def parse(self):
fp = file(self.pdf, 'rb')
parser = PDFParser(fp, dbg=self.debug)
doc = PDFDocument(parser, dbg=self.debug)
# extract blob of data after EOF (if it exists)
if doc.found_eof and doc.eof_distance > 3:
self.bin_blob = parser.read_from_end(doc.eof_distance)
res = '<pdf>'
visited = set() # keep track of the objects already visited
for xref in doc.xrefs:
for objid in xref.get_objids():
if objid in visited:
continue
visited.add(objid)
try:
obj = doc.getobj(objid)
res += '<object id="' + str(objid) + '">\n'
res += self.dump(obj)
res += '\n</object>\n\n'
except PDFObjectNotFound as e:
mal_obj = parser.read_n_from(xref.get_pos(objid)[1], 4096)
mal_obj = mal_obj.replace('<', '0x3C')
res += '<object id="%d" type="malformed">\n%s\n</object>\n\n' % (
objid, mal_obj)
self.takenote(self.malformed, 'objects', objid)
except Exception as e:
res += '<object id="%d" type="exception">\n%s\n</object>\n\n' % (
objid, e.message)
fp.close()
res += self.dumptrailers(doc)
res += '</pdf>'
self.xml = res
self.errors = doc.errors
self.bytes_read = parser.BYTES
return
def parse (self):
fp = file(self.pdf, 'rb')
parser = PDFParser(fp, dbg=self.debug)
doc = PDFDocument(parser, dbg=self.debug)
#extract blob of data after EOF (if it exists)
if doc.found_eof and doc.eof_distance > 3:
self.bin_blob = parser.read_from_end(doc.eof_distance)
res = '<pdf>'
visited = set() #keep track of the objects already visited
for xref in doc.xrefs:
for objid in xref.get_objids():
if objid in visited:
continue
if objid == 21 or objid == 67:
print objid
visited.add(objid)
try:
obj = doc.getobj(objid)
res += '<object id="' + str(objid) + '">\n'
res += self.dump(obj)
res += '\n</object>\n\n'
except PDFObjectNotFound as e:
mal_obj = parser.read_n_from(xref.get_pos(objid)[1], 4096)
mal_obj = mal_obj.replace('<', '0x3C')
res += '<object id="%d" type="malformed">\n%s\n</object>\n\n' % (objid, mal_obj)
self.takenote(self.malformed, 'objects', objid)
except Exception as e:
res += '<object id="%d" type="exception">\n%s\n</object>\n\n' % (objid, e.message)
fp.close()
res += self.dumptrailers(doc)
res += '</pdf>'
self.xml=res
self.errors = doc.errors
self.bytes_read = parser.BYTES
return
