mt in models: # mt = metadata
if mt['hook']:
getattr(self, mt['hook'])
continue
model = mt['model']
file = mt['file_field']
itens = model.objects.all()
count_pages = 0
count_reg = 0
for i in itens:
path = ''
count_reg += 1
try:
ff = getattr(i, file)
if ff:
path = ff.file.name
pdf = PdfReader(path)
count_pages += len(pdf.pages)
ff.file.close()
except Exception as e:
print(e)
if count_reg % 100 == 0:
print(count_reg, model._meta.verbose_name_plural,
count_pages)
print(model._meta.verbose_name_plural, count_pages)
def AddMetadata(self, lstPdfIn):
lstNameOut = []
if lstPdfIn != []:
try:
Mx_name = self.name_Generator()
for idx, pdf in enumerate(lstPdfIn):
_, file = os.path.split(pdf)
file_name = self.extract_file_name(file)
if self.PTEInfo.toPlainText() == '':
info = 'N/A'
else:
info = self.PTEInfo.toPlainText()
dictIn = {
'doc_num': str(idx + 1) + " Of " + str(len(lstPdfIn)),
'nome': file_name,
'data': datetime.today().date().isoformat(),
'horas': datetime.today().time().isoformat(),
'treePath': self.CBToStore.currentText(),
'doc_type': self.CBType.currentText(),
'info': info,
'systemEncoding': os.sys.getfilesystemencoding(),
'os': platform.platform()
}
trailer = PdfReader(pdf) #Open the pdf FIle
metadata = PdfDict(
doc_num=dictIn['doc_num'],
nome=dictIn['nome'],
data=dictIn['data'],
horas=dictIn['horas'],
treePath=dictIn['treePath'],
doc_type=dictIn['doc_type'],
info=dictIn['info'],
systemEncoding=dictIn['systemEncoding'],
os=dictIn['os'],
numero=idx) #Dict where we gointo insert our metadata
trailer.Info.clear(
) #we clear the default data that the lib adds
trailer.Info.update(metadata) #We add our own Metadata
abs_path = self.CBToStore.currentText()
if abs_path == None:
return False, None
else:
cat = self.CBType.currentText()
file_path = self.return_path(abs_path, cat)
#file_mx = file[:7] #separe the firts 6 char
namePath = os.path.join(file_path, Mx_name + ".pdf")
PdfWriter().write(namePath, trailer)
lstNameOut.append(namePath)
bOK = True
except:
bOK = False
#Check if it is encrypted
try:
PdfReader(pdf)
except ValueError:
QT_msg.aviso(
txt='O Ficherio <i>' + pdf +
'</i> esta <b>Corrompido</b> ou <b>Encriptado</b>, queria por favor removê-lo e voltar a tentar.'
)
else:
bOK = None
return bOK, lstNameOut
#! /usr/bin/env python # ./gp.py -c hidost -s samples/seeds/ff0bfa347b60be403f3f13b8461d9e230570078b -e /Users/apple/EvadeML-master/samples/hidost_benign_3 -p 48 -g 20 -m 0.1 -x 0 -f 0 -t attack_hidost_hidost_benign_3 --round 1 # ./utils/detection_agent_server.py ./utils/36vms_sigs.pickle from common import * import pickle import random from pdfrw.pdfreader import PdfReader from pdf_genome import PdfGenome ben_folder = '/Users/apple/EvadeML-master/samples/hidost_benign_3' ben_path = '/Users/apple/EvadeML2.0/samples/hidost_benign_3/e23abe0df1bf1c01df7567ca11192f2576aaaf5c.pdf' mal_path = '/Users/apple/EvadeML2.0/samples/seeds/ff0bfa347b60be403f3f13b8461d9e230570078b' file = ben_path print "file: %s" % file PdfReader(file, slow_parsing = True) root = PdfGenome.load_genome(file, pickleable = False) print "load: %s" % file files = list_file_paths(ben_folder) print "ben_folder: %s" % ben_folder print "ben_files: %s" % files ext_genome = PdfGenome.load_external_genome(ben_folder, pickleable = False) print "load_external_genome: %s" % ben_folder