def test_link_checker(self):
valid_urls = ['http://domain.com',
'http://example.com/path/to/page?name=ferret&color=purple',
'https://docs.python.org/2/library/unittest.html',
'http://127.0.0.1:8080',
'http://localhost:8080',
'http://web-nginx.example.com:80'
]
invalid_urls = ['domain.com',
'http://domain',
'http://.com',
'file:///etc/fstab,'
]
# test valid urls
for url in valid_urls:
self.assertTrue(HttpClient.is_link_ok(url))
# test invalid urls
for url in invalid_urls:
self.assertFalse(HttpClient.is_link_ok(url))
def page_links(self, link):
"""
Downloads defined url from link with content like images, css, JavaScript, then parse all urls in a href tags.
and return it as list.
:param link: web page to be processed
:return: list of parsed urls.
"""
self.driver.get(link)
links = self.driver.find_elements_by_tag_name('a')
hrefs = []
for link in links:
url = link.get_attribute("href")
if HttpClient.is_link_ok(url):
hrefs.append(url)
self.wait()
return hrefs
