全模式
#import jieba
sentence="我是只长着大长腿的小白兔"
word1=jieba.cut(sentence,cut_all=True)
for item in word1:
print(item)
#jingzhunmoshi
word2=jieba.cut(sentence,cut_all=False)
for item in word2:
print(item)
#搜索引擎模式
word3=jieba.cut_for_search(sentence)#搜索模式
for item in word3:
print (item)
print ("")
word4=jieba.cut(sentence)#精准模式
for item in word4:
print (item)
#词性标注
import jieba.posseg
word5=jieba.posseg.cut(sentence)
#调用词性 .flag 调用词语 . word
for item in word5:
print (item.word+","+item.flag)
#(a: adj; c: conj; d；adv: e: exclamation ! ;f: 方向词；i: idiom(成语)；
# m:number; n:none; nr: name; ns:location; nt:institution name; nz:其他专有名词；
# p:prep; r: pronone(代词); t:time; u:auxiliary(do); v；verb;vn:doing; w:marks; un: unknow word
#我,r;是,v;只长,v;着,uz;大,a;长,a;腿,n;的,uj;小白兔,nr
#加载词典
print ("")
jieba.load_userdict("C:/Users/Administrator/Desktop/tripadvisor_gm/tripadvisor_code_python/galaxy_macau_dict.txt")
word6=jieba.posseg.cut(sentence)
for item in word6:
print (item.word+","+item.flag)
#词频的更改
jieba.suggest_freq("大长腿的小兔子",True)
jieba.add_word("大长腿的小兔子",True)
word7=jieba.cut(sentence)
print (word7)
print ("")
#topic extract
import jieba.analyse
tag=jieba.analyse.extract_tags(sentence,2)
print(tag)
word8=jieba.tokenize(sentence)
for item in word8:
print (item)
#编码解决方案
import urllib.request
data=urllib.request.urlopen("http://127.0.0.1/txt1.txt").read().decode("utf-8","ignore")
word10=jieba.analyse.extract_tags(data,200)
print(word10)
#data=urllib.request.urlopen("http://127.0.0.1/txt1.html").read().decode("utf-8","ignore")
#<html><body>...</body></html>