标题基于Hive大数据分析springboot为后端以及vue为前端的的民宿系
本文介绍了如何利用Hive进行大数据分析，并结合Spring Boot和Vue构建了一个民宿管理系统。该民民宿管理系统包含用户和管理员登陆注册的功能，发布下架酒店信息，模糊搜索，酒店详情信息展示，收藏以及对收藏的酒店进行排序可视化，管理员发布，添加用户的功能。
1. 数据采集
通过 Python 爬虫实现数据采集，并将采集到的数据存储到数据库中。这些数据将作为我们民宿系统的基础数据，在后续的处理和分析中发挥重要作用。我们首先使用 Python 爬虫从艺龙酒店获取民宿相关信息，包括房源信息、评论信息、价格信息等。以下是一个简单的示例代码，使用 BeautifulSoup 库进行网页解析，并通过 requests 库发送 HTTP 请求获取网页内容。
import json
import time
import requests
from request_data.sync_data2mysql import request_data2mysql
hotels_data = []
class YiLongList:
def __init__(self,inDate,outDate,city):
self.inDate,self.outDate = inDate,outDate
self.city = city
self.session = requests.Session()
def jxList(self,hotelList):
for h in hotelList:
hotelName = h.get("hotelName")
starLevelDes = h.get("starLevelDes")
commentScore = h.get("commentScore")
price = h.get("price")
commentScoreDes = h.get("commentScoreDes")
commentMainTag = h.get("commentMainTag")
commentCount = h.get("commentCount")
hotelAddress = h.get("hotelAddress")
trafficInfo = h.get("trafficInfo")
areaName = h.get("areaName")
hotelTags = h.get("hotelTags")
if hotelTags:
hotelTags = "|".join([i.get("tagName") for i in hotelTags])
themeList = "|".join(h.get("themeList"))
recallReason = h.get("recallReason")[0]
data = {
'hotelName': hotelName,
'starLevelDes': starLevelDes,
'commentCount': commentCount,
'price': price,
'commentScore': commentScore,
'commentScoreDes': commentScoreDes,
'areaName': areaName,
'hotelTags': hotelTags,
'themeList': themeList,
'recallReason': recallReason,
'commentMainTag': commentMainTag,
'hotelAddress': hotelAddress,
'trafficInfo': trafficInfo
}
hotels_data.append(data)
print(hotelName,starLevelDes,commentCount,price,commentScore,commentScoreDes,\
areaName,hotelTags,themeList,recallReason,commentMainTag,hotelAddress,trafficInfo,)
def getList(self,page,traceToken):
url = "https://hotel.elong.com/tapi/v2/list"
headers = {
"Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6,zh-TW;q=0.5",
"Referer": "https://hotel.elong.com/hotel/hotellist?city=0101&inDate=2024-03-23&outDate=2022-03-24&filterList=8888_1&pageSize=20&t=1669994718934",
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/107.0.0.0 Safari/537.36 Edg/107.0.1418.62",
"accept": "application/json, text/plain, */*",
"deviceid": "c2a61f65-fa3e-4360-8ccd-4093f4f99f41",
"traceid": "4630a377-472b-4765-852f-959e2fa139cd"
}
if page == 0:
params = {
"city": self.city,
"inDate": self.inDate,
"outDate": self.outDate,
"filterList": "8888_1",
"pageIndex": str(page),
"pageSize": "20",
"sugActInfo": ""
}
else:
params = {
"city"
