基于Python的涉台大数据获取与处理  

Data Acquisition and Processing of Taiwan-Related Information Based on Python

作　　者：杨斌[1] 李文慧[2] 

机构地区：[1]淮阴师范学院,数学科学学院,江苏淮安 [2]淮阴师范学院,城市与环境学院,江苏淮安

出　　处：《计算机科学与应用》2019年第1期63-69,共7页Computer Science and Application

摘　　要：当前涉台宣传、言论及经济信息发布与共享等,地方事务人员难以完全掌握国家权威部门或其它省市部门对类似问题的法律法规、指示发言等。本文主要研究当前互联网环境下,使用大数据技术对涉台相关事宜进行抓取分析,辅助相关部门和人员有理有据有节的处理相关涉台事件。本文基于Python实现了涉台信息的数据获取、网站信息挖掘、自然语言分词、文本聚类、词云辅助显示等功能,为提高涉台工作的规范性与进一步研究提供基础。At present, it is difficult for local affairs personnel to fully grasp the laws, regulations, instructions and speeches of the state authorities or other provincial and municipal departments on similar is-sues, such as Taiwan-related propaganda, publication and sharing of economic information on speech discipline. This paper mainly studies using big data technology to grasp and analyze Taiwan-related issues, assisting relevant departments and personnel to deal with relevant Taiwan-related incidents with reasonable and knowledgeable. This paper realizes the functions of data acquisition, website information mining, natural language word segmentation, text clustering and word cloud assistant display, which provides a basis for improving the standardization and further research of Taiwan-related work based on Python.

关 键 词：数据抓取 分词 文本聚类 PYTHON 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]