Python江苏南京二手房源爬虫数据可视化系统设计与实现

import requests
from bs4 import BeautifulSoup
import pandas as pd
import matplotlib.pyplot as plt
 
# 获取房源数据
def get_data(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3'}
    response = requests.get(url, headers=headers)
    soup = BeautifulSoup(response.text, 'html.parser')
    data = soup.find_all('div', class_='info-panel')
    return data
 
# 解析数据并存储
def parse_and_store_data(data):
    houses = []
    for house in data:
        title = house.find('div', class_='title').text
        price = house.find('div', class_='price').text
        address = house.find('div', class_='address').text
        house_info = {
            'title': title,
            'price': price,
            'address': address
        }
        houses.append(house_info)
    df = pd.DataFrame(houses)
    df.to_csv('houses.csv', index=False)
 
# 读取数据并进行可视化分析
def visualize_data(csv_file):
    df = pd.read_csv(csv_file)
    # 可以在此处添加更多的数据可视化分析，例如：
    # 1. 价格分布直方图
    plt.hist(df['price'].str.replace('元/月', '').astype('int64'), bins=50)
    plt.xlabel('Price')
    plt.ylabel('Count')
    plt.title('Histogram of House Prices')
    plt.show()
 
# 主函数
def main():
    url = 'https://sou.zhaopin.com/jobs/searchresult.htm?keyword=Python&city_id=400000&district_id=&business_id=&employment_type=&job_nature_id=&degree_id=&position_id=&page=1&ka=page-1'
    data = get_data(url)
    parse_and_store_data(data)
    visualize_data('houses.csv')
 
if __name__ == '__main__':
    main()

这段代码示例展示了如何使用Python爬取南京的二手房源数据，并使用Pandas和Matplotlib进行数据可视化。代码简洁，注重逻辑性和实用性，可以作为学习爬虫和数据分析的入门示例。