def testScannedPdfPageExtraction(self):
pdfSeparate = PdfSeparate('tests/sample-scanned.pdf', self.outdir)
pdfSeparate.extractPages()
self.assertTrue(os.path.isfile(os.path.join(self.outdir,"1.pdf")))
self.assertTrue(os.path.isfile(os.path.join(self.outdir,"2.pdf")))
self.assertTrue(os.path.isfile(os.path.join(self.outdir,"3.pdf")))
self.assertTrue(os.path.isfile(os.path.join(self.outdir,"4.pdf")))
self.assertTrue(os.path.isfile(os.path.join(self.outdir,"5.pdf")))
def separatePdfPages(self):
self.logger.info('Calling PdfTkseparate: Separating pdf to pages at %s', os.path.join(self.outputDir,'pages'))
pdfTkSeparate = PdfTkSeparate(self.filePath, os.path.join(self.outputDir,'pages'))
pdfTkProcessStatus = pdfTkSeparate.extractPages()
self.logger.info('PdfTkseparate Status: %s', pdfTkProcessStatus)
if pdfTkProcessStatus != 0:
self.logger.info('Calling Pdfseparate: Separating pdf to pages at %s', os.path.join(self.outputDir,'pages'))
pdfSeparate = PdfSeparate(self.filePath, os.path.join(self.outputDir,'pages'))
pdfSeparate.extractPages()
def testScannedPdfPageForUnauthorisec(self):
pdfSeparate = PdfSeparate('tests/sample-scanned-1.pdf', self.indir)
pdfSeparate.extractPages()
self.assertTrue(os.path.isfile(os.path.join(self.indir, "1.pdf")))
try:
abbyyPdf = AbbyyPdfTextExtractor(self.indir, self.outdir, 1,
"english")
abbyyPdf.setApplicationCredentials('nouser', 'nopassword')
abbyyPdf.processPdfPage(1)
except HTTPError as e:
self.assertEqual(e.code, 401)
self.assertEqual(e.reason, "Unauthorized")
def testScannedPdfPage(self):
pdfSeparate = PdfSeparate('tests/sample-scanned-1.pdf', self.indir)
pdfSeparate.extractPages()
self.assertTrue(os.path.isfile(os.path.join(self.indir, "1.pdf")))
try:
abbyyPdf = AbbyyPdfTextExtractor(self.indir, self.outdir, 1,
"english")
abbyyPdf.setApplicationCredentials(
self.configParser.get('abbyy', 'appid'),
self.configParser.get('abbyy', 'password'))
abbyyPdf.processPdfPage(1)
self.assertTrue(os.path.isfile(os.path.join(self.outdir, "1.txt")))
except Exception:
pass
