def test_no_year(self):
# Make sure parser doesn't crash for movies with no year
parser = ImdbParser()
parser.parse('tt3303790')
assert parser.name == 'Master of None'
# There is no year
assert not parser.year
def test_no_year(self):
# Make sure parser doesn't crash for movies with no year
parser = ImdbParser()
parser.parse('tt3303790')
assert parser.name == 'Master of None'
# There is no year
assert not parser.year
def test_no_plot(self):
# Make sure parser doesn't crash for movies with no plot
parser = ImdbParser()
parser.parse('tt1300562')
assert parser.name == 'Goodbye Mothers'
# There is no plot
assert not parser.plot_outline
def test_no_plot(self):
# Make sure parser doesn't crash for movies with no plot
parser = ImdbParser()
parser.parse('tt1300562')
assert parser.name == 'Goodbye Mothers'
# There is no plot
assert not parser.plot_outline
def _parse_new_movie(self, imdb_url, session):
"""
Get Movie object by parsing imdb page and save movie into the database.
:param imdb_url: IMDB url
:param session: Session to be used
:return: Newly added Movie
"""
parser = ImdbParser()
parser.parse(imdb_url)
# store to database
movie = db.Movie()
movie.photo = parser.photo
movie.title = parser.name
movie.original_title = parser.original_name
movie.score = parser.score
movie.votes = parser.votes
movie.meta_score = parser.meta_score
movie.year = parser.year
movie.mpaa_rating = parser.mpaa_rating
movie.plot_outline = parser.plot_outline
movie.url = imdb_url
for name in parser.genres:
genre = session.query(db.Genre).filter(db.Genre.name == name).first()
if not genre:
genre = db.Genre(name)
movie.genres.append(genre) # pylint:disable=E1101
for index, name in enumerate(parser.languages):
language = session.query(db.Language).filter(db.Language.name == name).first()
if not language:
language = db.Language(name)
movie.languages.append(db.MovieLanguage(language, prominence=index))
for imdb_id, name in parser.actors.items():
actor = session.query(db.Actor).filter(db.Actor.imdb_id == imdb_id).first()
if not actor:
actor = db.Actor(imdb_id, name)
movie.actors.append(actor) # pylint:disable=E1101
for imdb_id, name in parser.directors.items():
director = session.query(db.Director).filter(db.Director.imdb_id == imdb_id).first()
if not director:
director = db.Director(imdb_id, name)
movie.directors.append(director) # pylint:disable=E1101
for imdb_id, name in parser.writers.items():
writer = session.query(db.Writer).filter(db.Writer.imdb_id == imdb_id).first()
if not writer:
writer = db.Writer(imdb_id, name)
movie.writers.append(writer) # pylint:disable=E1101
for name in parser.plot_keywords:
plot_keyword = (
session.query(db.PlotKeyword).filter(db.PlotKeyword.name == name).first()
)
if not plot_keyword:
plot_keyword = db.PlotKeyword(name)
movie.plot_keywords.append(plot_keyword) # pylint:disable=E1101
# so that we can track how long since we've updated the info later
movie.updated = datetime.now()
session.add(movie)
return movie
def test_parsed_data(self):
parser = ImdbParser()
parser.parse('tt0114814')
assert parser.actors == {
'nm0000592': 'Pete Postlethwaite',
'nm0261452': 'Christine Estabrook',
'nm0000751': 'Suzy Amis',
'nm0000286': 'Stephen Baldwin',
'nm0000445': 'Dan Hedaya',
'nm0800339': 'Phillipe Simon',
'nm0002064': 'Giancarlo Esposito',
'nm0001590': 'Chazz Palminteri',
'nm0000321': 'Gabriel Byrne',
'nm0790436': 'Jack Shearer',
'nm0000228': 'Kevin Spacey',
'nm0001629': 'Kevin Pollak',
