python中文分词库结巴使用示例

结巴是开源库，中文分词，使用简单，可以添加用户字典
https://github.com/fxsjy/jieba

使用示例

from xml.etree import ElementTree
import re
import jieba
import jieba.posseg as pseg

jieba.load_userdict("dict.txt")

#读root
root = ElementTree.parse(r"爬虫.xml")
persons = root.findall("person")

#写root
root = ElementTree.Element("documents")

for person in persons:
    name = person.find("name")
    dis = person.find("dis")
    #s删除作品名
    text = re.sub(r'《.*》', '', str(dis.text))
    words = pseg.cut(text)
    try:
        for w in words:
            if len(w.word) == 1:
                continue
            #nr为人名标志
            if str(w.flag) == "nr":
                print(w.word)
    except:
        pass