>>> jieba.lcut("中國(guó)是一個(gè)偉大的國(guó)家")
['中國(guó)', '是', '一個(gè)', '偉大', '的', '國(guó)家']

>>> jieba.lcut("中國(guó)是一個(gè)偉大的國(guó)家", cut_all=True)
['中國(guó)', '國(guó)是', '一個(gè)', '偉大', '的', '國(guó)家']

>>> jieba.lcut_for_search("中華人民共和國(guó)是偉大的")
['中華', '華人', '人民', '共和', '共和國(guó)', '中華人民共和國(guó)', '是', '偉大', '的']

def getText():
 # 打開 hamlet.txt 這個(gè)文件
 txt = open("hamlet.txt", "r").read()
 # 避免大小寫對(duì)詞頻統(tǒng)計(jì)的干擾，將所有單詞轉(zhuǎn)換為小寫
 txt = txt.lower()
 # 將文中出現(xiàn)的所有特殊字符替換為空格
 for ch in '|"#$%^*()_+-=\\`~{}[];:>?/':
 txt = txt.replace(ch, " ")
 # 返回一個(gè)所以后單詞都是小寫的，單詞間以空格間隔的文本
 return txt

hamletTxt = getText()
# split() 默認(rèn)使用空格作為分隔符
words = hamletTxt.split()
counts = {}
for word in words:
 counts[word] = counts.get(word,0) + 1
items = list(counts.items())
items.sort(key=lambda x:x[1], reverse=True)
for i in range(10):
 word, count = items[i]
 print("{0:10}{1:>5}".format(word,count))

items.sort(key=lambda x:x[1], reverse=True)

import jieba
txt = open("threekingdoms.txt","r",encoding="utf-8").read()
words = jieba.lcut(txt)
counts = {}
for word in words:
 if len(word) == 1:
 continue
 else:
 counts[word] = counts.get(word, 0) + 1

items = list(counts.items())
items.sort(key=lambda x:x[1], reverse=True)
for i in range(15):
 word, count = items[i]
 print("{0:10}{1:>5}".format(word,count))

曹操  953
孔明  836
將軍  772
卻說(shuō)  656
玄德  585
關(guān)公  510
丞相  491
二人  469
不可  440
荊州  425
玄德曰  390
孔明曰  390
不能  384
如此  378
張飛  358

import jieba
txt = open("threekingdoms.txt","r",encoding="utf-8").read()
excludes = {"將軍","卻說(shuō)","荊州","二人","不可","不能","如此"}
words = jieba.lcut(txt)
counts = {}
for word in words:
 if len(word) == 1:
 continue
 elif word == "諸葛亮" or word == "孔明曰":
 rword == "孔明"
 elif word == "關(guān)公" or word == "云長(zhǎng)":
 rword == "關(guān)羽"
 elif word == "玄德" or word == "玄德曰":
 rword == "劉備"
 elif word == "孟德" or word == "丞相":
 rword == "曹操"
 else:
 rword = word
 counts[rword] = counts.get(rword, 0) + 1

items = list(counts.items())
items.sort(key=lambda x:x[1], reverse=True)
for i in range(15):
 word, count = items[i]
 print("{0:10}{1:>5}".format(word,count))

曹操  963
孔明  847
張飛  366
商議  359
如何  352
主公  340
軍士  320
呂布  303
左右  298
軍馬  297
趙云  283
劉備  282
引兵  279
次日  278
大喜  274