天天看点

每日总结

中文新闻分词展示:

分词代码:

import jieba as fc
import pymysql
db = pymysql.connect(host="localhost", user="", passwd="", database="")
cursor = db.cursor()
sql = "select  title,content from 财经";
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("开始写入数据库")
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("运行成功")
      
每日总结
每日总结
每日总结