def parse_sentence(self, s):
keywords = []
# Lemmatize sentence and only keep verbs, nouns, dates and PTs
l = Lemmatizer()
lemmas = l.lemmatize(s)
lemmas = l.filter(lemmas, ['V', 'N', 'W', 'PT'])
# Normalize lemmas
for l in lemmas:
if l['tag'] == 'W':
norm_lemma = l['lemma']
else:
norm_lemma = self.normalize(l['lemma'])
if len(norm_lemma) > 0 and norm_lemma not in ignore_lemmas:
keywords.append(norm_lemma)
self.vprint("Keywords: ", keywords)
return [self.crawler.getwordid(word) for word in keywords]
def parse_sentence(self, s):
keywords = []
# Lemmatize sentence and only keep verbs, nouns, dates and PTs
l = Lemmatizer()
lemmas = l.lemmatize(s)
lemmas = l.filter(lemmas, ['V', 'N', 'W', 'PT'])
# Normalize lemmas
for l in lemmas:
if l['tag'] == 'W':
norm_lemma = l['lemma']
else:
norm_lemma = self.normalize(l['lemma'])
if len(norm_lemma) > 0 and norm_lemma not in ignore_lemmas:
keywords.append(norm_lemma)
self.vprint("Keywords: ", keywords)
return [self.crawler.getwordid(word) for word in keywords]