'nm0107808': 'Carl Bressler',
'nm0001125': 'Benicio Del Toro',
'nm0000860': 'Paul Bartel',
}, 'Actors not parsed correctly'
assert parser.directors == {
'nm0001741': 'Bryan Singer'
}, 'Directors not parsed correctly'
print(parser.genres)
assert len(
set(parser.genres).intersection([
u'crime', u'mystery', u'thriller'
])) == len([u'crime', u'mystery',
u'thriller']), 'Genres not parsed correctly'
assert parser.imdb_id == 'tt0114814', 'ID not parsed correctly'
assert (len(
set(parser.languages).intersection(
['english', 'hungarian', 'spanish',
'french'])) == 4), 'Languages not parsed correctly'
assert parser.mpaa_rating == 'R', 'Rating not parsed correctly'
assert parser.name == 'The Usual Suspects', 'Name not parsed correctly'
assert parser.photo, 'Photo not parsed correctly'
assert parser.plot_outline == (
'Following a truck hijack in New York, five conmen are arrested and brought together for questioning. '
'As none of them are guilty, they plan a revenge operation against the police. The operation goes well, '
'but then the influence of a legendary mastermind criminal called Keyser S\xf6ze is felt. It becomes '
'clear that each one of them has wronged S\xf6ze at some point and must pay back now. The payback job '
'leaves 27 men dead in a boat explosion, but the real question arises now: Who actually is Keyser S\xf6ze?'
), 'Plot outline not parsed correctly'
assert 8.0 < parser.score < 9.0, 'Score not parsed correctly'
assert parser.url == 'https://www.imdb.com/title/tt0114814/', 'URL not parsed correctly'
assert 400000 < parser.votes < 1000000, 'Votes not parsed correctly'
assert parser.year == 1995, 'Year not parsed correctly'
expected_keywords = {
u'criminal', u'suspect', u'criminal mastermind', u'dirty cop',
u'burying a body'
}
assert len(expected_keywords.intersection(parser.plot_keywords)) == len(expected_keywords),\
'Parsed plot keywords missing items from the expected result'
assert len(expected_keywords) == len(parser.plot_keywords),\
'Parsed plot keyword count does not match expected.'
def test_plot_with_links(self):
"""Make sure plot doesn't terminate at the first link. GitHub #756"""
parser = ImdbParser()
parser.parse('tt2503944')
assert parser.plot_outline == (
"Chef Adam Jones (Bradley Cooper) had it all - and lost it. A two-star Michelin "
"rockstar with the bad habits to match, the former enfant terrible of the Paris "
"restaurant scene did everything different every time out, and only ever cared "
"about the thrill of creating explosions of taste. To land his own kitchen and "
"that third elusive Michelin star though, he'll need the best of the best on "
"his side, including the beautiful Helene (Sienna Miller).")
def test_plot_with_links(self):
"""Make sure plot doesn't terminate at the first link. GitHub #756"""
parser = ImdbParser()
parser.parse('tt2503944')
assert parser.plot_outline == (
"Chef Adam Jones (Bradley Cooper) had it all - and lost it. A two-star Michelin "
"rockstar with the bad habits to match, the former enfant terrible of the Paris "
"restaurant scene did everything different every time out, and only ever cared "
"about the thrill of creating explosions of taste. To land his own kitchen and "
"that third elusive Michelin star though, he'll need the best of the best on "
"his side, including the beautiful Helene (Sienna Miller)."
)
def _parse_new_movie(self, imdb_url, session):
"""
Get Movie object by parsing imdb page and save movie into the database.
