def test_process_file():
doc = Doc(filetype='pdf')
doc.link = Link(url='foo')
doc.link.context = 'Lorem ipsum dolor sit amet'
doc.link.anchortext = 'Lorem ipsum dolor sit amet'
doc.source = Source(url='foo', html='<b>Lorem ipsum dolor sit amet</b>')
doc.tempfile = os.path.join(testdir, 'simple.pdf')
scraper.process_file(doc)
assert doc.title == 'Lorem ipsum dolor sit amet'
