def test_word_embedding_extractor():
pytest.importorskip('gensim')
stims = [TextStim(text='this'), TextStim(text='sentence')]
ext = WordEmbeddingExtractor(join(TEXT_DIR, 'simple_vectors.bin'),
binary=True)
result = merge_results(ext.transform(stims),
extractor_names='multi',
format='wide')
assert ('WordEmbeddingExtractor', 'embedding_dim99') in result.columns
assert np.allclose(0.0010911,
result[('WordEmbeddingExtractor', 'embedding_dim0')][0])
unk = TextStim(text='nowaythisinvocab')
result = ext.transform(unk).to_df()
assert result['embedding_dim10'][0] == 0.0
ones = np.ones(100)
ext = WordEmbeddingExtractor(join(TEXT_DIR, 'simple_vectors.bin'),
binary=True,
unk_vector=ones)
result = ext.transform(unk).to_df()
assert result['embedding_dim10'][0] == 1.0
ext = WordEmbeddingExtractor(join(TEXT_DIR, 'simple_vectors.bin'),
binary=True,
unk_vector='random')
result = ext.transform(unk).to_df()
assert result['embedding_dim10'][0] <= 1.0
assert result['embedding_dim10'][0] >= -1.0
ext = WordEmbeddingExtractor(join(TEXT_DIR, 'simple_vectors.bin'),
binary=True,
unk_vector='nothing')
result = ext.transform(unk).to_df()
assert result['embedding_dim10'][0] == 0.0
def test_word_embedding_extractor():
pytest.importorskip('gensim')
stims = [TextStim(text='this'), TextStim(text='sentence')]
ext = WordEmbeddingExtractor(join(TEXT_DIR, 'simple_vectors.bin'),
binary=True)
result = merge_results(ext.transform(stims))
assert ('WordEmbeddingExtractor', 'embedding_dim99') in result.columns
assert 0.001091 in result[('WordEmbeddingExtractor', 'embedding_dim0')]
def test_vader_sentiment_extractor():
stim = TextStim(join(TEXT_DIR, 'scandal.txt'))
ext = VADERSentimentExtractor()
result = ext.transform(stim).to_df()
assert result['sentiment_neu'][0] == 0.752
stim2 = TextStim(text='VADER is smart, handsome, and funny!')
result2 = ext.transform(stim2).to_df()
assert result2['sentiment_pos'][0] == 0.752
assert result2['sentiment_neg'][0] == 0.0
assert result2['sentiment_neu'][0] == 0.248
assert result2['sentiment_compound'][0] == 0.8439
def extract_visual_semantics(visual_events, glove=True):
res = pd.DataFrame.from_csv(visual_events)
onsets = res['onset']
durations = res['duration']
res = res.drop(['onset', 'duration', 'order', 'object_id'], axis=1)
words = res.apply(lambda x: list(res.columns[x.values.astype('bool')]),
axis=1)
texts = []
for tags, o, d in zip(words, onsets, durations):
for w in tags:
# Slicing here to get rid of b''
texts.append(TextStim(text=w[2:-1], onset=o, duration=d))
if glove:
ext = WordEmbeddingExtractor(GLOVE_PATH, binary=False)
out = 'events/visual_semantic_events.csv'
else:
ext = WordEmbeddingExtractor(WORD2VEC_PATH, binary=True)
out = 'events/visual_glove_events.csv'
results = ext.transform(texts)
res = merge_results(results,
metadata=False,
flatten_columns=True,
format='long')
res = res.drop(['object_id', 'order', 'duration'], axis=1)
res = res.groupby('onset').sum().reset_index()
res['duration'] = durations
res.rename(columns={
'value': 'modulation',
'feature': 'trial_type'
},
inplace=True)
res.to_csv(out)
def test_multiple_text_filters():
stim = TextStim(text='testing the filtering features')
filt1 = TokenizingFilter()
filt2 = WordStemmingFilter()
stemmed_tokens = filt2.transform(filt1.transform(stim))
full_text = ' '.join([s.text for s in stemmed_tokens])
assert full_text == 'test the filter featur'
def test_tfhub_text():
