def test_to_json():
p = HtmlParser(page)
jsoned_document = p.to_json()
assert "A fantastic title!" in jsoned_document['title']
clean_body = jsoned_document['body']
assert "A fantastic body!" in clean_body
assert "The header" not in clean_body
assert "The footer" not in clean_body
assert jsoned_document["links"] == [
'/defra',
'www.links1.com',
'www.links2.com',
'www.links3.com',
'http://www.gov.uk/stats.pdf'
]
assert jsoned_document["download_links"] == [
'http://www.gov.uk/stats.pdf'
]
assert jsoned_document["organisations"] == [
'DEFRA'
]
def test_clean_body():
p = HtmlParser(page)
clean_body = p.clean_body()
assert "A fantastic body!" in clean_body
assert "The header" not in clean_body
assert "The footer" not in clean_body
def test_links():
p = HtmlParser(page)
assert p.links() == [
'/defra',
'www.links1.com',
'www.links2.com',
'www.links3.com',
'http://www.gov.uk/stats.pdf'
]
def test_organisations():
p = HtmlParser(page)
assert p.organisations() == [
'DEFRA'
]
def test_download_links():
p = HtmlParser(page)
assert p.download_links() == [
'http://www.gov.uk/stats.pdf'
]
def test_title():
p = HtmlParser(page)
assert "A fantastic title!" in p.title()