NLTK 对文本结构进行语法分析代码示例

from nltk import CFG
import nltk
from nltk.chunk.regexp import *
from nltk.parse.stanford import StanfordParser
# import re

# nltk.download('maxent_ne_chunker')
# nltk.download('words')
# nltk.download('ieer')
# 语法分析
toy_grammar = nltk.CFG.fromstring(
 """
  S -> NP VP                      
  VP -> V NP            
  V -> "eats" | "drinks"
  NP -> Det N 
  Det -> "a" | "an" | "the" 
  N -> "president" |"Obama" |"apple"| "coke" 
    """)
toy_grammar.productions()
print(toy_grammar.productions())
# S indicate the entire sentence
# VP is verb phrase the
# NP is noun phrase (chunk that has noun in it)
# N some example nouns
# V is verb
# Det is determiner used in the sentences

# 正则表达式语法分析器
chunk_rules = ChunkRule("<.*>+", "chunk everything")
# NP
# Preposition
# Verb
# PP