:param imdb_url: IMDB url
:param session: Session to be used
:return: Newly added Movie
"""
parser = ImdbParser()
parser.parse(imdb_url)
# store to database
movie = db.Movie()
movie.photo = parser.photo
movie.title = parser.name
movie.original_title = parser.original_name
movie.score = parser.score
movie.votes = parser.votes
movie.meta_score = parser.meta_score
movie.year = parser.year
movie.mpaa_rating = parser.mpaa_rating
movie.plot_outline = parser.plot_outline
movie.url = imdb_url
for name in parser.genres:
genre = session.query(db.Genre).filter(db.Genre.name == name).first()
if not genre:
genre = db.Genre(name)
movie.genres.append(genre) # pylint:disable=E1101
for index, name in enumerate(parser.languages):
language = session.query(db.Language).filter(db.Language.name == name).first()
if not language:
language = db.Language(name)
movie.languages.append(db.MovieLanguage(language, prominence=index))
for imdb_id, name in parser.actors.items():
actor = session.query(db.Actor).filter(db.Actor.imdb_id == imdb_id).first()
if not actor:
actor = db.Actor(imdb_id, name)
movie.actors.append(actor) # pylint:disable=E1101
for imdb_id, name in parser.directors.items():
director = session.query(db.Director).filter(db.Director.imdb_id == imdb_id).first()
if not director:
director = db.Director(imdb_id, name)
movie.directors.append(director) # pylint:disable=E1101
for imdb_id, name in parser.writers.items():
writer = session.query(db.Writer).filter(db.Writer.imdb_id == imdb_id).first()
if not writer:
writer = db.Writer(imdb_id, name)
movie.writers.append(writer) # pylint:disable=E1101
# so that we can track how long since we've updated the info later
movie.updated = datetime.now()
session.add(movie)
return movie
def test_parsed_data(self):
parser = ImdbParser()
parser.parse('tt0114814')
assert parser.actors == {
'nm0000592': 'Pete Postlethwaite',
'nm0261452': 'Christine Estabrook',
'nm0000751': 'Suzy Amis',
'nm0000286': 'Stephen Baldwin',
'nm0000445': 'Dan Hedaya',
'nm0800339': 'Phillipe Simon',
'nm0002064': 'Giancarlo Esposito',
'nm0001590': 'Chazz Palminteri',
'nm0000321': 'Gabriel Byrne',
'nm0790436': 'Jack Shearer',
'nm0000228': 'Kevin Spacey',
'nm0001629': 'Kevin Pollak',
'nm0107808': 'Carl Bressler',
'nm0001125': 'Benicio Del Toro',
'nm0000860': 'Paul Bartel',
}, 'Actors not parsed correctly'
assert parser.directors == {'nm0001741': 'Bryan Singer'}, 'Directors not parsed correctly'
print(parser.genres)
assert len(set(parser.genres).intersection([u'crime', u'mystery', u'thriller'])) == len(
[u'crime', u'mystery', u'thriller']
), 'Genres not parsed correctly'
assert parser.imdb_id == 'tt0114814', 'ID not parsed correctly'
assert (
len(set(parser.languages).intersection(['english', 'hungarian', 'spanish', 'french']))
== 4
), 'Languages not parsed correctly'
assert parser.mpaa_rating == 'R', 'Rating not parsed correctly'
assert parser.name == 'The Usual Suspects', 'Name not parsed correctly'
assert parser.photo, 'Photo not parsed correctly'
assert parser.plot_outline == (
'Following a truck hijack in New York, five conmen are arrested and brought together for questioning. '
'As none of them are guilty, they plan a revenge operation against the police. The operation goes well, '
'but then the influence of a legendary mastermind criminal called Keyser S\xf6ze is felt. It becomes '
'clear that each one of them has wronged S\xf6ze at some point and must pay back now. The payback job '
'leaves 27 men dead in a boat explosion, but the real question arises now: Who actually is Keyser S\xf6ze?'
), 'Plot outline not parsed correctly'
assert 8.0 < parser.score < 9.0, 'Score not parsed correctly'
assert parser.url == 'https://www.imdb.com/title/tt0114814/', 'URL not parsed correctly'
assert 400000 < parser.votes < 1000000, 'Votes not parsed correctly'
assert parser.year == 1995, 'Year not parsed correctly'