使用哈工大LTP进行文本命名实体识别并保存到txt

需求说明：
（1）将计算机本地文档集中的文本进行分词、词性标注，最后进行命名实体识别。
（2）将（1）中处理结果保存到本地txt文件中。

技术选择：
本需求的实现使用了哈工大的pyltp，如果你对ltp还不太了解，请点击这里或者去哈工大语言云官网了解相关内容。

完整代码展示：

# -*- coding: utf-8 -*-
import os
import jieba

LTP_DATA_DIR = 'D:\pyprojects\LTP\ltp_data'  # ltp模型目录的路径
cws_model_path = os.path.join(LTP_DATA_DIR, 'cws.model')  # 分词模型路径，模型名称为`cws.model`
pos_model_path = os.path.join(LTP_DATA_DIR, 'pos.model')  # 词性标注模型路径，模型名称为`pos.model`
ner_model_path = os.path.join(LTP_DATA_DIR, 'ner.model')  # 命名实体识别模型路径，模型名称为`ner.model`
par_model_path = os.path.join(LTP_DATA_DIR, 'parser.model')  # 依存句法分析模型路径，模型名称为`parser.model`
srl_model_path = os.path.join(LTP_DATA_DIR, 'srl')  # 语义角色标注模型目录路径，模型目录为`srl`。注意该模型路径是一个目录，而不是一个文件。

from pyltp import SentenceSplitter
from pyltp import Segmentor
from pyltp import Postagger
from pyltp import NamedEntityRecognizer
from pyltp import Parser
from pyltp import SementicRoleLabeller

#创建停用词表
def stopwordslist(filepath):
    stopwords = [line.strip() for line in open(filepath, 'r', encoding='utf-8').readlines()]
    return stopwords


# 分句，也就是将一片文本分割为独立的句子
def sentence_splitter(sentence):
    sents = SentenceSplitter.split(sentence)  # 分句
    print('\n'.join(sents))


# 分词
def segmentor(sentence):
    segmentor = Segmentor()  # 初始化实例
    segmentor.load(cws_model_path)  # 加载模型
    #segmentor.load_with_lexicon('cws_model_path', 'D:\pyprojects\LTP\ltp_data\dict.txt') #加载模型   使用用户自定义字典的高级分词
    words = segmentor.segment(sentence)  # 分词
    # 默认可以这样输出
   # print('/'.join(words))
    # 可以转换成List 输出
    words_list = list(words)
    segmentor.release()  # 释放模型
    return words_list


# 词性标注
def posttagger(words):
    postagger = Postagger()  # 初始化实例
    postagger.load(pos_model_path)  # 加载模型
    postags = postagger.postag(words)  # 词性标注
    #for word, tag in zip(words, postags):
     #   print(word + '/' + tag)
    postagger.release()  # 释放模型
    return postags


# 命名实体识别
def ner(words, postags):
    recognizer = NamedEntityRecognizer()  # 初始化实例
    recognizer.load(ner_model_path)  # 加载模型
    netags = recognizer.recognize(words, postags)  # 命名实体识别
    #for word, ntag in zip(words, netags):
     #   print(word + '/' + ntag)
    recognizer.release()  # 释放模型
    return netags

stopwords = stopwordslist('D:/2181729/stop_words.txt')
final = ''
f1=open('D:/2181729/nerfcdata/30.txt','w', encoding='UTF-8')
with open('D:/2181729/data/30.txt', 'r', encoding='UTF-8') as f:

       for line in f:
           segs = jieba.cut(line, cut_all=False)
           for seg in segs:
              if seg not in stopwords:
                 final += seg

words = segmentor(final)
postags = posttagger(words)
netags = ner(words,postags)

tags = []
dict = []

for word, ntag in zip(words, netags):
    if(ntag != 'O'):#过滤非命名实体
        tags.append(ntag)
        if (ntag not in dict):
             dict.append(ntag)
       # print(word + '/' + ntag)
        f1.write(word + ':' + ntag + '\r\n')


for tag in dict:
    num = tags.count(tag)
    print(tag + ":"+str(num))
    f1.write(tag + ":"+str(num) + '\r\n')
f1.close()

效果展示：

参考：
https://blog.csdn.net/informationscience/article/details/76850652