stim = TextStim(join(TEXT_DIR, 'scandal.txt'))
ext = TFHubTextExtractor(SENTENC_URL, output_key=None)
df = ext.transform(stim).to_df()
assert all([f'feature_{i}' in df.columns for i in range(512)])
true = hub.KerasLayer(SENTENC_URL)([stim.text])[0, 10].numpy()
assert np.isclose(df['feature_10'][0], true)
def test_word_stemming_filter():
stim = ComplexTextStim(join(TEXT_DIR, 'sample_text.txt'),
columns='to',
default_duration=1)
# With all defaults (porter stemmer)
filt = WordStemmingFilter()
assert isinstance(filt.stemmer, nls.PorterStemmer)
stemmed = filt.transform(stim)
stems = [s.text for s in stemmed]
target = ['some', 'sampl', 'text', 'for', 'test', 'annot']
assert stems == target
# Try a different stemmer
filt = WordStemmingFilter(stemmer='snowball', language='english')
assert isinstance(filt.stemmer, nls.SnowballStemmer)
stemmed = filt.transform(stim)
stems = [s.text for s in stemmed]
assert stems == target
# Handles StemmerI stemmer
stemmer = nls.SnowballStemmer(language='english')
filt = WordStemmingFilter(stemmer=stemmer)
stemmed = filt.transform(stim)
stems = [s.text for s in stemmed]
assert stems == target
# Fails on invalid values
with pytest.raises(ValueError):
filt = WordStemmingFilter(stemmer='nonexistent_stemmer')
# Try a long text stim
stim2 = TextStim(text='theres something happening here')
filt = WordStemmingFilter()
assert filt.transform(stim2).text == 'there someth happen here'
def test_indico_api_text_extractor():
ext = IndicoAPITextExtractor(api_key=os.environ['INDICO_APP_KEY'],
models=['emotion', 'personality'])
# With ComplexTextStim input
srtfile = join(get_test_data_path(), 'text', 'wonderful.srt')
srt_stim = ComplexTextStim(srtfile, onset=4.2)
result = merge_results(ext.transform(srt_stim), extractor_names=False)
outdfKeysCheck = {
'onset', 'duration', 'order', 'object_id', 'emotion_anger',
'emotion_fear', 'emotion_joy', 'emotion_sadness', 'emotion_surprise',
'personality_openness', 'personality_extraversion',
'personality_agreeableness', 'personality_conscientiousness'
}
meta_columns = {'source_file', 'history', 'class', 'filename'}
assert set(result.columns) - set(['stim_name'
]) == outdfKeysCheck | meta_columns
assert result['onset'][1] == 92.622
# With TextStim input
ts = TextStim(text="It's a wonderful life.")
result = ext.transform(ts).to_df(object_id=True)
assert set(result.columns) == outdfKeysCheck
assert len(result) == 1
def test_validation_levels(caplog):
cache_default = config.get_option('cache_transformers')
config.set_option('cache_transformers', False)
ext = BrightnessExtractor()
stim = TextStim(text='hello world')
with pytest.raises(TypeError):
ext.transform(stim)
res = ext.transform(stim, validation='warn')
log_message = caplog.records[0].message
assert log_message == (
"Transformers of type BrightnessExtractor can "
"only be applied to stimuli of type(s) <class 'pliers"
".stimuli.image.ImageStim'> (not type TextStim), and no "
"applicable Converter was found.")
assert not res
res = ext.transform(stim, validation='loose')
assert not res
stim2 = ImageStim(join(get_test_data_path(), 'image', 'apple.jpg'))
res = ext.transform([stim, stim2], validation='loose')
assert len(res) == 1
assert np.isclose(res[0].to_df()['brightness'][0], 0.88784294, 1e-5)
config.set_option('cache_transformers', cache_default)
def test_spacy_token_extractor():
stim = TextStim(text='This is a test.')
