def test_caching(self):
# Test case for bug #1313119
uri = "http://example.com/doc/"
unicode_uri = unicode(uri)
urlparse.urlparse(unicode_uri)
p = urlparse.urlparse(uri)
self.assertEqual(type(p.scheme), type(uri))
self.assertEqual(type(p.hostname), type(uri))
self.assertEqual(type(p.path), type(uri))
def test_caching(self):
# Test case for bug #1313119
uri = "http://example.com/doc/"
unicode_uri = str(uri)
urlparse.urlparse(unicode_uri)
p = urlparse.urlparse(uri)
self.assertEqual(type(p.scheme), type(uri))
self.assertEqual(type(p.hostname), type(uri))
self.assertEqual(type(p.path), type(uri))
def test_portseparator(self):
# Issue 754016 makes changes for port separator ':' from scheme separator
self.assertEqual(urlparse.urlparse("path:80"),
('', '', 'path:80', '', '', ''))
self.assertEqual(urlparse.urlparse("http:"),
('http', '', '', '', '', ''))
self.assertEqual(urlparse.urlparse("https:"),
('https', '', '', '', '', ''))
self.assertEqual(urlparse.urlparse("http://www.python.org:80"),
('http', 'www.python.org:80', '', '', '', ''))
def test_anyscheme(self):
# Issue 7904: s3://foo.com/stuff has netloc "foo.com".
self.assertEqual(urlparse.urlparse("s3://foo.com/stuff"),
('s3','foo.com','/stuff','','',''))
self.assertEqual(urlparse.urlparse("x-newscheme://foo.com/stuff"),
('x-newscheme','foo.com','/stuff','','',''))
self.assertEqual(urlparse.urlparse("x-newscheme://foo.com/stuff?query#fragment"),
('x-newscheme','foo.com','/stuff','','query','fragment'))
self.assertEqual(urlparse.urlparse("x-newscheme://foo.com/stuff?query"),
('x-newscheme','foo.com','/stuff','','query',''))
def test_withoutscheme(self):
# Test urlparse without scheme
# Issue 754016: urlparse goes wrong with IP:port without scheme
# RFC 1808 specifies that netloc should start with //, urlparse expects
# the same, otherwise it classifies the portion of url as path.
self.assertEqual(urlparse.urlparse("path"),
('','','path','','',''))
self.assertEqual(urlparse.urlparse("//www.python.org:80"),
('','www.python.org:80','','','',''))
self.assertEqual(urlparse.urlparse("http://www.python.org:80"),
('http','www.python.org:80','','','',''))
def test_withoutscheme(self):
# Test urlparse without scheme
# Issue 754016: urlparse goes wrong with IP:port without scheme
# RFC 1808 specifies that netloc should start with //, urlparse expects
# the same, otherwise it classifies the portion of url as path.
self.assertEqual(urlparse.urlparse("path"),
('', '', 'path', '', '', ''))
self.assertEqual(urlparse.urlparse("//www.python.org:80"),
('', 'www.python.org:80', '', '', '', ''))
self.assertEqual(urlparse.urlparse("http://www.python.org:80"),
('http', 'www.python.org:80', '', '', '', ''))
def test_portseparator(self):
# Issue 754016 makes changes for port separator ':' from scheme separator
self.assertEqual(urlparse.urlparse("path:80"),
('','','path:80','','',''))
self.assertEqual(urlparse.urlparse("http:"),('http','','','','',''))
self.assertEqual(urlparse.urlparse("https:"),('https','','','','',''))
self.assertEqual(urlparse.urlparse("http://www.python.org:80"),
('http','www.python.org:80','','','',''))
# def test_main():
# test_support.run_unittest(UrlParseTestCase)
# if __name__ == "__main__":
# test_main()
def checkRoundtrips(self, url, parsed, split):
result = urlparse.urlparse(url)
self.assertEqual(result, parsed)
t = (result.scheme, result.netloc, result.path, result.params,
result.query, result.fragment)
self.assertEqual(t, parsed)
# put it back together and it should be the same
result2 = urlparse.urlunparse(result)
self.assertEqual(result2, url)
self.assertEqual(result2, result.geturl())
# the result of geturl() is a fixpoint; we can always parse it
# again to get the same result:
result3 = urlparse.urlparse(result.geturl())
self.assertEqual(result3.geturl(), result.geturl())
self.assertEqual(result3, result)
self.assertEqual(result3.scheme, result.scheme)
self.assertEqual(result3.netloc, result.netloc)
self.assertEqual(result3.path, result.path)
self.assertEqual(result3.params, result.params)
self.assertEqual(result3.query, result.query)
self.assertEqual(result3.fragment, result.fragment)
self.assertEqual(result3.username, result.username)
self.assertEqual(result3.password, result.password)
self.assertEqual(result3.hostname, result.hostname)
self.assertEqual(result3.port, result.port)
# check the roundtrip using urlsplit() as well
result = urlparse.urlsplit(url)
self.assertEqual(result, split)
t = (result.scheme, result.netloc, result.path, result.query,
result.fragment)
