def test_get_html_bad_schema(): """ Gracefully fail on bad schema """ url = 'https://bad.url' html = TVScraper._get_html(url=url) assert html is None
def test_create_season_url():
imdb_id = 'garbage'
series_url = f'https://www.imdb.com/title/{imdb_id}'
season_number = '666'
url = TVScraper._create_season_url(series_url=series_url,
season_number=season_number)
assert url == f'{series_url}/episodes?season={season_number}'
def main(title_id):
"""Console script for imdb_tv_scraper.
TITLE_ID is the IMDB title identifier like ttXXXXXXX"""
data = TVScraper.scrape_imdb_id(imdb_id=title_id)
json_data = json.dumps(data)
click.echo(json_data)
return 0
def test_scrape_series_success(path):
with open(path) as f:
html = f.read()
data = TVScraper._scrape_series(html=html)
assert data['title']
assert type(data['title']) is str
assert data['seasons']
assert type(data['seasons']) is int
def test_scrape_season_success(path):
with open(path) as f:
html = f.read()
season_data = TVScraper._scrape_season(html=html)
for episode in season_data:
assert episode['title']
assert type(episode['title']) is str
assert episode['rating']
assert type(episode['rating']) is float
def test_scrape_imdb_id_success(): imdb_id = 'tt0412142' series_data = TVScraper.scrape_imdb_id(imdb_id=imdb_id) assert type(series_data) is dict assert series_data['title'] assert series_data['seasons'] for season in series_data['seasons']: assert season for episode in season: assert episode['title'] assert type(episode['title']) is str assert episode['rating'] assert type(episode['rating']) is float
def test_scrape_season_failure():
season_data = TVScraper._scrape_season(html=None)
assert season_data == []
def test_create_series_url():
imdb_id = 'garbage'
url = TVScraper._create_series_url(imdb_id=imdb_id)
assert url == f'https://www.imdb.com/title/{imdb_id}'
def test_scrape_series_failure():
data = TVScraper._scrape_series(html=None)
assert data is None
def test_get_html_success(): url = 'https://www.imdb.com/title/tt0412142' html = TVScraper._get_html(url=url) assert html
def test_scrape_imdb_id_bad_id(): imdb_id = '' series_data = TVScraper.scrape_imdb_id(imdb_id=imdb_id) assert series_data is None
def test_get_html_not_found(): url = 'https://www.imdb.com/title/123' html = TVScraper._get_html(url=url) assert html is None