需求分析

1：爬取厦门市租房网的信息
2 : 对厦门市各个区的租房的价格进行分析
3：通过数据的可视化，来让别人清楚了解厦门市各个区的租房价格的水平

架构选型

开发环境及需要的其他的插件

数据来源

网页url：http://fangzi.xmfish.com/web/search_hire.html?h=&hf=&ca=59201&r=&s=&a=&rm=&f=&d=&tp=&l=0&tg=&hw=&o=&ot=0&tst=0&page=2

程序结构图：

爬虫程序(Crawling_Data.py)：

# -*- coding: utf-8 -*-
import requests
from bs4 import BeautifulSoup
import csv# num表示记录序号
Url_head = "http://fangzi.xmfish.com/web/search_hire.html?h=&hf=&ca=5920"
Url_tail = "&r=&s=&a=&rm=&f=&d=&tp=&l=0&tg=&hw=&o=&ot=0&tst=0&page="
Num = 0
Filename = "rent.csv"# 把每一页的记录写入文件中
def write_csv(msg_list):out = open(Filename, 'a', newline='')csv_write = csv.writer(out, dialect='excel')for msg in msg_list:csv_write.writerow(msg)out.close()# 访问每一页
def acc_page_msg(page_url):web_data = requests.get(page_url).content.decode('utf8')soup = BeautifulSoup(web_data, 'html.parser')address_list = []area_list = []num_address = 0num_area = 0msg_list = []# 得到了地址列表，以及区域列表for tag in soup.find_all(attrs="list-addr"):for em in tag:count = 0for a in em:count += 1if count == 1 and a.string != "[":address_list.append(a.string)elif count == 2:area_list.append(a.string)num_area += 1elif count == 4:if a.string is not None:address_list[num_address] = address_list[num_address] + "-" + a.stringelse:address_list[num_address] = address_list[num_address] + "-Null"num_address += 1# 得到了价格列表price_list = []for tag in soup.find_all(attrs="list-price"):price_list.append(tag.b.string)# 组合成为一个新的tuple——list并加上序号for i in range(len(price_list)):txt = (address_list[i], area_list[i], price_list[i])msg_list.append(txt)# 写入csvwrite_csv(msg_list)# 爬所有的页面
def get_pages_urls():urls = []# 思明可访问页数134for i in range(134):urls.append(Url_head + "1" + Url_tail + str(i + 1))# 湖里可访问页数134for i in range(134):urls.append(Url_head + "2" + Url_tail + str(i + 1))# 集美可访问页数27for i in range(27):urls.append(Url_head + "3" + Url_tail + str(i + 1))# 同安可访问页数41for i in range(41):urls.append(Url_head + "4" + Url_tail + str(i + 1))# 翔安可访问页数76for i in range(76):urls.append(Url_head + "5" + Url_tail + str(i + 1))# 海沧可访问页数6for i in range(6):urls.append(Url_head + "6" + Url_tail + str(i + 1))return urlsdef run():print("开始爬虫")out = open(Filename, 'a', newline='')csv_write = csv.writer(out, dialect='excel')title = ("address", "area", "price")csv_write.writerow(title)out.close()url_list = get_pages_urls()for url in url_list:try:acc_page_msg(url)except:print("格式出错", url)print("结束爬虫")