self.assertEqual(t, split)
result2 = urlparse.urlunsplit(result)
self.assertEqual(result2, url)
self.assertEqual(result2, result.geturl())
# check the fixpoint property of re-parsing the result of geturl()
result3 = urlparse.urlsplit(result.geturl())
self.assertEqual(result3.geturl(), result.geturl())
self.assertEqual(result3, result)
self.assertEqual(result3.scheme, result.scheme)
self.assertEqual(result3.netloc, result.netloc)
self.assertEqual(result3.path, result.path)
self.assertEqual(result3.query, result.query)
self.assertEqual(result3.fragment, result.fragment)
self.assertEqual(result3.username, result.username)
self.assertEqual(result3.password, result.password)
self.assertEqual(result3.hostname, result.hostname)
self.assertEqual(result3.port, result.port)
def checkRoundtrips(self, url, parsed, split):
result = urlparse.urlparse(url)
self.assertEqual(result, parsed)
t = (result.scheme, result.netloc, result.path,
result.params, result.query, result.fragment)
self.assertEqual(t, parsed)
# put it back together and it should be the same
result2 = urlparse.urlunparse(result)
self.assertEqual(result2, url)
self.assertEqual(result2, result.geturl())
# the result of geturl() is a fixpoint; we can always parse it
# again to get the same result:
result3 = urlparse.urlparse(result.geturl())
self.assertEqual(result3.geturl(), result.geturl())
self.assertEqual(result3, result)
self.assertEqual(result3.scheme, result.scheme)
self.assertEqual(result3.netloc, result.netloc)
self.assertEqual(result3.path, result.path)
self.assertEqual(result3.params, result.params)
self.assertEqual(result3.query, result.query)
self.assertEqual(result3.fragment, result.fragment)
self.assertEqual(result3.username, result.username)
self.assertEqual(result3.password, result.password)
self.assertEqual(result3.hostname, result.hostname)
self.assertEqual(result3.port, result.port)
# check the roundtrip using urlsplit() as well
result = urlparse.urlsplit(url)
self.assertEqual(result, split)
t = (result.scheme, result.netloc, result.path,
result.query, result.fragment)
self.assertEqual(t, split)
result2 = urlparse.urlunsplit(result)
self.assertEqual(result2, url)
self.assertEqual(result2, result.geturl())
# check the fixpoint property of re-parsing the result of geturl()
result3 = urlparse.urlsplit(result.geturl())
self.assertEqual(result3.geturl(), result.geturl())
self.assertEqual(result3, result)
self.assertEqual(result3.scheme, result.scheme)
self.assertEqual(result3.netloc, result.netloc)
self.assertEqual(result3.path, result.path)
self.assertEqual(result3.query, result.query)
self.assertEqual(result3.fragment, result.fragment)
self.assertEqual(result3.username, result.username)
self.assertEqual(result3.password, result.password)
self.assertEqual(result3.hostname, result.hostname)
self.assertEqual(result3.port, result.port)
def parse_url_archive(self, url):
try:
if ("\"" in url):
return
original_url = url.replace("http://arquivo.pt/noFrame/replay/", "")
datetime_s = original_url.split("/")[0]
original_url = original_url.split("/")[1:]
original_url = "/".join(original_url)
domain = urlparse(original_url).netloc
pubdate = datetime.strptime(datetime_s, '%Y%m%d%H%M%S')
doc = {
"domain": domain,
"url": url,
"original_url": original_url,
"pubdate": pubdate
}
db["processed_urls"].insert(doc)
except Exception as exc:
raise self.retry(exc=exc)
def test_issue14072(self):
p1 = urlparse.urlsplit('tel:+31-641044153')
self.assertEqual(p1.scheme, 'tel')
self.assertEqual(p1.path, '+31-641044153')
p2 = urlparse.urlsplit('tel:+31641044153')
self.assertEqual(p2.scheme, 'tel')
self.assertEqual(p2.path, '+31641044153')
# Assert for urlparse
p1 = urlparse.urlparse('tel:+31-641044153')
self.assertEqual(p1.scheme, 'tel')
self.assertEqual(p1.path, '+31-641044153')
p2 = urlparse.urlparse('tel:+31641044153')
self.assertEqual(p2.scheme, 'tel')
self.assertEqual(p2.path, '+31641044153')
def test_issue14072(self):
p1 = urlparse.urlsplit('tel:+31-641044153')
self.assertEqual(p1.scheme, 'tel')
self.assertEqual(p1.path, '+31-641044153')
p2 = urlparse.urlsplit('tel:+31641044153')
self.assertEqual(p2.scheme, 'tel')
self.assertEqual(p2.path, '+31641044153')
# Assert for urlparse
p1 = urlparse.urlparse('tel:+31-641044153')
self.assertEqual(p1.scheme, 'tel')
self.assertEqual(p1.path, '+31-641044153')
p2 = urlparse.urlparse('tel:+31641044153')
self.assertEqual(p2.scheme, 'tel')
self.assertEqual(p2.path, '+31641044153')
def test_attributes_bad_port(self):
"""Check handling of non-integer ports."""
