def test_mixed_types_rejected(self):
# Several functions that process either strings or ASCII encoded bytes
# accept multiple arguments. Check they reject mixed type input
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urlparse("www.python.org", b"http")
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urlparse(b"www.python.org", "http")
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urlsplit("www.python.org", b"http")
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urlsplit(b"www.python.org", "http")
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urlunparse(
(b"http", "www.python.org", "", "", "", ""))
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urlunparse(
("http", b"www.python.org", "", "", "", ""))
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urlunsplit((b"http", "www.python.org", "", "", ""))
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urlunsplit(("http", b"www.python.org", "", "", ""))
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urljoin("http://python.org", b"http://python.org")
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urljoin(b"http://python.org", "http://python.org")
def checkJoin(self, base, relurl, expected):
str_components = (base, relurl, expected)
self.assertEqual(urllib_parse.urljoin(base, relurl), expected)
bytes_components = baseb, relurlb, expectedb = [
x.encode('ascii') for x in str_components
]
self.assertEqual(urllib_parse.urljoin(baseb, relurlb), expectedb)
def parse(html):
soup = BeautifulSoup(html, 'lxml')
urls = soup.find_all('a', {"href": re.compile('^/.+?/$')})
title = soup.find('h1').get_text().strip()
page_urls = set([urljoin(base_url, url['href']) for url in urls])
url = soup.find('meta', {'property': "og:url"})['content']
return title, page_urls, url
def get_attachments(self, obj):
attachments = itertools.chain(
itertools.chain(*map(
lambda a: itertools.chain(a.attachments.all(
), a.report_attachments.all()), obj.tpm_activities.all())),
obj.report_attachments.all())
return ', '.join(
map(
lambda a: '{} - {}'.format(a.file_type,
urljoin(site_url(), a.url)),
attachments))
def test_mixed_types_rejected(self):
# Several functions that process either strings or ASCII encoded bytes
# accept multiple arguments. Check they reject mixed type input
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urlparse("www.python.org", b"http")
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urlparse(b"www.python.org", "http")
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urlsplit("www.python.org", b"http")
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urlsplit(b"www.python.org", "http")
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urlunparse(( b"http", "www.python.org","","","",""))
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urlunparse(("http", b"www.python.org","","","",""))
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urlunsplit((b"http", "www.python.org","","",""))
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urlunsplit(("http", b"www.python.org","","",""))
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urljoin("http://python.org", b"http://python.org")
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urljoin(b"http://python.org", "http://python.org")
def download_file(filename, base_url, out_dir):
url = urljoin(base_url, filename)
out = join(out_dir, filename)
if exists(out):
while True:
overwrite = input(
'File {} already exists, overwrite it (Y/N)?'.format(out))
if overwrite.upper() in {'Y', 'YES'}:
overwrite = 'Y'
break
elif overwrite.upper() in {'N', 'NO'}:
overwrite = 'N'
break
if overwrite == 'N':
return
print('Downloading {url} to {out}'.format(
url=url,
out=out,
))
sh.wget('-O', out, url, _tty_out=True)
def endpoint_ava(endp, baseurl):
key = '{}_endpoint'.format(endp.etype)
val = urljoin(baseurl, endp.url)
return {key: val}
def checkJoin(self, base, relurl, expected):
str_components = (base, relurl, expected)
self.assertEqual(urllib_parse.urljoin(base, relurl), expected)
bytes_components = baseb, relurlb, expectedb = [
x.encode('ascii') for x in str_components]
self.assertEqual(urllib_parse.urljoin(baseb, relurlb), expectedb)
def endpoint_ava(endp, baseurl):
key = '{}_endpoint'.format(endp.etype)
val = urljoin(baseurl, endp.url)
return {key: val}
def get_token_auth_link(user):
token = create_callback_token_for_user(user, 'email')
return update_url_with_kwargs(urljoin(site_url(), reverse('email_auth:login')), token=token)
