├── 1.png ├── 2.png ├── 3.png ├── 4.png ├── 5.png ├── 6.png ├── 7.png ├── 8.png ├── 9.png ├── JedisUtil.java ├── README.md ├── ReduceByKeySortRddDemo.scala └── crawler.py /1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bysj2022NB/travel2024_spark_hadoop_hive/15855ad5c05c231edaecde89482418649d3bee1b/1.png -------------------------------------------------------------------------------- /2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bysj2022NB/travel2024_spark_hadoop_hive/15855ad5c05c231edaecde89482418649d3bee1b/2.png -------------------------------------------------------------------------------- /3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bysj2022NB/travel2024_spark_hadoop_hive/15855ad5c05c231edaecde89482418649d3bee1b/3.png -------------------------------------------------------------------------------- /4.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bysj2022NB/travel2024_spark_hadoop_hive/15855ad5c05c231edaecde89482418649d3bee1b/4.png -------------------------------------------------------------------------------- /5.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bysj2022NB/travel2024_spark_hadoop_hive/15855ad5c05c231edaecde89482418649d3bee1b/5.png -------------------------------------------------------------------------------- /6.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bysj2022NB/travel2024_spark_hadoop_hive/15855ad5c05c231edaecde89482418649d3bee1b/6.png -------------------------------------------------------------------------------- /7.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bysj2022NB/travel2024_spark_hadoop_hive/15855ad5c05c231edaecde89482418649d3bee1b/7.png -------------------------------------------------------------------------------- /8.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bysj2022NB/travel2024_spark_hadoop_hive/15855ad5c05c231edaecde89482418649d3bee1b/8.png -------------------------------------------------------------------------------- /9.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bysj2022NB/travel2024_spark_hadoop_hive/15855ad5c05c231edaecde89482418649d3bee1b/9.png -------------------------------------------------------------------------------- /JedisUtil.java: -------------------------------------------------------------------------------- 1 | package com.bigdata.storm.kafka.util; 2 | 3 | import redis.clients.jedis.Jedis; 4 | import redis.clients.jedis.JedisPool; 5 | import redis.clients.jedis.JedisPoolConfig; 6 | 7 | /** 8 | * @program: storm-kafka-api-demo 9 | * @description: redis工具类 10 | * @author: 小毕 11 | * @company: 清华大学深圳研究生院 12 | * @create: 2019-08-22 17:23 13 | */ 14 | public class JedisUtil { 15 | 16 | /*redis连接池*/ 17 | private static JedisPool pool; 18 | 19 | /** 20 | *@Description: 返回redis连接池 21 | *@Param: 22 | *@return: 23 | *@Author: 小毕 24 | *@date: 2019/8/22 0022 25 | */ 26 | public static JedisPool getPool(){ 27 | if(pool==null){ 28 | //创建jedis连接池配置 29 | JedisPoolConfig jedisPoolConfig = new JedisPoolConfig(); 30 | //最大连接数 31 | jedisPoolConfig.setMaxTotal(20); 32 | //最大空闲连接 33 | jedisPoolConfig.setMaxIdle(5); 34 | pool=new JedisPool(jedisPoolConfig,"node03.hadoop.com",6379,3000); 35 | } 36 | return pool; 37 | } 38 | 39 | public static Jedis getConnection(){ 40 | return getPool().getResource(); 41 | } 42 | 43 | /* public static void main(String[] args) { 44 | //System.out.println(getPool()); 45 | //System.out.println(getConnection().set("hello","world")); 46 | }*/ 47 | 48 | 49 | 50 | 51 | 52 | 53 | 54 | 55 | } -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | ## 计算机毕业设计吊打导师hadoop+spark+hive旅游推荐系统 旅游数据 旅游分析可视化大屏 智慧旅游路线推荐 旅游爬虫 旅游大数据 旅游攻略系统 大数据 大数据毕业设计 机器学习 预测系统 数据仓库 大数据毕业设计 文本分类 LSTM情感分析 大数据毕业设计 知识图谱 大数据毕业设计 预测系统 实时计算 离线计算 数据仓库 人工智能 神经网络 2 | 3 | ## 要求 4 | ### 源码有偿！