def test_recursive_links_not_separated_equivalent_separated(self):
"""
Test that not separating the links returns the same articles as when separating them.
"""
page = 'Stichting Voortgezet Onderwijs van de Bovenwindse Eilanden'
separate_articles = links.collect_recursive(page, 2, separate=True)
articles = links.collect_recursive(page, 2, separate=False)
self.assertEqual(
set(articles),
set([
article for articles in separate_articles.values()
for article in articles
]))
def test_recursive_links_not_separated_multiple_pages(self):
"""
Test that getting recursive links from multiple pages without separating them works.
"""
page = 'Stichting Voortgezet Onderwijs van de Bovenwindse Eilanden'
articles = links.collect_recursive(page, 2, separate=False)
self.assertTrue(len(articles))
def test_recursive_links_multiple_levels(self):
"""
Test that recursive collection with multiple levels returns more pages.
"""
page = 'Stichting Voortgezet Onderwijs van de Bovenwindse Eilanden'
articles = links.collect_recursive(page, 2, separate=True)
self.assertTrue(page in articles)
self.assertGreater(len(articles), 1)
def test_recursive_links_separated_multiple_pages(self):
"""
Test that getting recursive links from separate pages and separating them by article works.
"""
pages = ['Olympique Lyonnais', 'Michelangelo']
articles = links.collect_recursive(pages, 1, separate=True)
self.assertEqual(set(pages), set(articles.keys()))
self.assertTrue(all(len(links) for links in articles.values()))
def test_recursive_links_not_separated(self):
"""
Test that getting recursive links without separating them works.
"""
page = 'Olympique Lyonnais'
articles = links.collect_recursive(page, 1, separate=False)
self.assertEqual(set(articles), set(links.collect(page,
separate=False)))
def test_recursive_links_level_one(self):
"""
Test that recursive collection with a level of 1 returns the same results as normal link collection.
"""
page = 'Olympique Lyonnais'
articles = links.collect_recursive(page, 1, separate=False)
self.assertEqual(set(articles), set(links.collect(page,
separate=False)))
def test_recursive_links_introduction_subset(self):
"""
Test that when getting recursive links from the introduction retrieves a subset of normal recursive link retrieval.
"""
page = 'Scholengemeenschap Bonaire'
intro_articles = links.collect_recursive(page,
2,
separate=True,
introduction_only=True)
articles = links.collect_recursive(page,
2,
separate=True,
introduction_only=False)
self.assertLess(len(intro_articles), len(articles))
self.assertTrue(
all(
len(intro_articles[article]) < len(articles[article])
for article in intro_articles))
def test_recursive_links_separated(self):
"""
Test that getting recursive links and separating them by article works.
"""
page = 'Olympique Lyonnais'
articles = links.collect_recursive(page, 1, separate=True)
self.assertTrue(page in articles)
self.assertEqual(set(articles.get(page)),
set(links.collect(page, separate=True).get(page)))