ext = SpaCyExtractor(extractor_type='token')
assert ext.model is not None
ext2 = SpaCyExtractor(model='en_core_web_sm')
assert isinstance(ext2.model, spacy.lang.en.English)
result = ext.transform(stim).to_df()
assert result['text'][0] == 'This'
assert result['lemma_'][0].lower() == 'this'
assert result['pos_'][0] == 'DET'
assert result['tag_'][0] == 'DT'
assert result['dep_'][0] == 'nsubj'
assert result['shape_'][0] == 'Xxxx'
assert result['is_alpha'][0] == 'True'
assert result['is_stop'][0] == 'True'
assert result['is_punct'][0] == 'False'
assert result['is_ascii'][0] == 'True'
assert result['is_digit'][0] == 'False'
assert result['sentiment'][0] == '0.0'
assert result['text'][1] == 'is'
assert result['lemma_'][1].lower() == 'be'
assert result['pos_'][1] == 'VERB'
assert result['tag_'][1] == 'VBZ'
assert result['dep_'][1] == 'ROOT'
assert result['shape_'][1] == 'xx'
assert result['is_alpha'][1] == 'True'
assert result['is_stop'][1] == 'True'
assert result['is_punct'][1] == 'False'
assert result['is_ascii'][1] == 'True'
assert result['is_digit'][1] == 'False'
assert result['sentiment'][1] == '0.0'
assert result['text'][2] == 'a'
assert result['lemma_'][2].lower() == 'a'
assert result['pos_'][2] == 'DET'
assert result['tag_'][2] == 'DT'
assert result['dep_'][2] == 'det'
assert result['shape_'][2] == 'x'
assert result['is_alpha'][2] == 'True'
assert result['is_stop'][2] == 'True'
assert result['is_punct'][2] == 'False'
assert result['is_ascii'][2] == 'True'
assert result['is_digit'][2] == 'False'
assert result['sentiment'][2] == '0.0'
assert result['text'][3] == 'test'
assert result['lemma_'][3].lower() == 'test'
assert result['pos_'][3] == 'NOUN'
assert result['tag_'][3] == 'NN'
assert result['dep_'][3] == 'attr'
assert result['shape_'][3] == 'xxxx'
assert result['is_alpha'][3] == 'True'
assert result['is_stop'][3] == 'False'
assert result['is_punct'][3] == 'False'
assert result['is_ascii'][3] == 'True'
assert result['is_digit'][3] == 'False'
assert result['sentiment'][3] == '0.0'
def test_indico_api_text_extractor():
ext = IndicoAPITextExtractor(api_key=os.environ['INDICO_APP_KEY'],
models=['emotion', 'personality'])
# With ComplexTextStim input
srtfile = join(get_test_data_path(), 'text', 'wonderful.srt')
srt_stim = ComplexTextStim(srtfile, onset=4.2)
result = ext.transform(srt_stim).to_df()
outdfKeysCheck = set([
'onset',
'duration',
'emotion_anger',
'emotion_fear',
'emotion_joy',
'emotion_sadness',
'emotion_surprise',
'personality_openness',
'personality_extraversion',
'personality_agreeableness',
'personality_conscientiousness'])
assert set(result.columns) == outdfKeysCheck
assert result['onset'][1] == 92.622
# With TextStim input
ts = TextStim(text="It's a wonderful life.")
result = ext.transform(ts).to_df()
assert set(result.columns) == outdfKeysCheck
assert len(result) == 1
def clean_transcript(input_transcript, input_media, onset=None, offset=None):
stim = load_stims([input_media])[0]
if not isinstance(stim, AudioStim):
conv = VideoToAudioConverter()
stim = conv.transform(stim)
input_media = '/tmp/input_audio.wav'
stim.save(input_media)
_, extension = splitext(input_transcript)
clean_transcript = '/tmp/clean_transcript.txt'
with open(clean_transcript, 'w') as new_file:
if extension == 'srt':
txt = ComplexTextStim(input_transcript)
for el in txt.elements:
_clean_save(el.text, new_file, el.onset, el.duration)
else: # Treat as a singe block of text
if onset is None or offset is None:
raise Exception("Onset and offset must be declared")
txt = TextStim(input_transcript)
_clean_save(txt.text, new_file, onset, stim.duration - offset)
return clean_transcript, input_media
def test_predefined_dictionary_extractor():
stim = TextStim(text='enormous')
td = PredefinedDictionaryExtractor(['aoa/Freq_pm'])
result = td.transform(stim).to_df()
assert result.shape == (1, 5)
