def extractTextFromStructuredDoc(self):
"""
creates "text" dir to dump the extracted pages
"""
self.logger.info('Calling Pdftotext: Dumping text pages at %s', os.path.join(self.outputDir,'text'))
pdfToText = PdfToText(self.filePath, self.totalPages, os.path.join(self.outputDir,'text'))
pdfToText.extractPages()
def testStructuredPdfAllPagewise(self):
pdfToText = PdfToText('tests/sample.pdf', 5, self.outdir)
pdfToText.extractPages()
self.assertTrue(os.path.isfile(os.path.join(self.outdir, "1.txt")))
self.assertTrue(os.path.isfile(os.path.join(self.outdir, "2.txt")))
self.assertTrue(os.path.isfile(os.path.join(self.outdir, "3.txt")))
self.assertTrue(os.path.isfile(os.path.join(self.outdir, "4.txt")))
self.assertTrue(os.path.isfile(os.path.join(self.outdir, "5.txt")))
def testStructuredPdfAllPagewise(self):
pdfToText = PdfToText('tests/sample.pdf', 5, self.outdir)
pdfToText.extractPages()
self.assertTrue(os.path.isfile(os.path.join(self.outdir,"1.txt")))
self.assertTrue(os.path.isfile(os.path.join(self.outdir,"2.txt")))
self.assertTrue(os.path.isfile(os.path.join(self.outdir,"3.txt")))
self.assertTrue(os.path.isfile(os.path.join(self.outdir,"4.txt")))
self.assertTrue(os.path.isfile(os.path.join(self.outdir,"5.txt")))
def processToCheckStructured(self):
"""
dumps the entire pdf to text to get the size of the content
"""
pdfToText = PdfToText(self.filePath, self.totalPages, self.outputDir)
pdfToText.dumpPages()
self.textContentSize += os.path.getsize(pdfToText.dumpedTextFilepath)
self.logger.info('Text content size: %d bytes', self.textContentSize)
self.logger.info('Structured? %s', self.isStructured())
def testStructuredPdfAllPagesDump(self):
pdfToText = PdfToText('tests/sample.pdf', 5, self.outdir)
pdfToText.dumpPages()
self.assertTrue(os.path.isfile(os.path.join(self.outdir,"sample.txt")))
def testScannedPdfPage(self):
pdfToText = PdfToText('tests/sample-scanned.pdf', 5, self.outdir)
pdfToText.extractPage(2)
self.assertTrue(os.path.isfile(os.path.join(self.outdir,"2.txt")))
def testStructuredPdfPage(self):
pdfToText = PdfToText('tests/sample.pdf', 5, self.outdir)
pdfToText.extractPage(1)
self.assertTrue(os.path.isfile(os.path.join(self.outdir,"1.txt")))
def testStructuredPdfAllPagesDump(self):
pdfToText = PdfToText('tests/sample.pdf', 5, self.outdir)
pdfToText.dumpPages()
self.assertTrue(os.path.isfile(os.path.join(self.outdir,
"sample.txt")))
def testScannedPdfPage(self):
pdfToText = PdfToText('tests/sample-scanned.pdf', 5, self.outdir)
pdfToText.extractPage(2)
self.assertTrue(os.path.isfile(os.path.join(self.outdir, "2.txt")))
def testStructuredPdfPage(self):
pdfToText = PdfToText('tests/sample.pdf', 5, self.outdir)
pdfToText.extractPage(1)
self.assertTrue(os.path.isfile(os.path.join(self.outdir, "1.txt")))