p = urlparse.urlsplit("http://www.example.net:foo")
self.assertEqual(p.netloc, "www.example.net:foo")
self.assertRaises(ValueError, lambda: p.port)
p = urlparse.urlparse("http://www.example.net:foo")
self.assertEqual(p.netloc, "www.example.net:foo")
self.assertRaises(ValueError, lambda: p.port)
def test_attributes_bad_port(self):
"""Check handling of non-integer ports."""
p = urlparse.urlsplit("http://www.example.net:foo")
self.assertEqual(p.netloc, "www.example.net:foo")
self.assertRaises(ValueError, lambda: p.port)
p = urlparse.urlparse("http://www.example.net:foo")
self.assertEqual(p.netloc, "www.example.net:foo")
self.assertRaises(ValueError, lambda: p.port)
def test_telurl_params(self):
p1 = urlparse.urlparse('tel:123-4;phone-context=+1-650-516')
self.assertEqual(p1.scheme, 'tel')
self.assertEqual(p1.path, '123-4')
self.assertEqual(p1.params, 'phone-context=+1-650-516')
p1 = urlparse.urlparse('tel:+1-201-555-0123')
self.assertEqual(p1.scheme, 'tel')
self.assertEqual(p1.path, '+1-201-555-0123')
self.assertEqual(p1.params, '')
p1 = urlparse.urlparse('tel:7042;phone-context=example.com')
self.assertEqual(p1.scheme, 'tel')
self.assertEqual(p1.path, '7042')
self.assertEqual(p1.params, 'phone-context=example.com')
p1 = urlparse.urlparse('tel:863-1234;phone-context=+1-914-555')
self.assertEqual(p1.scheme, 'tel')
self.assertEqual(p1.path, '863-1234')
self.assertEqual(p1.params, 'phone-context=+1-914-555')
def test_telurl_params(self):
p1 = urlparse.urlparse('tel:123-4;phone-context=+1-650-516')
self.assertEqual(p1.scheme, 'tel')
self.assertEqual(p1.path, '123-4')
self.assertEqual(p1.params, 'phone-context=+1-650-516')
p1 = urlparse.urlparse('tel:+1-201-555-0123')
self.assertEqual(p1.scheme, 'tel')
self.assertEqual(p1.path, '+1-201-555-0123')
self.assertEqual(p1.params, '')
p1 = urlparse.urlparse('tel:7042;phone-context=example.com')
self.assertEqual(p1.scheme, 'tel')
self.assertEqual(p1.path, '7042')
self.assertEqual(p1.params, 'phone-context=example.com')
p1 = urlparse.urlparse('tel:863-1234;phone-context=+1-914-555')
self.assertEqual(p1.scheme, 'tel')
self.assertEqual(p1.path, '863-1234')
self.assertEqual(p1.params, 'phone-context=+1-914-555')
def test_unparse_parse(self):
for u in [
'Python',
'./Python',
'x-newscheme://foo.com/stuff',
'x://y',
'x:/y',
'x:/',
'/',
]:
self.assertEqual(urlparse.urlunsplit(urlparse.urlsplit(u)), u)
self.assertEqual(urlparse.urlunparse(urlparse.urlparse(u)), u)
def test_RFC2732(self):
for url, hostname, port in [
('http://Test.python.org:5432/foo/', 'test.python.org', 5432),
('http://12.34.56.78:5432/foo/', '12.34.56.78', 5432),
('http://[::1]:5432/foo/', '::1', 5432),
('http://[dead:beef::1]:5432/foo/', 'dead:beef::1', 5432),
('http://[dead:beef::]:5432/foo/', 'dead:beef::', 5432),
('http://[dead:beef:cafe:5417:affe:8FA3:deaf:feed]:5432/foo/',
'dead:beef:cafe:5417:affe:8fa3:deaf:feed', 5432),
('http://[::12.34.56.78]:5432/foo/', '::12.34.56.78', 5432),
('http://[::ffff:12.34.56.78]:5432/foo/',
'::ffff:12.34.56.78', 5432),
('http://Test.python.org/foo/', 'test.python.org', None),
('http://12.34.56.78/foo/', '12.34.56.78', None),
('http://[::1]/foo/', '::1', None),
('http://[dead:beef::1]/foo/', 'dead:beef::1', None),
('http://[dead:beef::]/foo/', 'dead:beef::', None),
('http://[dead:beef:cafe:5417:affe:8FA3:deaf:feed]/foo/',
'dead:beef:cafe:5417:affe:8fa3:deaf:feed', None),
('http://[::12.34.56.78]/foo/', '::12.34.56.78', None),
('http://[::ffff:12.34.56.78]/foo/',
'::ffff:12.34.56.78', None),
