python幾萬條微博高頻詞分析

看到別人有做影視熱評的分析統計，覺得挺好玩的，就來試試

看看效果

Screenshot_2018-05-21-11-00-42-879_com.master.wei.png

思路

抓取想要的微博數據寫入數據庫

分詞統計出詞匯出現次數

過濾無意義的干擾詞

存入數據庫

寫接口，然后Android端展示

代碼

數據庫連接 masterWeiBo.Utils.Sql

import pymysql

import pymysql.cursors

import threading

class Mydb(object):

tableName='master'

def __init__(self):

self.lock=threading.Lock()

self.client = pymysql.connect(host='localhost',charset='utf8', port=3306, user='root', passwd='ck123', db='weibo', cursorclass=pymysql.cursors.DictCursor)

self.client.autocommit(True)

self.cursor = self.client.cursor()

開始

import jieba

from masterWeiBo.Utils.Sql import Mydb as db

# 創建停用詞list

def stopwordslist(filepath):

stopwords = [line.strip() for line in open(filepath, 'r', encoding='utf-8').readlines()]

return stopwords

cursor = db().cursor

#如果不存在詞表就創建

cursor.execute("""CREATE TABLE IF NOT EXISTS `weibo`.`masterWeiBo_category` (

`id` INT NOT NULL AUTO_INCREMENT,

`count` INT NOT NULL DEFAULT 0,

`category` VARCHAR(100) NOT NULL,

`wordsTop10` VARCHAR(1000) NULL,

PRIMARY KEY (`id`));""")

#清空詞表

cursor.execute("DELETE FROM weibo.masterWeiBo_category")

#獲取分類分詞

cursor.execute("SELECT count(id) as countd, come FROM weibo.masterWeiBo_master GROUP BY come")

results = cursor.fetchall()

print(results)

dicts=[]

#加載過濾詞匯

stopwords = stopwordslist("/root/PYServer/myFirstPYServer/words.txt")

for result in results:

each={}

each['count']=result['countd']

each['come']=result['come']

print(result['countd'])

print(result['come'])

cursor.execute("SELECT content from weibo.masterWeiBo_master where come= '"+result['come']+"'")

contents = cursor.fetchall()

articals=''

#把指定分類的內容拼接起來

for artical in contents:

articals+=","+artical['content']

#結巴分詞

cuts = jieba.cut(articals)

words={}

#統計詞頻

for cut in cuts:

if(cut in words):

words[cut]=words[cut]+1

else:

words[cut]=1

#按詞頻倒序排列

sortedWords = sorted(words.items(), key=lambda d: d[1], reverse=True)

wordsTop10=''

i=0

#獲取top10詞匯

for key ,value in sortedWords:

#過濾無效詞匯

if(key in stopwords or key.__len__()<2):

continue

wordsTop10+=key+","+str(value)+";"

i+=1

if(i==10):

wordsTop10=wordsTop10[:wordsTop10.__len__()-1]

break

each['wordsTop10']=wordsTop10

dicts.append(each)

#寫入數據庫

for value in dicts:

sql = "INSERT INTO weibo.masterWeiBo_category (count,category,wordsTop10) values( '" + str(

value['count']) + "','" + value['come'] + "','" + value['wordsTop10'] + "')"

print(sql)

cursor.execute(sql)

cursor.close()

print(dicts)

大功告成

總結

以上是生活随笔為你收集整理的python高频词_python几万条微博高频词分析的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。