10 examples of 'python get domain from url' in Python

43
def get_domain_from_url(path):
44
    try:
45
        domain, = domain_url_re.search(path).groups()
46
    except Exception:
47
        domain = None
48
    return domain

90
def getDomainFromURL(url):
91
	# QUESTION-TODO added .split('\\')[0], because sometime URL looked like: http://domain\
92
	domain = url.split('://')[1].split('/')[0].split(':')[0].split('\\')[0]
93
	if(domain[-1] == '.'):
94
		domain = domain[:-1]
95
	return domain

6
def domain_for_url(url):
7
	# Strip out everything from url but the hostname
8
	hostname = url.strip()
9
	hostname = hostname.replace("http://", "")
10
	hostname = hostname.replace("https://", "")
11
	hostname = DomainIsolator.match(hostname).groups()[0]
12
	hostname = hostname.split(".")
13
14
	# We will still want to throw away most of the hostname
15
	if len(hostname) >= 2:
16
		# Take the top-level and second-level domain
17
		domain = hostname[len(hostname) - 2] + '.' + hostname[len(hostname) - 1]
18
		# If this is one of the known second-level domains, take the third
19
		# level as well
20
		if domain in DomainList and len(hostname) >= 3:
21
			domain = hostname[len(hostname) - 3] + '.' + domain
22
	else:
23
		domain = '.'.join(hostname)
24
	
25
	return domain

118
def get_domain(self, full_url):
119
	"""function to extract the domain name from the URL"""
120
	clean_reg= re.compile(r'^((?:https?:\/\/)?(?:www\.)?).*?(\/.*)?$')
121
	match = re.search(clean_reg, full_url)
122
	beg, end = match.group(1), match.group(2)
123
	domain = string.replace(full_url, beg, '')
124
	domain = string.replace(domain, end, '')
125
	return domain

535
def url_host_domain(url):
536
    """
537
    Return a tuple of the (host, domain) of a URL or None. Assumes that the
538
    URL has a scheme.
539
    """
540
    try:
541
        parsed = urlpy.parse(url)
542
        host = parsed.host if py3 else parsed._host
543
        if not host:
544
            return None, None
545
        domain = parsed.pld if py3 else parsed.pld()
546
        return host.lower(), domain.lower()
547
    except Exception as e:
548
        if TRACE:
549
            logger_debug('url_host_domain: failed for:', url, 'with:', repr(e))
550
        # ignore it
551
        return None, None

3
def get_domain(s):
4
    if '@' in s:
5
        # it's an email address
6
        domain = s[s.index('@') + 1:]
7
    else:
8
        result = urlparse.urlparse(s)
9
        domain = result.netloc
10
    return domain

148
def get_domain(self, url=""):
149
    domain = url[0].replace("http://", '')
150
    domain = domain.replace("https://", '')
151
    domain = domain.split("/")
152
    return domain[0]

77
def getHost(url) :
78
    exp = re.compile("^(https?\:\/\/)((([\da-z\.-]+)\.([a-z\.]{2,6}))|[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3})(:[0-9]+)?([\/\w \.-]*)\/?([\/\w \.-]*)\/?((\?|&).+?(=.+?)?)*$")
79
    res = exp.match(url)
80
    return str(res.group(2))

282
def get_host(url):
283
    """
284
    Given a url, return its scheme, host and port (None if it's not there).
285
286
    For example:
287
    >>> get_host('http://google.com/mail/')
288
    http, google.com, None
289
    >>> get_host('google.com:80')
290
    http, google.com, 80
291
    """
292
    # This code is actually similar to urlparse.urlsplit, but much
293
    # simplified for our needs.
294
    port = None
295
    scheme = 'http'
296
    if '//' in url:
297
        scheme, url = url.split('://', 1)
298
    if '/' in url:
299
        url, path = url.split('/', 1)
300
    if ':' in url:
301
        url, port = url.split(':', 1)
302
        port = int(port)
303
    return scheme, url, port

10
def __get_domain(uri):
11
    url = urlparse(uri)
12
    return '{}://{}'.format(url.scheme, url.netloc)