def dataset():
"""Fixture for standard dataset"""
print("setup")
doxil_dataset = ReviewDataset('TEST', 'WebMD')
doxil_dataset.load()
yield doxil_dataset
print("teardown")
final_dataset_name = 'doxil-dataset-' + str(date.today()) + '.pickle'
filenames = [
'doxil-dataset.pickle', 'doxil-reviews.json', 'doxil-reviews.csv',
'test-url-dataset.pickle', final_dataset_name
]
for name in filenames:
if os.path.exists(name):
os.remove(name)
def test_init_everydayhealth():
"""Test the name is lowercased during init"""
dataset = ReviewDataset('test', 'EverydayHealth')
assert dataset.drug_name == 'test'
assert dataset.scraper == 'EverydayHealth'
def test_init_drugratingz():
"""Test the name is lowercased during init"""
dataset = ReviewDataset('test', 'DrugRatingz')
assert dataset.drug_name == 'test'
assert dataset.scraper == 'DrugRatingz'
def test_collect_everydayhealth_urls():
"""Test collect urls"""
dataset = ReviewDataset('test-url', 'EverydayHealth')
dataset.collect_urls('test-urls.csv')
assert os.path.exists('testurl-dataset.pickle')
os.remove('testurl-dataset.pickle')
def test_collect_drugratingz_urls():
"""Test collect urls"""
dataset = ReviewDataset('test-url', 'DrugRatingz')
dataset.collect_urls('test-urls.csv')
assert os.path.exists('testurl-dataset.pickle')
os.remove('testurl-dataset.pickle')
def main():
""" Main function.
"""
review_dataset = ReviewDataset('Citalopram', 'WebMD')
url = 'https://www.webmd.com/drugs/drugreview-1701-citalopram-oral.aspx?drugid=1701&drugname=citalopram-oral'
review_dataset.collect(url)
review_dataset.save()
# review_dataset.load()
# review_dataset.final_save()
review_dataset.generate_rating_webmd()
review_dataset.print_stats()
review_dataset.print_meta()