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

Adapt to PDFMiner's breaking interface changes (#37).

Browse Source
This commit is contained in:
vi 2013-12-07 07:12:19 +08:00
parent 713776af67
commit 380bc289b3
6 changed files with 8 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
pdfparanoia/parser.py
View File

@ -16,6 +16,7 @@ except ImportError: # py3k
# from pdfquery import PDFQuery # from pdfquery import PDFQuery
import pdfminer.pdfparser import pdfminer.pdfparser
import pdfminer.pdfdocument
from .eraser import replace_object_with from .eraser import replace_object_with
@ -28,9 +29,7 @@ def parse_pdf(handler):
# setup for parsing # setup for parsing
parser = pdfminer.pdfparser.PDFParser(handler) parser = pdfminer.pdfparser.PDFParser(handler)
doc = pdfminer.pdfparser.PDFDocument() doc = pdfminer.pdfdocument.PDFDocument(parser)
parser.set_document(doc)
doc.set_parser(parser)
# actual parsing # actual parsing
doc.initialize() doc.initialize()
@ -58,8 +57,7 @@ def deflate(content):
pdf = parse_content(content) pdf = parse_content(content)
# get a list of all object ids # get a list of all object ids
xrefs = pdf._parser.read_xref() xref = pdf.xrefs[0]
xref = xrefs[0]
objids = xref.get_objids() objids = xref.get_objids()
# store new replacements # store new replacements

3
pdfparanoia/plugins/aip.py
View File

@ -25,8 +25,7 @@ class AmericanInstituteOfPhysics(Plugin):
pdf = parse_content(content) pdf = parse_content(content)
# get a list of all object ids # get a list of all object ids
xrefs = pdf._parser.read_xref() xref = pdf.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

3
pdfparanoia/plugins/ieee.py
View File

@ -22,8 +22,7 @@ class IEEEXplore(Plugin):
pdf = parse_content(content) pdf = parse_content(content)
# get a list of all object ids # get a list of all object ids
xrefs = pdf._parser.read_xref() xref = pdf.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

3
pdfparanoia/plugins/jstor.py
View File

@ -44,8 +44,7 @@ class JSTOR(Plugin):
pdf = parse_content(content) pdf = parse_content(content)
# get a list of all object ids # get a list of all object ids
xrefs = pdf._parser.read_xref() xref = pdf.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

3
pdfparanoia/plugins/rsc.py
View File

@ -42,8 +42,7 @@ class RoyalSocietyOfChemistry(Plugin):
pdf = parse_content(content) pdf = parse_content(content)
# get a list of all object ids # get a list of all object ids
xrefs = pdf._parser.read_xref() xref = pdf.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

3
pdfparanoia/plugins/sciencemagazine.py
View File

@ -27,8 +27,7 @@ class ScienceMagazine(Plugin):
pdf = parse_content(content) pdf = parse_content(content)
# get a list of all object ids # get a list of all object ids
xrefs = pdf._parser.read_xref() xref = pdf.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