一套(论文 PPT 源码+sql脚本+教程) 5 | 6 | ### 7 | ### 加好友前帮忙start一下，并备注github有偿hive旅游数仓+推荐 8 | ### 我的QQ号是2827724252或者798059319或者 1679232425或者微信:bysj2023nb 9 | 10 | # 11 | 12 | ### 加qq好友说明（被部分 网友整得心力交瘁）： 13 | 1.加好友务必按照格式备注 14 | 2.避免浪费各自的时间！ 15 | 3.当“客服”不容易，repo 主是体面人，不爆粗，性格好，文明人。 16 | 17 | 基础版，也就是当前下面连接这个版本(只带hadoop spark hive flask DrissionPage爬虫[全新爬虫框架吊打碾压selenium这些垃圾传统Python爬虫] echarts大屏可视化驾驶舱) 18 | 19 | https://www.bilibili.com/video/BV1ap4y1n7hY/?spm_id_from=333.999.0.0 20 | 21 | ![](1.png) 22 | ![](2.png) 23 | ![](3.png) 24 | ![](4.png) 25 | ![](5.png) 26 | ![](6.png) 27 | ![](7.png) 28 | ![](8.png) 29 | ![](9.png) 30 | ## 开发技术： 31 | spark hadoop hive 装杯显摆虚拟机Linux敲命令炫酷吊打 flask echarts sqoop scala hdfs yarn mysql python爬虫框架等； 32 | 33 | ## 流程： 34 | 35 | 1.DrissionPage自动化爬虫框架采集旅游数据约10万条存入mysql数据库、.csv文件作为数据集(旅游数据、用户数据、评论数据)； 36 | 37 | 2.使用pandas+numpy或MapReduce对数据进行数据清洗，生成最终的.csv文件并上传到hdfs(含nlp情感分析)； 38 | 39 | 3.使用hive数仓技术建表建库，导入.csv数据集； 40 | 41 | 4.离线分析采用hive_sql完成，实时分析利用Spark之Scala完成; 42 | 43 | 5.统计指标使用sqoop导入mysql数据库； 44 | 45 | 6.使用flask+echarts进行可视化大屏幕炫酷展示； 46 | 47 | 48 | ## 创新点： 49 | 1.全新DrissionPage爬虫框架，性能强悍碾压selenium/requests等常见传统Python爬虫技术； 50 | 51 | 2.可视化炫酷大屏幕； 52 | 53 | 3.虚拟机显摆敲命令碾压答辩现场(市面上全是假算法假爬虫假大数据都不带用虚拟机的)； 54 | 55 | 4.nlp深度学习文本分类情感分析； 56 | 57 | 5.Spark实时计算+Hive、Hadoop离线计算双实现有效避免导师喷你； 58 | 59 | ## 可选装项目模块如下： 60 | 1.推荐系统(4种深度学习推荐算法 协同过滤基于用户 基于物品 SVD神经网络 MLP)。附带AI、支付、短信、lstm情感分析。 61 | 2.预测系统(KNN CNN RNN卷积神经预测 K-means 线性回归)。 62 | 3.知识图谱neo4j可视化关系网络图。 63 | 4.后台管理系统。 64 | 65 | 66 | 选装视频效果如下： 67 | https://www.bilibili.com/video/BV1pm4y1d7S5/?spm_id_from=333.999.0.0 68 | 69 | 70 | 71 | 72 | 73 | 74 | 75 | 76 | 77 | 78 | 79 | 80 | 81 | 82 | 83 | 84 | 85 | 86 | -------------------------------------------------------------------------------- /ReduceByKeySortRddDemo.scala: -------------------------------------------------------------------------------- 1 | package com.bigdata.spark.reducebykey_sort 2 | 3 | import org.apache.spark.{SparkConf, SparkContext} 4 | 5 | /** 6 | * @program: spark-api-demo 7 | * @description: 类作用描述 8 | * @author: 小毕 9 | * @company: 清华大学深圳研究生院 10 | * @create: 2019-09-02 18:00 11 | */ 12 | object ReduceByKeySortRddDemo { 13 | 14 | def main(args: Array[String]): Unit = { 15 | val conf=new SparkConf() 16 | .setAppName("MapFilterApp") 17 | .setMaster("local") 18 | val sc=new SparkContext(conf) 19 | val rdd1=sc.parallelize(List(("tom", 1), ("jerry", 3), ("kitty", 2), ("shuke", 1))) 20 | val rdd2=sc.parallelize(List(("jerry", 2), ("tom", 3), ("shuke", 2), ("kitty", 5))) 21 | val rdd3=rdd1.union(rdd2) 22 | //按key进行聚合 23 | val rdd4=rdd3.reduceByKey(_+_) 24 | rdd4.collect.foreach(println(_)) 25 | //按value的降序排序 26 | val rdd5=rdd4.map(t=>(t._2,t._1)).sortByKey(false).map(t=>(t._2,t._1)) 27 | rdd5.collect.foreach(println) 28 | } 29 | 30 | } 31 | -------------------------------------------------------------------------------- /crawler.py: -------------------------------------------------------------------------------- 1 | # coding=utf-8 2 | from bs4 import BeautifulSoup 3 | import requests 4 | import sys 5 | import random 6 | import pymysql 7 | links = [] 8 | datas = [] 9 | hea = { 10 | 'User-Agent': 'Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2272.118 Safari/537.36' 11 | } 12 | urls =[ 13 | "https://www.chinanews.com/china.shtml", #国内 14 | "https://www.chinanews.com/society.shtml", #社会 15 | "https://www.chinanews.com/compatriot.shtml",#港澳 16 | "https://www.chinanews.com/wenhua.shtml",#文化 17 | "https://www.chinanews.com/world.shtml",#国际 18 | "https://www.chinanews.com/cj/gd.shtml",#财经 19 | "https://www.chinanews.com/sports.shtml",#体育 20 | "https://www.chinanews.com/huaren.shtml" #华人 21 | ] 22 | # 打开数据库连接 23 | db = pymysql.connect(host='127.0.0.1', user='root', password='123456', port=3396, db='news_recommendation_system') 24 | # 使用cursor()方法获取操作游标 25 | cursor = db.cursor() 26 | 27 | def main(): 28 | #reload(sys) 29 | #sys.setdefaultencoding("utf-8") 30 | #baseurl = 'https://www.chinanews.com/taiwan.shtml' # 要爬取的网页链接 31 | baseurl = 'https://www.chinanews.com/taiwan.shtml' # 要爬取的网页链接 32 | # deleteDate() 33 | # 1.爬取主网页获取各个链接 34 | getLink(baseurl) 35 | # 2.根据链接爬取内部信息并且保存数据到数据库 36 | getInformationAndSave() 37 | # 3.关闭数据库 38 | db.close() 39 | 40 | def getInformationAndSave(): 41 | for link in links: 42 | data = [] 43 | url = "https://www.chinanews.com" + link[1] 44 | cur_html = requests.get(url, headers=hea) 45 | cur_html.encoding = "utf8" 46 | soup = BeautifulSoup(cur_html.text, 'html.parser') 47 | # 获取时间 48 | title = soup.find('h1') 49 | title = title.text.strip() 50 | # 获取时间和来源 51 | tr = soup.find('div', class_='left-t').text.split() 52 | time = tr[0] + tr[1] 53 | recourse = tr[2] 54 | # 获取内容 55 | cont = soup.find('div', class_="left_zw") 56 | content = cont.text.strip() 57 | print(link[0] + "---" + title + "---" + time + "---" + recourse + "---" + url) 58 | saveDate(title,content,time,recourse,url) 59 | 60 | def deleteDate(): 61 | sql = "DELETE FROM news " 62 | try: 63 | # 执行SQL语句 64 | cursor.execute(sql) 65 | # 提交修改 66 | db.commit() 67 | except: 68 | # 发生错误时回滚 69 | db.rollback() 70 | 71 | def saveDate(title,content,time,recourse,url): 72 | try: 73 | cursor.execute("INSERT INTO news(news_title, news_content, type_id, news_creatTime, news_recourse,news_link) VALUES ('%s', '%s', '%s', '%s', '%s' ,'%s')" % \ 74 | (title, content, random.randint(1,8), time, recourse,url)) 75 | db.commit() 76 | print("执行成功") 77 | except: 78 | db.rollback() 79 | print("执行失败") 80 | 81 | def getLink(baseurl): 82 | html = requests.get(baseurl, headers=hea) 83 | html.encoding = 'utf8' 84 | soup = BeautifulSoup(html.text, 'html.parser') 85 | for item in soup.select('div.content_list > ul > li'): 86 | # 对不符合的数据进行清洗 87 | if (item.a == None): 88 | continue 89 | data = [] 90 | type = item.div.text[1:3] # 类型 91 | link = item.div.next_sibling.next_sibling.a['href'] 92 | data.append(type) 93 | data.append(link) 94 | links.append(data) 95 | 96 | if __name__ == '__main__': 97 | main() 98 | 99 | 100 | --------------------------------------------------------------------------------