PyPDF2

getannotations

@@ -27,7 +27,7 @@ highlights, and highlights with text notes are supported.
 
 import os
 import sys
-import pyPdf
+import PyPDF2
 from prsannots.prst1 import Reader
 from prsannots.misc import u_raw_input, u_print, u_argv
 

prsannots/generic.py

@@ -7,7 +7,7 @@
 from xml.dom import minidom
 from StringIO import StringIO
 import hashlib
-import pyPdf
+import PyPDF2
 from pagetext import PageText, get_layouts, NoSubstringError, MultipleSubstringError
 from pdfannotation import highlight_annotation, text_annotation, add_annotation
 from pdfcontent import pdf_add_content, svg_to_pdf_content
@@ -92,7 +92,7 @@ def hash(self):
     @property
     def pdf(self):
         """A pyPdf.PdfFileReader instance of the PDF file."""
-        return pyPdf.PdfFileReader(open(os.path.join(self.reader.path, self.file), 'rb'))
+        return PyPDF2.PdfFileReader(open(os.path.join(self.reader.path, self.file), 'rb'),strict=False)
 
     def pdf_layout(self, page):
         """Get a pdfminer.LTPage object for page."""
@@ -125,7 +125,7 @@ def write_annotated_pdf(self, outfd, pdf=None, dice_map=None, **kw):
         if dice_map is None:
             dice_map = OneToOneMap(len(self.pdf.pages))
 
-        outpdf = pyPdf.PdfFileWriter()
+        outpdf = PyPDF2.PdfFileWriter()
         j = k = 0
         for i, page in enumerate(pdf.pages):
             while j < len(dice_map) and dice_map[j][0] == i:

prsannots/pagetext.py

@@ -56,7 +56,6 @@ def get_layouts(fd):
 
     parser = PDFParser(fd)
     doc = new_doc(parser)
-    doc.initialize()
 
     laparams = LAParams()
     rsrcmgr = PDFResourceManager()

prsannots/pdfannotation.py

@@ -4,7 +4,7 @@
 # the LGPL license.  See the file COPYING for full details.
 
 from datetime import datetime
-from pyPdf.generic import *
+from PyPDF2.generic import *
 
 YELLOW = [0.95, 0.9, 0.2]
 

prsannots/pdfcontent.py

@@ -3,8 +3,8 @@
 # This file is part of prsannots and is distributed under the terms of
 # the LGPL license.  See the file COPYING for full details.
 
-from pyPdf.pdf import ContentStream
-from pyPdf.generic import ArrayObject, NameObject
+from PyPDF2.pdf import ContentStream
+from PyPDF2.generic import ArrayObject, NameObject
 
 class StupidSVGInterpreterError(Exception):
     pass