中文新聞分詞展示:
分詞代碼:
import jieba as fc
import pymysql
db = pymysql.connect(host="localhost", user="", passwd="", database="")
cursor = db.cursor()
sql = "select title,content from 财經";
cursor.execute(sql)
results = cursor.fetchall()
dict = {}
for one in results:
keys = fc.lcut(one[1], cut_all=False, HMM=True)
for key in keys:
if key in dict.keys():
dict[key] = dict[key] + 1
else:
dict[key] = 1
dict = sorted(dict.items(), key=lambda kv: (kv[1], kv[0]), reverse=True)
num = 0
print("開始寫入資料庫")
for words in dict:
if num<5000:
va = []
va.append(words[0])
va.append(words[1])
sql1 = "insert into junsiword (name,num) values(%s,%s) "
cursor.execute(sql1, va)
db.commit()
num=num+1
print("運作成功")
