[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

tests/test_cli.py

@@ -52,6 +52,30 @@ def test_cli_stream():
         assert format_error in result.output
 
 
+def test_cli_password():
+    with TemporaryDirectory() as tempdir:
+        infile = os.path.join(testdir, 'health_protected.pdf')
+        outfile = os.path.join(tempdir, 'health_protected.csv')
+        runner = CliRunner()
+        result = runner.invoke(cli, ['--password', 'userpass',
+                                     '--format', 'csv', '--output', outfile,
+                                     'stream', infile])
+        assert result.exit_code == 0
+        assert result.output == 'Found 1 tables\n'
+
+        output_error = 'file has not been decrypted'
+        # no password
+        result = runner.invoke(cli, ['--format', 'csv', '--output', outfile,
+                                     'stream', infile])
+        assert output_error in str(result.exception)
+
+        # bad password
+        result = runner.invoke(cli, ['--password', 'wrongpass',
+                                     '--format', 'csv', '--output', outfile,
+                                     'stream', infile])
+        assert output_error in str(result.exception)
+
+
 def test_cli_output_format():
     with TemporaryDirectory() as tempdir:
         infile = os.path.join(testdir, 'health.pdf')
@@ -78,7 +102,7 @@ def test_cli_output_format():
                                      'stream', infile])
         assert result.exit_code == 0
 
-def test_cli_quiet_flag():
+def test_cli_quiet():
     with TemporaryDirectory() as tempdir:
         infile = os.path.join(testdir, 'blank.pdf')
         outfile = os.path.join(tempdir, 'blank.csv')

tests/test_common.py

@@ -25,6 +25,17 @@ def test_parsing_report():
     assert tables[0].parsing_report == parsing_report
 
 
+def test_password():
+    df = pd.DataFrame(data_stream)
+
+    filename = os.path.join(testdir, "health_protected.pdf")
+    tables = camelot.read_pdf(filename, password="ownerpass", flavor="stream")
+    assert df.equals(tables[0].df)
+
+    tables = camelot.read_pdf(filename, password="userpass", flavor="stream")
+    assert df.equals(tables[0].df)
+
+
 def test_stream():
     df = pd.DataFrame(data_stream)
 

tests/test_errors.py

@@ -75,3 +75,17 @@ def test_ghostscript_not_found(monkeypatch):
     filename = os.path.join(testdir, 'foo.pdf')
     with pytest.raises(Exception, message=message):
         tables = camelot.read_pdf(filename)
+
+
+def test_no_password():
+    filename = os.path.join(testdir, 'health_protected.pdf')
+    message = 'file has not been decrypted'
+    with pytest.raises(Exception, message=message):
+        tables = camelot.read_pdf(filename)
+
+
+def test_bad_password():
+    filename = os.path.join(testdir, 'health_protected.pdf')
+    message = 'file has not been decrypted'
+    with pytest.raises(Exception, message=message):
+        tables = camelot.read_pdf(filename, password='wrongpass')