Python学习，房价代码更新

一.知识准备

我们需要学习以下python库，包括爬虫获取数据的requests库，pandas读取cvs文件的库，BeautifulSoup网页截取库，csv保存数据到csv文件的库，numpy科学计算库，matplotlib数据可视化库,具体库知识学习可以下面评论留言

import requests
import pandas as pd
from bs4 import BeautifulSoup
import csv
import numpy as np
from matplotlib.pyplot import MultipleLocator
import matplotlib.pyplot as plt

二.代码更新（加入更多数据集，爬取多个网站数据，进行可视化显示）

"""""
    作者：cpz
    目的：盐城房价分析
    版本：2.0
    时间：30/07/2019
"""""


import requests
import pandas as pd
from bs4 import BeautifulSoup
import csv
import numpy as np
from matplotlib.pyplot import MultipleLocator
import matplotlib.pyplot as plt
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
def get_building_price(create_utl_list):

    build_name_list = []
    build_price_list = []
    for url in create_utl_list:
        print(url)
        rtext = requests.get(url,timeout=30)
        soup = BeautifulSoup(rtext.text,'lxml')
        buliding_list = soup.find_all('div',{'class':'lp-list'})[0]
        #print(buliding_list)
        building_2_list = buliding_list.find_all('li',{'class':'list-item clearfix'})
        #print(building_2_list)
        #print(rtext.status_code)
        #print(len(building_2_list))

        for build in building_2_list:
            build_name = build.find_all('a',{'class':'tit'})
            build_price_div = build.find_all('div',{'class':'other fr'})
            build_price__em = build_price_div[0].find_all('em',{'class':'arial'})
            build_name_str = build_name[0].text.split('\n')[0]
            build_name_list.append(build_name_str)
            build_price_list.append(build_price__em[0].text)

    #print(build_name_list)
    #print(build_price_list)
    #buildings_name_list = building_2_list.find_all('a',{'class':'tit'})[0]
    #print(buildings_name_list)
    return build_name_list,build_price_list

def get_clean_data(build_name_list,build_price_list):
    build_price__name_int_list = []
    for i in range(len(build_price_list)):
        build_price__name_int_list.append((build_name_list[i],build_price_list[i]))
    print(build_price__name_int_list)
    Header = ['BuildName','Price']
    buildName = []
    buildPrice = []
    with open('yancheng_build_price.csv','w',encoding='utf-8',newline='') as f:
        writer = csv.writer(f)
        writer.writerow(Header)
        for i,build in enumerate(build_price__name_int_list):
            if build[1] !='待定':
                build_name = build[0]
                buildName.append(build_name)
                build_price = int(build[1])
                buildPrice.append(build_price)
                row = [build_name]+[build_price]
                writer.writerow(row)

    return buildName,buildPrice


def Create_url():
    url_list = []
    url_list.append('http://danke00.com/xinfang/1261')
    for i in range(1,5):
        url_list.append('http://danke00.com/xinfang/1261-no-no-no-no-no-no-no-no-no/'+str(i+1))

    #print(url_list)
    return url_list

def main():
    cerate_url = Create_url()
    build_name_list,build_price_list = get_building_price(cerate_url)
    buildName,buildPrice = get_clean_data(build_name_list,build_price_list)
    build_name_price_list = pd.read_csv('yancheng_build_price.csv')
    print(build_name_price_list.info())

    build_name_price_list.plot(kind='line',x='BuildName',y='Price',title='盐城盐都区各在售小区房价曲线图',figsize=(60,5),color='red')
    x = np.arange(len(buildName))
    tickpoints = np.arange(len(buildName))
    plt.xticks(tickpoints, buildName)
    for a,b in zip(x,buildPrice):
        plt.text(a,b,b,ha='center',va='bottom',fontsize='10')
    # x_major_locator = MultipleLocator(1)
    # ax = plt.gca()
    # ax.xaxis.set_major_locator(x_major_locator)

    plt.show()

if __name__ == '__main__':
    main()

 四.总结

不说多少，该换电脑了，才爬了五六个网站，电脑就卡爆了，更不谈建立训练集了

源码：https://github.com/520zyzy/Machine-Learning/tree/master