def extract_tvseries(dom):
'''
Extract a list of highest ranking TV series from DOM (of IMDB page).
Each TV series entry should contain the following fields:
- TV Title
- Ranking
- Genres (comma separated if more than one)
- Actors/actresses (comma separated if more than one)
- Runtime (only a number!)
'''
# ADD YOUR CODE HERE TO EXTRACT THE ABOVE INFORMATION ABOUT THE
# HIGHEST RANKING TV-SERIES
# NOTE: FOR THIS EXERCISE YOU ARE ALLOWED (BUT NOT REQUIRED) TO IGNORE
# UNICODE CHARACTERS AND SIMPLY LEAVE THEM OUT OF THE OUTPUT.
series = []
# Loops over top 5 imdb series
for index in dom.by_tag("tr.even detailed")[:5]:
actors = []
genres = []
serie = []
# Extracts the required fields of the html
for td in index.by_tag("td.number")[:1]:
ranking = unicode(plaintext(td.content)) # Extract ranking
for td in index.by_tag("td.title")[:1]:
for a in td.by_tag("a")[:1]:
title = unicode(plaintext(a.content)) # Extract title
for span in td.by_tag("span.credit")[:1]:
for a in span.by_tag("a"):
actors.append(unicode(plaintext(a.content))) # Extract actors
for span in td.by_tag("span.genre")[:1]:
for a in span.by_tag("a"):
genres.append(unicode(plaintext(a.content))) # Extract genres
for span in td.by_tag("span.runtime")[:1]:
runtime = unicode(plaintext(span.content)) # Extract runtime with minute
runtime_split = split_string(runtime, ' ') # Split number from minute
runtime_num = runtime_split[0]
# append required fields to serie list
serie.append(title)
serie.append(ranking)
serie.append(genres)
serie.append(actors)
serie.append(runtime_num)
# appends serie to series
series.append(serie)
return series
def test_normal(self):
self.assertEqual(split_string('abacadabra', 'b'), ['a', 'acada', 'ra'])
self.assertEqual(split_string('aabbaa', 'b'), ['aa', 'aa'])
self.assertEqual(split_string('abacadabra', 'ab'), ['c', 'd', 'r'])
def test_empty(self):
self.assertEqual(split_string('', ''), [])
self.assertEqual(split_string('', 'abc'), [])
self.assertEqual(split_string('abc', ''), ['abc'])
def test_dumb(self):
# Tests for the number of parameters
with self.assertRaises(TypeError):
split_string()
with self.assertRaises(TypeError):
split_string('')
def test_normal(self):
self.assertEqual(split_string('abacadabra', 'b'), ['a', 'acada', 'ra'])
self.assertEqual(split_string('aabbaa', 'b'), ['aa', 'aa'])
self.assertEqual(split_string('abacadabra', 'ab'), ['c', 'd', 'r'])
def test_empty(self):
self.assertEqual(split_string('', ''), [])
self.assertEqual(split_string('', 'abc'), [])
self.assertEqual(split_string('abc', ''), ['abc'])
def test_dumb(self):
# Tests for the number of parameters
with self.assertRaises(TypeError):
split_string()
with self.assertRaises(TypeError):
split_string('')