assert 'aoa_Freq_pm' in result.columns
assert np.isclose(result['aoa_Freq_pm'][0], 10.313725, 1e-5)
def test_dictionary_extractor():
td = DictionaryExtractor(join(TEXT_DIR, 'test_lexical_dictionary.txt'),
variables=['length', 'frequency'])
assert td.data.shape == (7, 2)
stim = TextStim(text='annotation')
result = td.transform(stim).to_df()
assert np.isnan(result['onset'][0])
assert 'length' in result.columns
assert result['length'][0] == 10
stim2 = TextStim(text='some')
result = td.transform(stim2).to_df()
assert np.isnan(result['onset'][0])
assert 'frequency' in result.columns
assert np.isnan(result['frequency'][0])
def test_token_removal_filter():
stim = TextStim(text='this is not a very long sentence')
filt = TokenRemovalFilter()
assert filt.transform(stim).text == 'long sentence'
filt2 = TokenRemovalFilter(tokens=['a', 'the', 'is'])
assert filt2.transform(stim).text == 'this not very long sentence'
stim2 = TextStim(text='More. is Real, sentence that\'ll work')
try:
nltk.data.find('corpora/stopwords')
except LookupError:
nltk.download('stopwords')
from nltk.corpus import stopwords
tokens = set(stopwords.words('english')) | set(string.punctuation)
filt3 = TokenRemovalFilter(tokens=tokens)
assert filt3.transform(stim2).text == 'More Real sentence \'ll work'
def test_text_length_extractor():
stim = TextStim(text='hello world', onset=4.2, duration=1)
ext = LengthExtractor()
result = ext.transform(stim).to_df()
assert 'text_length' in result.columns
assert result['text_length'][0] == 11
assert result['onset'][0] == 4.2
assert result['duration'][0] == 1
def test_word_stemming_filter():
stim = ComplexTextStim(join(TEXT_DIR, 'sample_text.txt'),
columns='to',
default_duration=1)
# With all defaults (porter stemmer)
filt = WordStemmingFilter()
assert isinstance(filt.stemmer, nls.PorterStemmer)
stemmed = filt.transform(stim)
stems = [s.text for s in stemmed]
target = ['some', 'sampl', 'text', 'for', 'test', 'annot']
assert stems == target
# Try a different stemmer
filt = WordStemmingFilter(stemmer='snowball', language='english')
assert isinstance(filt.stemmer, nls.SnowballStemmer)
stemmed = filt.transform(stim)
stems = [s.text for s in stemmed]
assert stems == target
# Handles StemmerI stemmer
stemmer = nls.SnowballStemmer(language='english')
filt = WordStemmingFilter(stemmer=stemmer)
stemmed = filt.transform(stim)
stems = [s.text for s in stemmed]
assert stems == target
# Try lemmatization filter
try:
nltk.find('taggers/universal_tagset')
except LookupError:
nltk.download('universal_tagset')
try:
nltk.find('corpora/wordnet')
except LookupError:
nltk.download('wordnet')
stim = ComplexTextStim(text='These are tests for Stemming filters')
filt = WordStemmingFilter(stemmer='wordnet')
lemmatized = filt.transform(stim)
lemmas = [l.text for l in lemmatized]
target = ['these', 'be', 'test', 'for', 'stem', 'filter']
assert lemmas == target
# Try case sensitive
filt = WordStemmingFilter(stemmer='wordnet', case_sensitive=True)
lemmatized = filt.transform(stim)
lemmas = [l.text for l in lemmatized]
target = ['These', 'be', 'test', 'for', 'Stemming', 'filter']
assert lemmas == target
# Fails on invalid values
with pytest.raises(ValueError):
filt = WordStemmingFilter(stemmer='nonexistent_stemmer')
# Try a long text stim
stim2 = TextStim(text='theres something happening here')
filt = WordStemmingFilter()
assert filt.transform(stim2).text == 'there someth happen here'
def test_metric_er_as_stim():
stim = TextStim(text='This is a test')
ext_sent = VADERSentimentExtractor()
ext_metric = MetricExtractor(
functions='numpy.sum',
subset_idx=[f'sentiment_{d}' for d in ['neg', 'pos', 'neu']])
r = ext_metric.transform(ext_sent.transform(stim))
df = merge_results(r, extractor_names=False)
assert np.isclose(df['sum'][0], 1)
def test_tfhub_text_one_feature():
