【python】爬取百度热搜排行榜Top50+可视化

import requests
from bs4 import BeautifulSoup
import matplotlib.pyplot as plt
import numpy as np
 
# 请求URL，获取网页内容
def get_html(url):
    try:
        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)
        return response.text
    except requests.RequestException as e:
        print(e)
        return None
 
# 解析网页，提取热搜词
def parse_html(html):
    soup = BeautifulSoup(html, 'lxml')
    hot_list = soup.find_all('div', class_='title-content')
    hot_searches = [item.text.strip() for item in hot_list]
    return hot_searches
 
# 数据可视化
def visualize(data):
    plt.figure(figsize=(10, 8))
    plt.barh(range(len(data)), np.arange(1, len(data)+1), align='center', color='orange')
    plt.yticks(np.arange(0.5, len(data), 1), data)
    plt.xlabel('热度指数')
    plt.ylabel('搜索词')
    plt.title('百度热搜排行榜')
    plt.show()
 
# 主函数
def main():
    url = 'http://top.baidu.com/buzz?b=1&c=1&class=3&fr=www_v2'
    html = get_html(url)
    data = parse_html(html)
    visualize(data)
 
if __name__ == '__main__':
    main()

这段代码实现了从百度热搜排行榜获取数据，并使用matplotlib进行数据可视化的功能。代码简洁，注重逻辑性和实用性，是学习爬虫和数据可视化的好例子。