Python 爬虫项目实战：爬取某云热歌榜歌曲

import requests
from bs4 import BeautifulSoup
import pandas as pd
 
# 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'}
 
def get_html(url):
    """发送请求，获取网页内容"""
    response = requests.get(url, headers=headers)
    if response.status_code == 200:
        return response.text
    return None
 
def parse_html(html):
    """解析网页，提取数据"""
    soup = BeautifulSoup(html, 'lxml')
    ranks = soup.find_all(class_='num')
    songs = soup.find_all(class_='song-name')
    artists = soup.find_all(class_='singer-name')
    
    data = {
        '排名': [rank.get_text() for rank in ranks],
        '歌名': [song.get_text() for song in songs],
        '艺人': [artist.get_text() for artist in artists]
    }
    return data
 
def save_data(data, filename):
    """保存数据到CSV文件"""
    df = pd.DataFrame(data)
    df.to_csv(filename + '.csv', index=False, encoding='utf-8-sig')
 
def main():
    """主函数，控制流程"""
    url = 'https://music.163.com/#/discover/toplist?id=3778678'
    html = get_html(url)
    data = parse_html(html)
    save_data(data, '云音乐热歌榜')
 
if __name__ == '__main__':
    main()

这段代码实现了获取某云音乐热歌榜的信息，提取了歌名、艺人和排名，并将其保存到CSV文件中。代码使用了requests库来发送HTTP请求，使用BeautifulSoup库来解析网页，使用pandas库来保存数据。同时，代码中加入了请求头来模拟浏览器访问，以避免被反爬机制阻止。