('http://Test.python.org:/foo/', 'test.python.org', None),
('http://12.34.56.78:/foo/', '12.34.56.78', None),
('http://[::1]:/foo/', '::1', None),
('http://[dead:beef::1]:/foo/', 'dead:beef::1', None),
('http://[dead:beef::]:/foo/', 'dead:beef::', None),
('http://[dead:beef:cafe:5417:affe:8FA3:deaf:feed]:/foo/',
'dead:beef:cafe:5417:affe:8fa3:deaf:feed', None),
('http://[::12.34.56.78]:/foo/', '::12.34.56.78', None),
('http://[::ffff:12.34.56.78]:/foo/',
'::ffff:12.34.56.78', None),
]:
urlparsed = urlparse.urlparse(url)
self.assertEqual((urlparsed.hostname, urlparsed.port) , (hostname, port))
for invalid_url in [
'http://::12.34.56.78]/',
'http://[::1/foo/',
'ftp://[::1/foo/bad]/bad',
'http://[::1/foo/bad]/bad',
'http://[::ffff:12.34.56.78']:
self.assertRaises(ValueError, urlparse.urlparse, invalid_url)
def test_attributes_without_netloc(self):
# This example is straight from RFC 3261. It looks like it
# should allow the username, hostname, and port to be filled
# in, but doesn't. Since it's a URI and doesn't use the
# scheme://netloc syntax, the netloc and related attributes
# should be left empty.
uri = "sip:[email protected];maddr=239.255.255.1;ttl=15"
p = urlparse.urlsplit(uri)
self.assertEqual(p.netloc, "")
self.assertEqual(p.username, None)
self.assertEqual(p.password, None)
self.assertEqual(p.hostname, None)
self.assertEqual(p.port, None)
self.assertEqual(p.geturl(), uri)
p = urlparse.urlparse(uri)
self.assertEqual(p.netloc, "")
self.assertEqual(p.username, None)
self.assertEqual(p.password, None)
self.assertEqual(p.hostname, None)
self.assertEqual(p.port, None)
self.assertEqual(p.geturl(), uri)
def test_attributes_without_netloc(self):
# This example is straight from RFC 3261. It looks like it
# should allow the username, hostname, and port to be filled
# in, but doesn't. Since it's a URI and doesn't use the
# scheme://netloc syntax, the netloc and related attributes
# should be left empty.
uri = "sip:[email protected];maddr=239.255.255.1;ttl=15"
p = urlparse.urlsplit(uri)
self.assertEqual(p.netloc, "")
self.assertEqual(p.username, None)
self.assertEqual(p.password, None)
self.assertEqual(p.hostname, None)
self.assertEqual(p.port, None)
self.assertEqual(p.geturl(), uri)
p = urlparse.urlparse(uri)
self.assertEqual(p.netloc, "")
self.assertEqual(p.username, None)
self.assertEqual(p.password, None)
self.assertEqual(p.hostname, None)
self.assertEqual(p.port, None)
self.assertEqual(p.geturl(), uri)
def test_unparse_parse(self):
for u in ['Python', './Python','x-newscheme://foo.com/stuff','x://y','x:/y','x:/','/',]:
self.assertEqual(urlparse.urlunsplit(urlparse.urlsplit(u)), u)
self.assertEqual(urlparse.urlunparse(urlparse.urlparse(u)), u)
def test_noslash(self):
# Issue 1637: http://foo.com?query is legal
self.assertEqual(urlparse.urlparse("http://example.com?blahblah=/foo"),
('http', 'example.com', '', '', 'blahblah=/foo', ''))
def test_RFC2368(self):
# Issue 11467: path that starts with a number is not parsed correctly
self.assertEqual(urlparse.urlparse('mailto:[email protected]'),
('mailto', '', '*****@*****.**', '', '', ''))
def test_RFC2368(self):
# Issue 11467: path that starts with a number is not parsed correctly
self.assertEqual(urlparse.urlparse('mailto:[email protected]'),
('mailto', '', '*****@*****.**', '', '', ''))
def test_noslash(self):
# Issue 1637: http://foo.com?query is legal
self.assertEqual(urlparse.urlparse("http://example.com?blahblah=/foo"),
('http', 'example.com', '', '', 'blahblah=/foo', ''))