stim = TextStim(join(TEXT_DIR, 'scandal.txt'))
cstim = ComplexTextStim(join(TEXT_DIR, 'wonderful.txt'))
ext = TFHubTextExtractor(GNEWS_URL, output_key=None, features='embedding')
df = merge_results(ext.transform(cstim), extractor_names=False)
assert df.shape[0] == len(cstim.elements)
true = hub.KerasLayer(GNEWS_URL)([cstim.elements[3].text])[0, 2].numpy()
assert np.isclose(df['embedding'][3][2], true)
with pytest.raises(ValueError) as err:
TFHubTextExtractor(GNEWS_URL, output_key='key').transform(stim)
assert 'not a dictionary' in str(err.value)
def test_google_language_api_category_extractor():
verify_dependencies(['googleapiclient'])
ext = GoogleLanguageAPITextCategoryExtractor()
stim = TextStim(join(TEXT_DIR, 'sample_text_with_entities.txt'))
result = ext.transform(stim).to_df(timing=False, object_id='auto')
assert result.shape == (1, 4)
assert 'category_/Computers & Electronics' in result.columns
assert result['category_/Computers & Electronics'][0] > 0.3
assert 'category_/News' in result.columns
assert result['category_/News'][0] > 0.3
assert result['language'][0] == 'en'
def test_google_language_api_entity_sentiment_extractor():
verify_dependencies(['googleapiclient'])
ext = GoogleLanguageAPIEntitySentimentExtractor()
stim = TextStim(join(TEXT_DIR, 'sample_text_with_entities.txt'))
result = ext.transform(stim).to_df(timing=False, object_id='auto')
# Produces same result as entity extractor with sentiment columns
assert result.shape == (10, 11)
assert result['text'][8] == 'phones'
assert result['type'][8] == 'CONSUMER_GOOD'
assert 'sentiment_score' in result.columns
assert result['sentiment_score'][8] > 0.6 # 'love their ... phones'
def test_multiple_text_filters():
stim = TextStim(text='testing the filtering features')
filt1 = TokenizingFilter()
filt2 = WordStemmingFilter()
stemmed_tokens = filt2.transform(filt1.transform(stim))
full_text = ' '.join([s.text for s in stemmed_tokens])
assert full_text == 'test the filter featur'
stim = TextStim(text='ARTICLE ONE: Rights')
g = Graph()
g.add_node(LowerCasingFilter())
filt1 = LowerCasingFilter()
filt2 = PunctuationRemovalFilter()
filt3 = TokenizingFilter()
final_texts = filt3.transform(filt2.transform(filt1.transform(stim)))
assert len(final_texts) == 3
assert final_texts[0].text == 'article'
assert final_texts[0].order == 0
assert final_texts[1].text == 'one'
assert final_texts[2].text == 'rights'
assert final_texts[2].order == 2
def test_vectorizer_extractor():
pytest.importorskip('sklearn')
stim = TextStim(join(TEXT_DIR, 'scandal.txt'))
result = TextVectorizerExtractor().transform(stim).to_df()
assert 'woman' in result.columns
assert result['woman'][0] == 3
from sklearn.feature_extraction.text import TfidfVectorizer
custom_vectorizer = TfidfVectorizer()
ext = TextVectorizerExtractor(vectorizer=custom_vectorizer)
stim2 = TextStim(join(TEXT_DIR, 'simple_text.txt'))
result = merge_results(ext.transform([stim, stim2]))
assert ('TextVectorizerExtractor', 'woman') in result.columns
assert 0.129568189476 in result[('TextVectorizerExtractor', 'woman')]
ext = TextVectorizerExtractor(vectorizer='CountVectorizer',
analyzer='char_wb',
ngram_range=(2, 2))
result = ext.transform(stim).to_df()
assert 'wo' in result.columns
assert result['wo'][0] == 6
def test_google_language_api_extractor():
verify_dependencies(['googleapiclient'])
ext = GoogleLanguageAPIExtractor(features=['classifyText',
'extractEntities'])
stim = TextStim(text='hello world')
with pytest.raises(googleapiclient.errors.HttpError):
# Should fail because too few tokens
ext.transform(stim)
stim = TextStim(join(TEXT_DIR, 'scandal.txt'))
result = ext.transform(stim).to_df(timing=False, object_id='auto')
assert result.shape == (43, 10)
assert 'category_/Books & Literature' in result.columns
assert result['category_/Books & Literature'][0] > 0.5
irene = result[result['text'] == 'Irene Adler']
