def extractembedded(outfp, fname, objids, pagenos, password='',
dumpall=False, codec=None, extractdir=None):
def extract1(obj):
filename = os.path.basename(obj['UF'] or obj['F'])
fileref = obj['EF']['F']
fileobj = doc.getobj(fileref.objid)
if not isinstance(fileobj, PDFStream):
raise PDFValueError(
'unable to process PDF: reference for %r is not a PDFStream' %
(filename))
if fileobj.get('Type') is not LITERAL_EMBEDDEDFILE:
raise PDFValueError(
'unable to process PDF: reference for %r is not an EmbeddedFile' %
(filename))
path = os.path.join(extractdir, filename)
if os.path.exists(path):
raise IOError('file exists: %r' % path)
print('extracting: %r' % path, file=sys.stderr)
out = file(path, 'wb')
out.write(fileobj.get_data())
out.close()
return
fp = open(fname, 'rb')
parser = PDFParser(fp)
doc = PDFDocument(parser, password)
for xref in doc.xrefs:
for objid in xref.get_objids():
obj = doc.getobj(objid)
if isinstance(obj, dict) and obj.get('Type') is LITERAL_FILESPEC:
extract1(obj)
fp.close()
return
def dumppdf(outfp, fname, objids, pagenos, password='',
dumpall=False, codec=None, extractdir=None):
fp = open(fname, 'rb')
parser = PDFParser(fp)
doc = PDFDocument(parser, password)
if objids:
for objid in objids:
obj = doc.getobj(objid)
dumpxml(outfp, obj, codec=codec)
if pagenos:
for (pageno,page) in enumerate(PDFPage.create_pages(doc)):
if pageno in pagenos:
if codec:
for obj in page.contents:
obj = stream_value(obj)
dumpxml(outfp, obj, codec=codec)
else:
dumpxml(outfp, page.attrs)
if dumpall:
dumpallobjs(outfp, doc, codec=codec)
if (not objids) and (not pagenos) and (not dumpall):
dumptrailers(outfp, doc)
fp.close()
if codec not in ('raw','binary'):
outfp.write('\n')
return
def extractembedded(fname, password='', extractdir=None, emailsDir=None):
def extract1(obj):
filename = os.path.basename(obj['F'])
# filename = os.path.basename(obj['UF'] or obj['F'])
fileref = obj['EF']['F']
fileobj = doc.getobj(fileref.objid)
if not isinstance(fileobj, PDFStream):
raise PDFValueError(
'unable to process PDF: reference for %r is not a PDFStream' %
(filename))
if fileobj.get('Type') is not LITERAL_EMBEDDEDFILE:
raise PDFValueError(
'unable to process PDF: reference for %r is not an EmbeddedFile'
% (filename))
file_name, extension = os.path.splitext(fname)
path = os.path.join(extractdir, file_name + " " + filename)
while os.path.exists(path):
path = os.path.join(
extractdir,
file_name + " " + str(randint(1, 100)) + " " + filename)
print >> sys.stderr, "file exists, create random name %s" % path
# print >>sys.stderr, 'extracting: %r' % path
out = file(path, 'wb')
out.write(fileobj.get_data())
out.close()
return
fp = file(os.path.join(emailsDir, fname), 'rb')
parser = PDFParser(fp)
doc = PDFDocument(parser, password)
for xref in doc.xrefs:
if type(xref
) == PDFXRef: # Ignore PDFXreffallback. Not sure what it is.
for objid in xref.get_objids():
obj = doc.getobj(objid)
if isinstance(obj,
dict) and obj.get('Type') is LITERAL_FILESPEC:
extract1(obj)
return
cmd_args = virtual_environment(parser)
from pdfminer3.pdfdocument import PDFDocument
from pdfminer3.pdftypes import PDFObjectNotFound
from pdfminer3.pdfparser import PDFParser, PDFStream
print(cmd_args.file_name)
input_file = open(cmd_args.file_name, "rb")
parsed = PDFDocument(PDFParser(input_file))
try:
shutil.rmtree('%s.pdfminer_out' % cmd_args.file_name)
except FileNotFoundError:
pass
os.mkdir('%s.pdfminer_out' % cmd_args.file_name)
for obj_id in set(obj_id for xref in parsed.xrefs
for obj_id in xref.get_objids()):
try:
obj = parsed.getobj(obj_id)
except PDFObjectNotFound:
continue
if not isinstance(obj, PDFStream):
continue
print('%s' % obj)
obj.decode()
length = obj.attrs.get('Length', '')
output_file = open(
'%s.pdfminer_out/pdf_%07d_0.dat' % (cmd_args.file_name, obj_id),
'wb')
output_file.write(obj.data)
output_file.close()
toc = time()
print('\nExecution time: %s sec.' % (toc - tic))