security-and-privacy/pdfparanoia
security-and-privacy/pdfparanoia
1
0
Fork 0
mirror of https://github.com/kanzure/pdfparanoia.git synced 2024-12-04 23:15:52 +01:00
Code Releases Activity

Check PDF is from the RSC before cleaning

Browse Source
This commit is contained in:
Donncha O'Cearbhaill 2013-05-13 21:01:52 +01:00
parent 18140d838d
commit c673d77ec6
1 changed files with 28 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
pdfparanoia/plugins/rsc.py
View File

@ -35,35 +35,38 @@ class RoyalSocietyOfChemistry(Plugin):
#"Table of Contents for this issue", #"Table of Contents for this issue",
] ]
# parse the pdf into a pdfminer document # Confirm the PDF is from the RSC
pdf = parse_content(content) if "pubs.rsc.org" in content:
# parse the pdf into a pdfminer document
pdf = parse_content(content)
# get a list of all object ids # get a list of all object ids
xrefs = pdf._parser.read_xref() xrefs = pdf._parser.read_xref()
xref = xrefs[0] xref = xrefs[0]
objids = xref.get_objids() objids = xref.get_objids()
# check each object in the pdf # check each object in the pdf
for objid in objids: for objid in objids:
# get an object by id # get an object by id
obj = pdf.getobj(objid) obj = pdf.getobj(objid)
if hasattr(obj, "attrs"): if hasattr(obj, "attrs"):
# watermarks tend to be in FlateDecode elements # watermarks tend to be in FlateDecode elements
if obj.attrs.has_key("Filter") and str(obj.attrs["Filter"]) == "/FlateDecode": if obj.attrs.has_key("Filter") and str(obj.attrs["Filter"]) == "/FlateDecode":
rawdata = copy(obj.rawdata) rawdata = copy(obj.rawdata)
data = copy(obj.get_data()) data = copy(obj.get_data())
# Check if any of the watermarks are in the current object # Check if any of the watermarks are in the current object
for phrase in watermarks: for phrase in watermarks:
if phrase in data: if phrase in data:
if verbose >= 2: if verbose >= 2:
sys.stderr.write("%s: Found object %s with %r: %r; omitting...\n" % (cls.__name__, objid, phrase, data[data.index(phrase):data.index(phrase)+1000])) sys.stderr.write("%s: Found object %s with %r: %r; omitting...\n" % (cls.__name__, objid, phrase, data[data.index(phrase):data.index(phrase)+1000]))
elif verbose >= 1: elif verbose >= 1:
sys.stderr.write("%s: Found object %s with %r; omitting...\n" % (cls.__name__, objid, phrase)) sys.stderr.write("%s: Found object %s with %r; omitting...\n" % (cls.__name__, objid, phrase))
# We had a match so replace the watermark data with an empty string # We had a match so replace the watermark data with an empty string
replacements.append([rawdata, ""]) replacements.append([rawdata, ""])
for deets in replacements: for deets in replacements:
# Directly replace the stream data in binary encoded object # Directly replace the stream data in binary encoded object