def test_pdf(self):
        shutil.copy('./tests/data/dirty.pdf', './tests/data/clean.pdf')
        p = pdf.PDFParser('./tests/data/clean.pdf')

        meta = p.get_meta()
        self.assertEqual(meta['producer'], 'pdfTeX-1.40.14')

        p.lightweight_cleaning = True
        ret = p.remove_all()
        self.assertTrue(ret)

        p = pdf.PDFParser('./tests/data/clean.cleaned.pdf')
        expected_meta = {'creation-date': -1, 'format': 'PDF-1.5', 'mod-date': -1}
        self.assertEqual(p.get_meta(), expected_meta)

        os.remove('./tests/data/clean.pdf')
        os.remove('./tests/data/clean.cleaned.pdf')
Beispiel #2
0
 def test_pdf(self):
     p = pdf.PDFParser('./tests/data/dirty.pdf')
     meta = p.get_meta()
     self.assertEqual(meta['producer'], 'pdfTeX-1.40.14')
     self.assertEqual(
         meta['creator'],
         "'Certified by IEEE PDFeXpress at 03/19/2016 2:56:07 AM'")
     self.assertEqual(meta['DocumentID'],
                      "uuid:4a1a79c8-404e-4d38-9580-5bc081036e61")
     self.assertEqual(
         meta['PTEX.Fullbanner'], "This is pdfTeX, Version "
         "3.1415926-2.5-1.40.14 (TeX Live 2013/Debian) kpathsea "
         "version 6.1.1")
Beispiel #3
0
 def test_pdf(self):
     shutil.copy('./tests/data/dirty.png', './tests/data/clean.png')
     with self.assertRaises(ValueError):
         pdf.PDFParser('./tests/data/clean.png')
     os.remove('./tests/data/clean.png')