def test_href_url_same_suffix():
f = e.css('#links a') | e.href_url_same_suffix
res = f(create_response(example))
# we want the result to be an iterable, but not a list
assert hasattr(res, '__iter__')
assert not isinstance(res, list)
assert list(res) == ['http://base.com/1', 'http://subdomain.base.com/2']
def test_href_url_same_suffix():
f = e.css('#links a') | e.href_url_same_suffix
res = f(create_response(example))
# we want the result to be an iterable, but not a list
assert hasattr(res, '__iter__')
assert not isinstance(res, list)
assert list(res) == ['http://base.com/1', 'http://subdomain.base.com/2']
def test_text_content_with_br():
f = e.css('#br') | e.text_content
assert f(create_response(example)) == ['oh\nmy']
def test_text():
f = e.css('h1') | e.text | list
assert f(create_response(example)) == ['hi']
def test_href_url_single():
f = e.css('#div1 a') | item0 | e.href_url
assert f(create_response(example)) == 'http://base.com/1'
def test_img_src():
f = e.css('img') | e.src_url
res = f(create_response(example))
assert hasattr(res, '__iter__')
assert not isinstance(res, list)
assert list(res) == ['http://other.com/src']
def test_attrib():
f = e.css('#div1 a') | e.attrib('href') | list
r = create_response(example)
assert f(r) == ['/1', ' /2 ', None]
def test_css():
f = e.css('h1')
response = create_response(example)
res = f(response)
assert isinstance(res, list)
assert [elem.tag for elem in res] == ['h1']
def test_normalize_space_nbsp():
f = e.css('#nbsp') | e.normalize_space
assert f(create_response(example)) == ['']
def test_href_url_single():
f = e.css('#div1 a') | item0 | e.href_url
assert f(create_response(example)) == 'http://base.com/1'
def test_img_src():
f = e.css('img') | e.src_url
res = f(create_response(example))
assert hasattr(res, '__iter__')
assert not isinstance(res, list)
assert list(res) == ['http://other.com/src']
def test_attrib_default():
f = e.css('#div1 a') | e.attrib('nosuch', '') | list
assert f(create_response(example)) == ['', '', '']
def test_attrib():
f = e.css('#div1 a') | e.attrib('href') | list
r = create_response(example)
assert f(r) == ['/1', ' /2 ', None]
def test_css_called_twice():
f = e.css('h1')
response = create_response(example)
with Cache():
assert f(response)== f(response)
def test_list_normalize_space():
func = e.css('ul li') | e.normalize_space
assert func(create_response(example)) == ['1', '', '2']
def test_itertext():
f = e.css('.thing') | e.itertext() | flatten | list
expected = ['First ', 'one thing', 'then ', 'another thing', '.']
assert f(create_response(example)) == expected
def test_href_empty():
f = e.css('#nosuch') | e.href_url | list
assert f(create_response(example)) == []
def test_css():
f = e.css('h1')
response = create_response(example)
res = f(response)
assert isinstance(res, list)
assert [elem.tag for elem in res] == ['h1']
def test_text():
f = e.css('h1') | e.text | list
assert f(create_response(example)) == ['hi']
def test_css_called_twice():
f = e.css('h1')
response = create_response(example)
with Cache():
assert f(response) == f(response)
def test_nbsp():
func = e.css('#nbsp') | e.itertext() | list
assert func(create_response(example)) == [u'\xa0\xa0']
def test_attrib_default():
f = e.css('#div1 a') | e.attrib('nosuch', '') | list
assert f(create_response(example)) == ['', '', '']
def test_text_content_with_br():
f = e.css('#br') | e.text_content
assert f(create_response(example)) == ['oh\nmy']
def test_list_text_content():
func = e.css('ul li') | e.text_content
assert func(create_response(example)) == [' 1', '', '2 ']
def test_list_normalize_space():
func = e.css('ul li') | e.normalize_space
assert func(create_response(example)) == ['1', '', '2']
def test_href_empty():
f = e.css('#nosuch') | e.href_url | list
assert f(create_response(example)) == []
def test_href_when_url_contains_dodgy_characters():
f = e.css('a') | e.href_url | list
r = create_response(example_with_dodgy_url)
# This will fail if we don't quote/unquote the base_url
assert f(r) == ['http://foo.com/1']
def test_nbsp():
func = e.css('#nbsp') | e.itertext() | list
assert func(create_response(example)) == [u'\xa0\xa0']
def test_itertext():
f = e.css('.thing') | e.itertext() | flatten | list
expected = ['First ', 'one thing', 'then ', 'another thing', '.']
assert f(create_response(example)) == expected
def test_list_text_content():
func = e.css('ul li') | e.text_content
assert func(create_response(example)) == [' 1', '', '2 ']
def test_itertext_elem():
f = e.css('.thing') | first | e.itertext() | list
expected = ['First ', 'one thing']
assert f(create_response(example)) == expected
def test_href_when_url_contains_non_ascii_characters():
f = e.css('a') | e.href_url | list
r = create_response(example_with_non_ascii_url)
assert f(r) == ['http://foo.com/bar™/1']
def test_normalize_space_nbsp():
f = e.css('#nbsp') | e.normalize_space
assert f(create_response(example)) == ['']
def test_itertext_elem():
f = e.css('.thing') | first | e.itertext() | list
expected = ['First ', 'one thing']
assert f(create_response(example)) == expected
def test_drop_tree():
f = (e.xpath('//*[@id="drop-tree"]') |
e.drop_tree(e.css('script')) |
e.xpath('string()'))
assert f(create_response(example)) == ['Drop this please.']
def test_drop_tree():
f = (e.xpath('//*[@id="drop-tree"]') | e.drop_tree(e.css('script'))
| e.xpath('string()'))
assert f(create_response(example)) == ['Drop this please.']
def test_href_when_url_contains_non_ascii_characters():
f = e.css('a') | e.href_url | list
r = create_response(example_with_non_ascii_url)
assert f(r) == ['http://foo.com/bar™/1']