导演：猪股隆一 長沼誠 鈴木勇馬
主演：芦田爱菜 铃木梨央 渡边木实 樱田日和 三浦翔平 木村文乃 大后寿
关键词：剧情
"""
sents = nlprocessor.sentence_split(text)
for sent in sents:
"""
sents = nlprocessor.sentence_split(text)
for sent in sents:
print(sent)
print()
seg_list = nlprocessor.jieba_pseg_cut(text)
for seg in seg_list:
print(seg.word, seg.flag)
print()
tokens = nlprocessor.sentence_tokenize_and_pos(text)
for tok in tokens:
print(tok.word, tok.pos, tok.flag)
print()
tokens = nlprocessor.sentence_tokenize_and_pos(text, pos_type='e')
for tok in tokens:
print(tok.word, tok.pos, tok.flag)
print()
tokens = nlprocessor.sentence_tokenize_and_pos(text, pos_type='d')
for tok in tokens:
print(tok.word, tok.pos, tok.flag)
print()
tokens = nlprocessor.sentence_tokenize_and_pos(text, pos_type='penn')
for tok in tokens:
print(tok.word, tok.pos, tok.flag)
print()
tokens = nlprocessor.sentence_tokenize_and_pos(text, pos_type='pt')
for tok in tokens:
print(tok.word, tok.pos, tok.flag)
print()
tokens = nlprocessor.sentence_tokenize_and_pos(text, pos_type='u')
for tok in tokens:
print(tok.word, tok.pos, tok.flag)
print()
tokens = nlprocessor.sentence_tokenize_and_pos(text, pos_type='nltk')
for tok in tokens:
print(tok.word, tok.pos, tok.flag)
print()
tokens = nlprocessor.sentence_tokenize_and_pos(text, pos_type='hmm')
for tok in tokens:
print(tok.word, tok.pos, tok.flag)
print()
tokens = nlprocessor.sentence_tokenize_and_pos(text, pos_type='2th')
for tok in tokens:
print(tok.word, tok.pos, tok.flag)
print()
tokens = nlprocessor.sentence_tokenize_and_pos(text, pos_type='nr')
for tok in tokens:
print(tok.word, tok.pos, tok.flag)
print()
tokens = nlprocessor.sentence_tokenize_and_pos(text, pos_type='ctb')
for tok in tokens:
print(tok.word, tok.pos, tok.flag)
print()
tokens = nlprocessor.sentence_tokenize_and_pos(text, pos_type='pku')
for tok in tokens:
print(tok.word, tok.pos, tok.flag)
print()
tokens = nlprocessor.sentence_tokenize_and_pos(text, pos_type='seg')
for tok in tokens:
print(tok.word, tok.pos, tok.flag)
print()
tokens = nlprocessor.sentence_tokenize_and_pos(text, pos_type='f')
for tok in tokens:
print(tok.word, tok.pos, tok.flag)
print()
tokens = nlprocessor.sentence_tokenize_and_pos(text, pos_type='snownlp')
for tok in tokens:
print(tok.word, tok.pos, tok.flag)
print()
tokens = nlprocessor.sentence_tokenize_and_pos(text, pos_type='kashgari')
for tok in tokens:
print(tok.word, tok.pos, tok.flag)
print()
tokens = nlprocessor.sentence_tokenize_and_pos(text, pos_type='thulac')
for tok in tokens:
print(tok.word, tok.pos, tok.flag)
print()
tokens = nlprocessor.sentence_tokenize_and_pos(text, pos_type='s')
for tok in tokens:
print(tok.word, tok.pos, tok.flag)
print()
keywords = nlprocessor.extract_keyword_and_pos(text, pos_type='thulac')
for kw in keywords:
print(kw.word, kw.pos, kw.flag)
print()
hashtags = nlprocessor.extract_hashtag_and_pos(text, pos_type='thulac')
for tag in hashtags:
print(tag.word, tag.pos, tag.flag)
print()
expressions = nlprocessor.extract_expression_and_pos(text, pos_type='thulac')
for expr in expressions:
print(expr.word, expr.pos, expr.flag)
print()
abbrs = nlprocessor.extract_abbreviation_and_pos(text, pos_type='thulac')
for abbr in abbrs:
print(abbr.word, abbr.pos, abbr.flag)
print()
tokens = nlprocessor.tokenize_and_pos(text, pos_type='thulac')
for tok in tokens:
print(tok.word, tok.pos, tok.flag)
print()
tokens = nlprocessor.tokenize_and_pos(text, pos_type='thulac', topk=3)
for tok in tokens:
print(tok.word, tok.pos, tok.flag)
详情
更多影视：
影林影视