assert (irene['type'] == 'PERSON').all()
assert not irene['metadata_wikipedia_url'].isna().any()
# Document row shouldn't have entity features, and vice versa
assert np.isnan(result.iloc[0]['text'])
assert np.isnan(result.iloc[1]['category_/Books & Literature']).all()
def test_google_language_api_sentiment_extractor():
verify_dependencies(['googleapiclient'])
ext = GoogleLanguageAPISentimentExtractor()
stim = TextStim(join(TEXT_DIR, 'scandal.txt'))
result = ext.transform(stim).to_df(timing=False, object_id='auto')
assert result.shape == (12, 7)
assert 'sentiment_magnitude' in result.columns
assert 'text' in result.columns
doc_sentiment = result['sentiment_score'][11]
assert doc_sentiment < 0.3 and doc_sentiment > -0.3
assert result['begin_char_index'][7] == 565.0
assert result['end_char_index'][7] == 672.0
assert result['sentiment_magnitude'][7] > 0.6
def test_google_language_api_entity_extractor():
verify_dependencies(['googleapiclient'])
ext = GoogleLanguageAPIEntityExtractor()
stim = TextStim(join(TEXT_DIR, 'sample_text_with_entities.txt'))
result = ext.transform(stim).to_df(timing=False, object_id='auto')
assert result.shape == (10, 9)
assert result['text'][0] == 'Google'
assert result['type'][0] == 'ORGANIZATION'
assert result['salience'][0] > 0.0 and result['salience'][0] < 0.5
assert result['begin_char_index'][4] == 165.0
assert result['end_char_index'][4] == 172.0
assert result['text'][4] == 'Android'
assert result['type'][4] == 'CONSUMER_GOOD'
def test_save():
text_dir = join(get_test_data_path(), 'text')
complextext_stim = ComplexTextStim(join(text_dir, 'complex_stim_no_header.txt'),
columns='ot', default_duration=0.2)
text_stim = TextStim(text='hello')
video_stim = VideoStim(join(get_test_data_path(), 'video', 'small.mp4'))
audio_stim = AudioStim(join(get_test_data_path(), 'audio', 'crowd.mp3'))
image_stim = ImageStim(join(get_test_data_path(), 'image', 'apple.jpg'))
stims = [complextext_stim, text_stim, video_stim, audio_stim, image_stim]
for s in stims:
path = tempfile.mktemp() + s._default_file_extension
s.save(path)
assert exists(path)
os.remove(path)
def test_save():
cts_file = join(get_test_data_path(), 'text', 'complex_stim_no_header.txt')
complextext_stim = ComplexTextStim(cts_file,
columns='ot',
default_duration=0.2)
text_stim = TextStim(text='hello')
audio_stim = AudioStim(join(get_test_data_path(), 'audio', 'crowd.mp3'))
image_stim = ImageStim(join(get_test_data_path(), 'image', 'apple.jpg'))
# Video gives travis problems
stims = [complextext_stim, text_stim, audio_stim, image_stim]
for s in stims:
path = tempfile.mktemp() + s._default_file_extension
s.save(path)
assert exists(path)
os.remove(path)
def parse_textgrid(transcript_path):
with open(transcript_path) as f:
start_parse = False # Indicates we are on the 'word' portion of output
all_lines = f.readlines()
texts = []
for i, line in enumerate(all_lines):
if line == '\titem [2]:\n':
start_parse = True
if start_parse and line.startswith('\t\t\ti'):
onset = float(all_lines[i + 1].split()[-1])
duration = float(all_lines[i + 2].split()[-1]) - onset
text = str(all_lines[i + 3].split()[-1])[1:-1].lower()
if not (text == 'sp'): # Space/hesitation in audio
texts.append(
TextStim(text=text, onset=onset, duration=duration))
return texts
def test_remote_stims():
url = 'http://www.obamadownloads.com/videos/iran-deal-speech.mp4'
video = VideoStim(url=url)
assert video.fps == 12
url = 'http://www.bobainsworth.com/wav/simpsons/themodyn.wav'
audio = AudioStim(url=url)
assert round(audio.duration) == 3
url = 'https://www.whitehouse.gov/sites/whitehouse.gov/files/images/twitter_cards_potus.jpg'
image = ImageStim(url=url)
assert image.data.shape == (240, 240, 3)
url = 'https://github.com/tyarkoni/pliers/blob/master/README.md'
text = TextStim(url=url)
assert len(text.text) > 1
