Python get_domain Examples

Example #1

def test_get_domain():
    assert urls.get_domain('http://www.bbc.co.uk') == 'bbc.co.uk'
    assert urls.get_domain('http://www.nhs.uk') == 'www.nhs.uk'  # nhs.uk is a public suffix, surprise
    assert urls.get_domain('http://sub.nhs.uk') == 'sub.nhs.uk'  # ditto
    assert urls.get_domain('http://www.example.com') == 'example.com'
    assert urls.get_domain('http://sub.example.com') == 'example.com'
    assert urls.get_domain('http://sub.blogspot.com') == 'sub.blogspot.com'  # we want this behavior
    # if the blogspot test doesn't work, try this from the shell: "tldextract -u -p"
    # unfortunately, all tldextract users use the same cache
    assert urls.get_domain('http://www.com') == 'www.com'

Example #2

File: test_urls.py Project: cocrawler/cocrawler

def test_get_domain():
    assert urls.get_domain('http://www.bbc.co.uk') == 'bbc.co.uk'
    assert urls.get_domain('http://www.nhs.uk') == 'www.nhs.uk'  # nhs.uk is a public suffix, surprise
    assert urls.get_domain('http://sub.nhs.uk') == 'sub.nhs.uk'  # ditto
    assert urls.get_domain('http://www.example.com') == 'example.com'
    assert urls.get_domain('http://sub.example.com') == 'example.com'
    assert urls.get_domain('http://sub.blogspot.com') == 'sub.blogspot.com', "make sure private domains are included"
    # if the blogspot test doesn't work, try this from the shell: "tldextract -u -p"
    # unfortunately, all tldextract users use the same cache
    # https://github.com/john-kurkowski/tldextract/issues/66
    assert urls.get_domain('http://www.com') == 'www.com'

Example #3

def test_get_domain():
    assert urls.get_domain('http://www.bbc.co.uk') == 'bbc.co.uk'
    assert urls.get_domain(
        'http://www.nhs.uk'
    ) == 'www.nhs.uk'  # nhs.uk is a public suffix, surprise
    assert urls.get_domain('http://sub.nhs.uk') == 'sub.nhs.uk'  # ditto
    assert urls.get_domain('http://www.example.com') == 'example.com'
    assert urls.get_domain('http://sub.example.com') == 'example.com'
    assert urls.get_domain(
        'http://sub.blogspot.com'
    ) == 'sub.blogspot.com', "make sure private domains are included"
    # if the blogspot test doesn't work, try this from the shell: "tldextract -u -p"
    # unfortunately, all tldextract users use the same cache
    # https://github.com/john-kurkowski/tldextract/issues/66
    assert urls.get_domain('http://www.com') == 'www.com'