def test_parsers():
soup = bs.to_soup(ex.HTML_1, parser='html.parser')
assert isinstance(soup, BeautifulSoup)
#
soup = bs.to_soup(ex.HTML_1, parser='lxml')
assert isinstance(soup, BeautifulSoup)
#
soup = bs.to_soup(ex.HTML_1, parser='html5lib')
assert isinstance(soup, BeautifulSoup)
def test_parsers():
soup = bs.to_soup(ex.HTML_1, parser='html.parser')
assert isinstance(soup, BeautifulSoup)
#
soup = bs.to_soup(ex.HTML_1, parser='lxml')
assert isinstance(soup, BeautifulSoup)
#
soup = bs.to_soup(ex.HTML_1, parser='html5lib')
assert isinstance(soup, BeautifulSoup)
def test_get_links():
soup = bs.to_soup(ex.LINKS)
links = bs.get_links(soup, 'http://retrogames.com')
assert links == ['http://retrogames.com', 'http://retrogames.com/games/elite', 'http://retrogames.com/games/commando']
#
links = bs.get_links(soup)
assert links == ['http://retrogames.com', '/games/elite', '/games/commando']
def test_make_links_absolute():
soup = bs.to_soup(ex.LINKS)
soup = bs.make_links_absolute(soup, 'http://retrogames.com')
#
links = bs.get_links(soup)
assert links == ['http://retrogames.com', 'http://retrogames.com/games/elite', 'http://retrogames.com/games/commando']
def test_make_links_absolute():
soup = bs.to_soup(ex.LINKS)
soup = bs.make_links_absolute(soup, 'http://retrogames.com')
#
links = bs.get_links(soup)
assert links == [
'http://retrogames.com', 'http://retrogames.com/games/elite',
'http://retrogames.com/games/commando'
]
def test_get_links():
soup = bs.to_soup(ex.LINKS)
links = bs.get_links(soup, 'http://retrogames.com')
assert links == [
'http://retrogames.com', 'http://retrogames.com/games/elite',
'http://retrogames.com/games/commando'
]
#
links = bs.get_links(soup)
assert links == [
'http://retrogames.com', '/games/elite', '/games/commando'
]
def check():
"""Just an example how to use the BS4 library."""
text = str(get_page(URL))
soup = bs.to_soup(text, PARSER)
book = soup.find('div', {'class' : 'module bookSmall'})
link = book.find('a', href=True)
print link['href']
#
book = soup.find('div', {'class' : 'module fullBook'})
try:
title = book.find('span', {'property': 'dc:title'}).text.lower()
except:
title = ""
print title
tabs = soup.find_all('div', {'class' : 'tabModules'})[-1]
try:
desc = tabs.find('p', {'class' : 'paragraph'}).text.lower()
except:
desc = ""
print desc
def test_to_soup():
soup = bs.to_soup(ex.HTML_1)
assert isinstance(soup, BeautifulSoup)
assert str(soup) == """
def test_prettify():
soup = bs.to_soup(ex.UGLY)
assert soup.prettify() == """<html>
def test_to_soup():
soup = bs.to_soup(ex.HTML_1)
assert isinstance(soup, BeautifulSoup)
assert str(soup) == """
def test_prettify():
soup = bs.to_soup(ex.UGLY)
assert soup.prettify() == """<html>