def test_handleHTML_regex_unit_code_test3(self):
parser = handleHTML.parse()
result = parser.unit_regex.match("year 2015")
if (not result):
pass
else:
self.fail()
def test_handleHTML_regex_unit_code_test2(self):
parser = handleHTML.parse()
result = parser.unit_regex.match("pys101")
if (result):
pass
else:
self.fail()
def test_handleHTML_regex_heading_tag(self):
parser = handleHTML.parse()
result = parser.heading_tag_regex.match("h5")
if (result):
pass
else:
self.fail()
def test_handleHTML_regex_test_double_slash(self):
parser = handleHTML.parse()
result = parser.double_slash_regex.match("//handbooks.uwa.edu.au/units/unitdetails?code=cits3200")
if (result):
pass
else:
self.fail()
def test_handleHTML_regex_test_http(self):
parser = handleHTML.parse()
result = parser.http_regex.match("http://handbooks.uwa.edu.au/units/unitdetails?code=cits3200")
if (result):
pass
else:
self.fail()
#
from urllib.request import urlopen
from urllib.error import URLError
import handleHTML
from Stack import Stack
#urls already visited
visited = set()
#urls to visit
stack = Stack()
in_stack = set()
#parser object to manipulate HTML
parser = handleHTML.parse()
#parser.re_init(stack, visited, in_stack)
#recursively load URL via stack
def recursiveload(url, dom, db):
database = db
count = 0
stack.push(url)
in_stack.add(url)
while stack.isEmpty() != True:
try:
newurl = stack.pop()
in_stack.remove(newurl)
if dom in newurl:
def test_handleHTML_get_domain(self):
parser = handleHTML.parse()
parser.url = "http://handbooks.uwa.edu.au/units/unitdetails?code=cits3200"
dom = parser.get_domain()
self.assertEqual(dom, "handbooks.uwa.edu.au")
def test_handleHTML_handle_end_tag(self):
parser = handleHTML.parse()
parser.feed("<body></body>")
self.assertTrue(not parser.body_tag_open)
def test_handleHTML_handle_start_tag(self):
parser = handleHTML.parse()
parser.feed("<body>")
self.assertTrue(parser.body_tag_open)