def test_uri_stripped_of_whitespace_and_quote_characters_correctly(self):
urls = [u' image.jpg ', u" '/data.jpg'", u'\n\t"file.jpg"\n\t\t']
results = ['http://www.example.com/images/image.jpg',
'http://www.example.com/data.jpg',
'http://www.example.com/images/file.jpg']
htmlpage = HtmlPage(url=u"http://www.example.com/images/",
body=u'<html><body></body></html>',
encoding='utf-8')
url_p = UrlFieldTypeProcessor()
img_p = ImagesFieldTypeProcessor()
for text, url in zip(urls, results):
self.assertEqual(img_p.adapt(img_p.extract(text), htmlpage), url)
self.assertEqual(url_p.adapt(url_p.extract(text), htmlpage), url)
def test_uri_with_illegal_html_entities(self):
urls = [u'	
 image.jpg ', u" '/�data.jpg'",
u'\n\t"file.jpg"\n\t\t']
results = ['http://www.example.com/images/image.jpg',
'http://www.example.com/data.jpg',
'http://www.example.com/images/file.jpg']
htmlpage = HtmlPage(url=u"http://www.example.com/images/",
body=u'<html><body></body></html>',
encoding='utf-8')
url_p = UrlFieldTypeProcessor()
img_p = ImagesFieldTypeProcessor()
for text, url in zip(urls, results):
self.assertEqual(img_p.adapt(img_p.extract(text), htmlpage), url)
self.assertEqual(url_p.adapt(url_p.extract(text), htmlpage), url)
def test_blank_image_url(self):
assert ImagesFieldTypeProcessor().extract(' ') == ''
