python爬虫demo——爬取历史平均房价

news2024/11/18 11:36:35

简单爬取历史房价

需求

爬取的网站汇聚数据的城市房价
https://fangjia.gotohui.com/

功能

选择城市
https://fangjia.gotohui.com/fjdata-3
在这里插入图片描述

需要爬取年份的数据，等等
https://fangjia.gotohui.com/years/3/2018/
在这里插入图片描述

使用bs4模块

使用bs4模块快速定义需要爬取的表格

在这里插入图片描述

代码

from urllib.request import urlopen

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


headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36 Edg/108.0.1462.54'}

# 发送网络请求获取网页内容
def get_page_data(data_url, headers):
    req = urllib.request.Request(data_url, headers=headers)
    content = urllib.request.urlopen(req).read()  # .decode('GBK')
    content = content.decode('utf-8')  # python3
    page = BeautifulSoup(content, 'html.parser')
    return page

# 按格式输出价格
def get_date(date, year):
    date_str = ''
    if date == '1月':
        date_str = year + '-' + '01'
    elif date == '2月':
        date_str = year + '-' + '02'
    elif date == '3月':
        date_str = year + '-' + '03'
    elif date == '4月':
        date_str = year + '-' + '04'
    elif date == '5月':
        date_str = year + '-' + '05'
    elif date == '6月':
        date_str = year + '-' + '06'
    elif date == '7月':
        date_str = year + '-' + '07'
    elif date == '8月':
        date_str = year + '-' + '08'
    elif date == '9月':
        date_str = year + '-' + '09'
    elif date == '10月':
        date_str = year + '-' + '10'
    elif date == '11月':
        date_str = year + '-' + '11'
    elif date == '12月':
        date_str = year + '-' + '12'
    return date_str


# 使用bs4内网页内容进行提取
def analyse_data(page, year):
    table = page.find('table', attrs={'class': 'ntable table-striped'})
    trs = table.find_all('tr')[3:]
    df_data = pd.DataFrame(columns=['date', 'price'])
    time.sleep(1)
    count = 0

    for tr in trs:
        tds = tr.find_all('td')
        date = tds[0].text
        date = get_date(date,year)
        new = tds[1].text
        new = new[:6]
        df_data.loc[count] = [date, new]
        count += 1
    return df_data


if __name__ == '__main__':

    data_url = 'https://fangjia.gotohui.com/fjdata-3'
    year = ['2011', '2012', '2013', '2014', '2015', '2016', '2017', '2018', '2019', '2020', '2021', '2022', '2023']
    all_datas = []
    file_path = "data.txt"

    # 遍历多年的数据
    for i in year:
        url = 'https://fangjia.gotohui.com/years/3/' + i + '/'
        page = get_page_data(url, headers)
        df_data = analyse_data(page, i)
        print(df_data)
        # 将数据保存到txt文件文件中，（存在编码问题后续解决）
        df_data1 = str(df_data)
        with open(file_path, 'a',encoding='utf-8') as file:
            file.write(df_data1)