数据存储

数据处理 (项目重点）

spark 数据处理程序（SparkBatch_Data.py）

# -*- coding: utf-8 -*-from pyspark.sql import SparkSession
from pyspark.sql.types import IntegerTypedef spark_analyse(filename):# 程序主入口spark = SparkSession.builder.master("local").appName("DataBatch").getOrCreate()df = spark.read.csv(filename, header=True, encoding="GBK")print(df)df.show()# max_list存储各个区的最大值，0海沧，1为湖里，2为集美，3为思明，4为翔安，5为同安;同理的mean_list, 以及min_list,approxQuantile中位数max_list = [0 for i in range(6)]# 平均值mean_list = [1.2 for i in range(6)]# minmin_list = [0 for i in range(6)]# 中位数mid_list = [0 for i in range(6)]# 类型转换，十分重要，保证了price列作为int用来比较，否则会用str比较, 同时排除掉一些奇怪的价格，比如写字楼的出租超级贵# 或者有人故意标签1元，其实要面议, 还有排除价格标记为面议的df = df.filter(df.price != '面议').withColumn("price", df.price.cast(IntegerType()))#df = df.filter(df.price >= 50).filter(df.price <= 40000)## print(df.filter(df.area == "海沧"))#mean_list[0] = df.filter(df.area == "海沧").agg({"price": "mean"}).first()['avg(price)']# print(mean_list[0].collect())#mean_list[1] = df.filter(df.area == "湖里").agg({"price": "mean"}).first()['avg(price)']mean_list[2] = df.filter(df.area == "集美").agg({"price": "mean"}).first()['avg(price)']mean_list[3] = df.filter(df.area == "思明").agg({"price": "mean"}).first()['avg(price)']mean_list[4] = df.filter(df.area == "翔安").agg({"price": "mean"}).first()['avg(price)']mean_list[5] = df.filter(df.area == "同安").agg({"price": "mean"}).first()['avg(price)']min_list[0] = df.filter(df.area == "海沧").agg({"price": "min"}).first()['min(price)']min_list[1] = df.filter(df.area == "湖里").agg({"price": "min"}).first()['min(price)']min_list[2] = df.filter(df.area == "集美").agg({"price": "min"}).first()['min(price)']min_list[3] = df.filter(df.area == "思明").agg({"price": "min"}).first()['min(price)']min_list[4] = df.filter(df.area == "翔安").agg({"price": "min"}).first()['min(price)']min_list[5] = df.filter(df.area == "同安").agg({"price": "min"}).first()['min(price)']#max_list[0] = df.filter(df.area == "海沧").agg({"price": "max"}).first()['max(price)']max_list[1] = df.filter(df.area == "湖里").agg({"price": "max"}).first()['max(price)']max_list[2] = df.filter(df.area == "集美").agg({"price": "max"}).first()['max(price)']max_list[3] = df.filter(df.area == "思明").agg({"price": "max"}).first()['max(price)']max_list[4] = df.filter(df.area == "翔安").agg({"price": "max"}).first()['max(price)']max_list[5] = df.filter(df.area == "同安").agg({"price": "max"}).first()['max(price)']print(max_list[1])# 返回值是一个list，所以在最后加一个[0]mid_list[0] = df.filter(df.area == "海沧").approxQuantile("price", [0.5], 0.01)[0]mid_list[1] = df.filter(df.area == "湖里").approxQuantile("price", [0.5], 0.01)[0]mid_list[2] = df.filter(df.area == "集美").approxQuantile("price", [0.5], 0.01)[0]mid_list[3] = df.filter(df.area == "思明").approxQuantile("price", [0.5], 0.01)[0]mid_list[4] = df.filter(df.area == "翔安").approxQuantile("price", [0.5], 0.01)[0]mid_list[5] = df.filter(df.area == "同安").approxQuantile("price", [0.5], 0.01)[0]all_list = []all_list.append(min_list)all_list.append(max_list)all_list.append(mean_list)all_list.append(mid_list)print("结束spark分析")# print(all_list.printSchema())return all_list

数据处理的时候遇到问题

数据格式问题

导致spark的DataFrame读到的数据格式出现问题
filter的算子把数据都过滤掉了，如下程序截图所示。
spark的filter算子他会过滤不符合的数据，如果我们的DataFrame的数据不是正常的显示，而是如下的乱码的格式。
那么filter算子会把数据全部过滤掉， 最终数据会是None

在read数据的时候加上编码就可以避免这样的问题

转成GBK就可以显示正常了

数据可视化

数据可视化生成界面程序（Draw.py）

# -*- coding: utf-8 -*-
import Draw
# -*- coding: utf-8 -*-from pyecharts import Map
# 1. 准备数据
def draw_bar(all_list):print("开始绘图")attr = ["海沧", "湖里", "集美", "思明", "翔安", "同安"]v0 = all_list[0]v1 = all_list[1]v2 = all_list[2]v3 = all_list[3]# 信阳地图 数据为信阳市下的区县attrlist= ["海沧区", "湖里区", "集美区", "思明区", "翔安区", "同安区"]map3 = Map("厦门地图", '厦门', width=1600, height=800)map3.add("厦门", attrlist, v2, visual_range=[1000, 4000], maptype='厦门', is_visualmap=True, visual_text_color='#000')map3.render("厦门租房价格分析地图.html")

总程序启动（main.py）

# -*- coding: utf-8 -*-
import Draw
import Crawling_Data
import SparkBatch_Dataif __name__ == '__main__':print("开始总程序")Filename = "rent.csv"# Crawling_Data.run()all_list = SparkBatch_Data.spark_analyse(Filename)Draw.draw_bar(all_list)# print("结束总程序")

厦门市租房情况分析App02项目

App02项目

需求分析

架构选型

开发环境及需要的其他的插件

数据来源

数据存储

数据处理 (项目重点）

数据格式问题

数据可视化

项目代码地址：github

项目成员

更多信息

厦门市租房情况分析App02项目相关推荐

最新文章

热门文章