用python爬取二手房交易信息并进行分析

用python爬取二手房交易信息并分析

1. 第一步：编写爬虫
   爬取某平台上海市十个区共900条二手房的交易信息

#爬取上海十个区的二手房价信息
import requests
from bs4 import BeautifulSoup
import csv

#获取房价的文本信息
def gethousetext(url):
    try:
        r = requests.get(url)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return "error"


# 获得房子的价格、面积、详细信息等
def gethouseinfo(h_list, html, loc):
    h_info = []
    soup = BeautifulSoup(html, "html.parser")
    house_info = soup.find_all('div', attrs={'class': "listX"})
    # 将房屋信息储存在一个列表里
    for h in house_info:
        p = h.find_all('p')
        h_info = [p[0].text, loc, p[2].text, p[3].text, p[4].text]
        h_list.append(h_info)


def storehouseinfo(h_list, fpath):
    # 打开csv文件，写入数据

    with open(fpath, 'w', encoding='utf-8') as f:
        house_csv = csv.wr