def process_text(text):
"""
Tries to get the summary, intro, keywords
Return is_valid indicating if text was okay
:param text:
:param title:
:return:
"""
is_valid = True
keywords = []
summarizer = Summarizer(text)
try:
summary = summarizer.summarize()
keywords = summarizer.keywords(number_keywords=number_keywords)
phrases = summarizer.key_noun_phrases(
number_noun_phrases=number_noun_phrase)
phrases = [phrase.replace(" ", "_") for phrase in phrases]
keywords = keywords + phrases
except SummaryException:
summary = [""]
is_valid = False
summary = " ".join(summary)
return is_valid, summary, keywords
def test_dirty_text_summary(self):
test_text = '最新 科技 http: 新闻和创业 公司信息 ”∆˙∫˚˜ ˜µ∆∫˙© ∆∆˚µ˚' + self.test_text[
0]
summarizer = Summarizer(test_text)
summarizer.parse()
text = summarizer.summarize()
keywords = summarizer.keywords()
key_noun_phrases = summarizer.key_noun_phrases()
self.assertEqual(text, [
'This is happening in the city of Tianjin, about an hours drive south of '
'Beijing, within a gleaming office building that belongs to iFlytek, one of '
'Chinas rapidly rising artificial-intelligence companies.',
'Beyond guarded gates, inside a glitzy showroom, the US president is on a '
'large TV screen heaping praise on the Chinese company.',
'This is happening in the city of Tianjin, about an hours drive south of '
'Beijing, within a gleaming office building that belongs to iFlytek, one of '
'Chinas rapidly rising artificial-intelligence companies.',
'Beyond guarded gates, inside a glitzy showroom, the US president is on a '
'large TV screen heaping praise on the Chinese company.',
'However, AI itself could change all that.',
'A more advanced chip industry will help China realize its dream of becoming '
'a true technology superpower.',
'China wont be playing catch-up with these new chips, as it has done with '
'more conventional chips for decades.',
'Chinas chip ambitions have geopolitical implications, too.',
'A successful chip industry would make China more economically competitive '
'and independent.'
])
self.assertEqual(keywords, [
'chip', 'china', 'ai', 'company', 'iflytek', 'technology',
'algorithm', 'microchip', 'time', 'silicon', 'advanced',
'industry', 'beijing', 'belongs', 'inside'
])
self.assertEqual(key_noun_phrases, [
'chinese company', 'tsinghua unigroup', 'donald trump',
'gleaming office building', 'artificial-intelligence companies'
])