[MRG + 1] Add basic support for encrypted PDF files (#180)

* [MRG] Add basic support for encrypted PDF files

Update API and CLI to accept ASCII passwords to decrypt PDFs
encrypted by algorithm code 1 or 2 (limited by support from PyPDF2).
Update documentation and unit tests accordingly.

Example document health_protected.pdf generated as follows:
qpdf --encrypt userpass ownerpass 128 -- health.pdf health_protected.pdf

Issue #162

* Support encrypted PDF files in python3

Issue #162

* Address review comments

Explicitly check passwords for None rather than falsey.
Correct read_pdf documentation for Owner/User password.

Issue #162

* Correct API documentation changes for consistency

Issue #162

* Move error tests from test_common to test_errors

Issue #162

* Add qpdf example

* Remove password is not None check

* Fix merge conflict

* Fix pages example

camelot/cli.py

@@ -27,6 +27,7 @@ pass_config = click.make_pass_decorator(Config)
 @click.version_option(version=__version__)
 @click.option('-p', '--pages', default='1', help='Comma-separated page numbers.'
               ' Example: 1,3,4 or 1,4-end.')
+@click.option('-pw', '--password', help='Password for decryption.')
 @click.option('-o', '--output', help='Output file path.')
 @click.option('-f', '--format',
               type=click.Choice(['csv', 'json', 'excel', 'html']),

camelot/handlers.py

@@ -1,6 +1,7 @@
 # -*- coding: utf-8 -*-
 
 import os
+import sys
 
 from PyPDF2 import PdfFileReader, PdfFileWriter
 
@@ -21,14 +22,22 @@ class PDFHandler(object):
         Path to PDF file.
     pages : str, optional (default: '1')
         Comma-separated page numbers.
-        Example: 1,3,4 or 1,4-end.
+        Example: '1,3,4' or '1,4-end'.
+    password : str, optional (default: None)
+        Password for decryption.
 
     """
-    def __init__(self, filename, pages='1'):
+    def __init__(self, filename, pages='1', password=None):
         self.filename = filename
         if not filename.lower().endswith('.pdf'):
             raise NotImplementedError("File format not supported")
         self.pages = self._get_pages(self.filename, pages)
+        if password is None:
+            self.password = ''
+        else:
+            self.password = password
+            if sys.version_info[0] < 3:
+                self.password = self.password.encode('ascii')
 
     def _get_pages(self, filename, pages):
         """Converts pages string to list of ints.
@@ -52,6 +61,8 @@ class PDFHandler(object):
             page_numbers.append({'start': 1, 'end': 1})
         else:
             infile = PdfFileReader(open(filename, 'rb'), strict=False)
+            if infile.isEncrypted:
+                infile.decrypt(self.password)
             if pages == 'all':
                 page_numbers.append({'start': 1, 'end': infile.getNumPages()})
             else:
@@ -84,7 +95,7 @@ class PDFHandler(object):
         with open(filename, 'rb') as fileobj:
             infile = PdfFileReader(fileobj, strict=False)
             if infile.isEncrypted:
-                infile.decrypt('')
+                infile.decrypt(self.password)
             fpath = os.path.join(temp, 'page-{0}.pdf'.format(page))
             froot, fext = os.path.splitext(fpath)
             p = infile.getPage(page - 1)
@@ -103,7 +114,7 @@ class PDFHandler(object):
                 os.rename(fpath, fpath_new)
                 infile = PdfFileReader(open(fpath_new, 'rb'), strict=False)
                 if infile.isEncrypted:
-                    infile.decrypt('')
+                    infile.decrypt(self.password)
                 outfile = PdfFileWriter()
                 p = infile.getPage(0)
                 if rotation == 'anticlockwise':

camelot/io.py

@@ -5,8 +5,8 @@ from .handlers import PDFHandler
 from .utils import validate_input, remove_extra
 
 
-def read_pdf(filepath, pages='1', flavor='lattice', suppress_warnings=False,
-             **kwargs):
+def read_pdf(filepath, pages='1', password=None, flavor='lattice',
+             suppress_warnings=False, **kwargs):
     """Read PDF and return extracted tables.
 
     Note: kwargs annotated with ^ can only be used with flavor='stream'
@@ -19,6 +19,8 @@ def read_pdf(filepath, pages='1', flavor='lattice', suppress_warnings=False,
     pages : str, optional (default: '1')
         Comma-separated page numbers.
         Example: '1,3,4' or '1,4-end'.
+    password : str, optional (default: None)
+        Password for decryption.
     flavor : str (default: 'lattice')
         The parsing method to use ('lattice' or 'stream').
         Lattice is used by default.
@@ -94,7 +96,7 @@ def read_pdf(filepath, pages='1', flavor='lattice', suppress_warnings=False,
             warnings.simplefilter("ignore")
 
         validate_input(kwargs, flavor=flavor)
-        p = PDFHandler(filepath, pages)
+        p = PDFHandler(filepath, pages=pages, password=password)
         kwargs = remove_extra(kwargs, flavor=flavor)
         tables = p.parse(flavor=flavor, **kwargs)
         return tables