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 testScanned44PdfPageForNetwork(self):
pdfSeparate = PdfSeparate('tests/sample-scanned-44pages.pdf', self.indir)
pdfSeparate.extractPages()
self.assertTrue(os.path.isfile(os.path.join(self.indir,"1.pdf")))
try:
abbyyPdf = AbbyyPdfTextExtractor(self.indir, self.outdir, 44, "english")
abbyyPdf.setApplicationCredentials(self.configParser.get('abbyy','appid'), self.configParser.get('abbyy','password'))
abbyyPdf.extractPages();
self.assertTrue(os.path.isfile(os.path.join(self.outdir,"1.txt")))
self.assertTrue(os.path.isfile(os.path.join(self.outdir,"44.txt")))
except Exception:
pass
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
def extractTextFromScannedDoc(self):
"""
makes api calls
"""
self.logger.info('Calling Abbyy: OCR-ing %d pages at %s', self.totalPages, os.path.join(self.outputDir,'text'))
abbyyPdf = AbbyyPdfTextExtractor(os.path.join(self.outputDir,'pages'), os.path.join(self.outputDir,'text'), self.totalPages, self.language)
abbyyPdf.setApplicationCredentials(self.configParser.get('abbyy','appid'), self.configParser.get('abbyy','password'))
abbyyPdf.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