def test_extraction(self):
'''Test the extractor's behaviour among different situations'''
lx = HTMLImageLinkExtractor(locations=('//img', ))
links_1 = lx.extract_links(self.response)
self.assertEqual(links_1, [
Link(url='http://example.com/sample1.jpg', text=u'sample 1'),
Link(url='http://example.com/sample2.jpg', text=u'sample 2'),
Link(url='http://example.com/sample4.jpg', text=u'sample 4')
])
lx = HTMLImageLinkExtractor(locations=('//img', ), unique=False)
links_2 = lx.extract_links(self.response)
self.assertEqual(links_2, [
Link(url='http://example.com/sample1.jpg', text=u'sample 1'),
Link(url='http://example.com/sample2.jpg', text=u'sample 2'),
Link(url='http://example.com/sample4.jpg', text=u'sample 4'),
Link(url='http://example.com/sample4.jpg',
text=u'sample 4 repetition')
])
lx = HTMLImageLinkExtractor(locations=('//div[@id="wrapper"]', ))
links_3 = lx.extract_links(self.response)
self.assertEqual(links_3, [
Link(url='http://example.com/sample1.jpg', text=u'sample 1'),
Link(url='http://example.com/sample2.jpg', text=u'sample 2'),
Link(url='http://example.com/sample4.jpg', text=u'sample 4')
])
lx = HTMLImageLinkExtractor(locations=('//a', ))
links_4 = lx.extract_links(self.response)
self.assertEqual(links_4, [
Link(url='http://example.com/sample2.jpg', text=u'sample 2'),
Link(url='http://example.com/sample3.html', text=u'sample 3')
])
def test_urls_type(self):
'''Test that the resulting urls are regular strings and not a unicode objects'''
lx = HTMLImageLinkExtractor()
links = lx.extract_links(self.response)
self.assertTrue(all(isinstance(link.url, str) for link in links))
