def test_pdf_extraction(self):
if not PdfFileReader:
self.skipTest("pyPdf is not installed")
pdf = open(os.path.join(my_path, 'testpdf.pdf'))
extractor = BaseExtractor(pdf.read())
self.assertEqual(extractor.get_title(), u'This is a test PDF file')
expected_content = [
'universal file format', 'fonts, formatting, colours and graphics',
'regardless of the application and platform'
]
content = extractor.get_content()
for c in expected_content:
self.assertTrue(c in content)
def test_extractor(self):
extractor = BaseExtractor(self.html)
self.assertEqual(extractor.get_title(), u'MY TITLE')
expected_content = [
u'MY TITLE',
u'Relative Link',
u'Absolute Link',
u'Offsite Link',
u'THIS IS A H1 HEADER',
u'Content in a paragraph',
u'THIS IS A H2 HEADER',
u'Content In A Span',
]
content = extractor.get_content()
for c in expected_content:
self.assertTrue(c.lower() in content.lower())
expected_headings = [
u'THIS IS A H1 HEADER',
u'THIS IS A H2 HEADER',
]
headings = extractor.get_headings()
for h in expected_headings:
self.assertTrue(h.lower() in headings.lower())
unexpected_content = [
'meta', 'Content-Type', 'stylesheet', 'script', 'style',
'relative_link', 'absolute_link', 'offsite_link', 'pagelocation',
'THIS IS A SCRIPT TAG', 'THIS_IS_A_STYLE_TAG'
]
for u in unexpected_content:
self.assertFalse(u in content)
self.assertFalse(u in headings)
