Python中使用Stanford CoreNLP 出现端点加载错误

柔情只为你懂 2023-06-29 10:36 30阅读 0赞

步骤：

1.  下载 https://stanfordnlp.github.io/CoreNLP/，下载1，2， 将2放入下载的1文件夹中  
    ![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dhbnppX2FudGFuZw_size_16_color_FFFFFF_t_70]
2.  在终端进行安装： pip install stanfordcorenlp (如果安装在自己的某个环境下，先激活虚拟环境：conda activate myenv, 然后安装：pip install stanfordcorenlp)
3.  使用  
    `from stanfordcorenlp import StanfordCoreNLP`  
    `nlp = StanfordCoreNLP(r'/anaconda3/demo/demo/stanford-corenlp-full-2018-10-05/', port=9999, lang='zh')`
4.  调试：  
    当出现port 无效错误时， 注释掉节点选择的代码，并且给指定的端点

注释代码为：

# # If port not set, auto select
                # if self.port is None:
                # for port_candidate in range(9000, 65535):
                # if port_candidate not in [conn.laddr[1] for conn in psutil.net_connections()]:
                # self.port = port_candidate
                # break
                #
                # # Check if the port is in use
                # if self.port in [conn.laddr[1] for conn in psutil.net_connections()]:
                # raise IOError('Port ' + str(self.port) + ' is already in use.')

注释之后如下：

class StanfordCoreNLP:
        def __init__(self, path_or_host, port=9999, memory='4g', lang='en', timeout=1500, quiet=True,
                     logging_level=logging.WARNING):
            self.path_or_host = path_or_host
            self.port = port
            self.memory = memory
            self.lang = lang
            self.timeout = timeout
            self.quiet = quiet
            self.logging_level = logging_level
    
            logging.basicConfig(level=self.logging_level)
    
            # Check args
            self._check_args()
    
            if path_or_host.startswith('http'):
                self.url = path_or_host + ':' + str(port)
                logging.info('Using an existing server {}'.format(self.url))
            else:
    
                # Check Java
                if not subprocess.call(['java', '-version'], stdout=subprocess.PIPE, stderr=subprocess.STDOUT) == 0:
                    raise RuntimeError('Java not found.')
    
                # Check if the dir exists
                if not os.path.isdir(self.path_or_host):
                    raise IOError(str(self.path_or_host) + ' is not a directory.')
                directory = os.path.normpath(self.path_or_host) + os.sep
                self.class_path_dir = directory
    
                # Check if the language specific model file exists
                switcher = { 
                    'en': 'stanford-corenlp-[0-9].[0-9].[0-9]-models.jar',
                    'zh': 'stanford-chinese-corenlp-[0-9][0-9][0-9][0-9]-[0-9][0-9]-[0-9][0-9]-models.jar',
                    'ar': 'stanford-arabic-corenlp-[0-9][0-9][0-9][0-9]-[0-9][0-9]-[0-9][0-9]-models.jar',
                    'fr': 'stanford-french-corenlp-[0-9][0-9][0-9][0-9]-[0-9][0-9]-[0-9][0-9]-models.jar',
                    'de': 'stanford-german-corenlp-[0-9][0-9][0-9][0-9]-[0-9][0-9]-[0-9][0-9]-models.jar',
                    'es': 'stanford-spanish-corenlp-[0-9][0-9][0-9][0-9]-[0-9][0-9]-[0-9][0-9]-models.jar'
                }
                jars = { 
                    'en': 'stanford-corenlp-x.x.x-models.jar',
                    'zh': 'stanford-chinese-corenlp-yyyy-MM-dd-models.jar',
                    'ar': 'stanford-arabic-corenlp-yyyy-MM-dd-models.jar',
                    'fr': 'stanford-french-corenlp-yyyy-MM-dd-models.jar',
                    'de': 'stanford-german-corenlp-yyyy-MM-dd-models.jar',
                    'es': 'stanford-spanish-corenlp-yyyy-MM-dd-models.jar'
                }
                if len(glob.glob(directory + switcher.get(self.lang))) <= 0:
                    raise IOError(jars.get(
                        self.lang) + ' not exists. You should download and place it in the ' + directory + ' first.')
    
                # # If port not set, auto select
                # if self.port is None:
                # for port_candidate in range(9000, 65535):
                # if port_candidate not in [conn.laddr[1] for conn in psutil.net_connections()]:
                # self.port = port_candidate
                # break
                #
                # # Check if the port is in use
                # if self.port in [conn.laddr[1] for conn in psutil.net_connections()]:
                # raise IOError('Port ' + str(self.port) + ' is already in use.')
    
                # Start native server

在调用方法时，给出指定的端点port = 9999

from stanfordcorenlp import StanfordCoreNLP
    nlp = StanfordCoreNLP(r'/stanford-corenlp-full-2018-10-05/', port=9999, lang='zh')
    sentence = '清华大学位于北京。'
    print nlp.word_tokenize(sentence)
    print nlp.pos_tag(sentence)
    print nlp.ner(sentence)
    print nlp.parse(sentence)
    print nlp.dependency_parse(sentence)

https://www.cnblogs.com/gaofighting/p/9768023.html

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dhbnppX2FudGFuZw_size_16_color_FFFFFF_t_70]: https://img-blog.csdnimg.cn/20200207100717986.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dhbnppX2FudGFuZw==,size_16,color_FFFFFF,t_70