基于python的网络爬虫爬取天气数据及可视化分析

import requests
import json
import pandas as pd
from datetime import datetime
import matplotlib.pyplot as plt
 
# 设置请求头，模拟浏览器访问
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'}
 
# 获取城市代码
def get_city_code(city_name, api_url):
    params = {'search': city_name, 'token': 'your_token'}
    response = requests.get(api_url, headers=headers, params=params)
    data = response.json()
    return data[0]['id']
 
# 获取天气数据
def get_weather_data(city_code, api_url):
    params = {'city': city_code, 'token': 'your_token'}
    response = requests.get(api_url, headers=headers, params=params)
    data = response.json()
    return data['data']['realtime']
 
# 保存数据到CSV
def save_data_to_csv(data, filename):
    with open(filename, 'w', encoding='utf-8') as f:
        f.write(json.dumps(data, ensure_ascii=False))
 
# 读取CSV数据
def read_csv_data(filename):
    data = pd.read_csv(filename, encoding='utf-8')
    return data
 
# 绘制天气变化图
def plot_weather_change(dataframe, column_name):
    dataframe.set_index('date', inplace=True)
    dataframe.index = pd.to_datetime(dataframe.index)
    plt.figure(figsize=(10, 5))
    plt.plot(dataframe.index, dataframe[column_name], 'b')
    plt.title('Weather Change over Time')
    plt.xlabel('Date')
    plt.ylabel(column_name)
    plt.show()
 
# 使用示例
city_name = '北京'
api_url = 'https://tianqiapi.com/api/'
city_code = get_city_code(city_name, api_url)
weather_data = get_weather_data(city_code, api_url)
 
# 天气数据处理
weather_data['date'] = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
save_data_to_csv(weather_data, 'weather_data.csv')
dataframe = read_csv_data('weather_data.csv')
 
# 绘制天气变化图
plot_weather_change(dataframe, 'tem')  # 绘制温度变化图
plot_weather_change(dataframe, 'humidity')  # 绘制湿度变化图

这段代码提供了一个简化的例子，展示了如何使用Python进行网络爬取，处理数据，并进行可视化分析。需要注意的是，实际应用中应该使用适当的异常处理、错误处理机制，并遵守API使用协议及网络爬取的法律规定。