Python数据分析实战：上海二手房价分析

1 数据搜集

使用 urllib 库中的request 模块爬取赶集网发布的上海二手房信息，包括包括户型、面积、单价等，再使用BeautifulSoup 库解析爬取的HTML数据，最终将数据保存到CSV文件中。

import urllib.request
from bs4 import BeautifulSoup
import pandas as pd

#爬取数据
def request_Data(url):

    #创建requests对象
    req = urllib.request.Request(url)
    
    page_data_list = []
    
    with urllib.request.urlopen(req) as response:
        data = response.read()
        htmlstr = data.decode()
        L = parse_HTMLData(htmlstr)
        page_data_list.extend(L)
    
    return page_data_list


#解析数据
def parse_HTMLData(htmlstr):
    
    sp = BeautifulSoup(htmlstr,'html.parser')
    
    #获得房子信息列表
    house_list = sp.select('#f_mew_list > div.f-main.f-clear.f-w1190 > div.f-main-left.f-fl.f-w980 > div.f-main-list > div > div')
   
    #当前页中的记录列表
    page_list = []
    for house in house_list:
        #每一行数据
        rows_list = []
        
        #获得房子标题
        title = house.select('dl > dd.dd-item.title > a')
        title = (title[0].text).strip()
        rows_list.append(title)
        
        #获得房子信息
        infos = house.select('dl > dd.dd-item.size > span')
        # 获得房子户型
        house_type = (infos[0].text).strip()
        rows_list.append(house_type)
        # 获得房子面积
        house_area = (infos[2].text).strip()
        rows_list.append(house_area)
        # 获得房子面积
        house_face = (infos[4].text).strip()
        rows_list.append(house_face)
        # 获得房子楼层
        house_floor = (infos[6].text).strip()
        rows_list.append(house_floor)
        #获得房子所在城区
        addr_dist = house.select('dl > dd.dd-item.address > span > a.address-eara')
        addr_dist = (addr_dist[0].text).strip()
        rows_list.append(addr_dist)
        #获得房子所在小区
        addr_name = house.select('dl > dd.dd-item.address > span > a > span')
        addr_name = (addr_name[0].text).strip()
        rows_list.append(addr_name)
        #获得房子总价
        total_price = house.select('dl > dd.dd-item.info > div.price')
        total_price = (total_price[0].text).strip()
        rows_list.append(total_price)
        #获得房子单价
        price = house.select('dl > dd.dd-item.info > div.time')
        price = (price[0].text).strip()
        rows_list.append(price)
           
        page_list.append(rows_list)
        
    return page_list
        

url_temp = 'http://sh.ganji.com/ershoufang/pn{}/'

data_list