def test_incorrect_url():
"""
Tests that the scrape_page function raises and assertion error when a url is
entered with an incorrect domain name (not 'https://everydayhealth.com...')
"""
scraper = EverydayHealthScraper()
with pytest.raises(AssertionError):
scraper.scrape_page(
'https://www.drugs.com/comments/aripiprazole/abilify.html?page=1')
def test_scrape_page_with_parameters():
"""
Tests to make sure that calling the scrape_page function on a scraper object with a
non-default parameter (collect_url true) collects the correct types of data
('comment', 'rating, 'date', 'drug', and 'url')
"""
scraper = EverydayHealthScraper(collect_urls=True)
scraper.scrape_page(
'https://www.everydayhealth.com/drugs/hydroxyzine/reviews')
data_collected = list(scraper.reviews[0].keys())
assert len(data_collected) == 5
assert 'url' in data_collected
def test_scrape_page_default_parameters():
"""
Tests to make sure that calling the scrape_page function on a scraper object
with a default parameter collects the correct types of data ('comment', 'rating',
'date', and 'drug') and that the correct number of reviews were collected (20)
"""
scraper = EverydayHealthScraper()
scraper.scrape_page('https://www.everydayhealth.com/drugs/allegra/reviews')
data_collected = list(scraper.reviews[0].keys())
assert len(data_collected) == 4
assert 'comment' in data_collected
assert 'rating' in data_collected
assert 'date' in data_collected
assert 'drug' in data_collected
assert len(scraper.reviews) == 20
def test_no_reviews():
"""
Tests that the scrape page function returns 'None' when no reviews are
found on the page
"""
scraper = EverydayHealthScraper()
returned = scraper.scrape_page(
'https://www.everydayhealth.com/drugs/triprolidine/reviews')
assert not returned