爬虫使用Beautiful Soup爬取网页信息示例代码（酷dog音乐）

import requests
from bs4 import BeautifulSoup
 
# 定义函数来获取页面内容
def get_page_content(url):
    try:
        response = requests.get(url)
        if response.status_code == 200:
            return response.text
        else:
            return None
    except requests.RequestException:
        return None
 
# 定义函数来解析页面和提取音乐信息
def parse_and_extract_music_info(html):
    soup = BeautifulSoup(html, 'html.parser')
    music_info = {}
    
    # 提取标题
    title = soup.find('h1', class_='title').get_text(strip=True)
    music_info['title'] = title
    
    # 提取作者
    author = soup.find('a', class_='author').get_text(strip=True)
    music_info['author'] = author
    
    # 提取发布日期
    publish_date = soup.find('span', class_='publish-time').get_text(strip=True)
    music_info['publish_date'] = publish_date
    
    # 提取播放次数
    play_count = soup.find('span', class_='count').get_text(strip=True)
    music_info['play_count'] = play_count
    
    # 提取音乐链接
    audio_element = soup.find('audio')
    if audio_element and 'src' in audio_element.attrs:
        music_url = audio_element.attrs['src']
        music_info['music_url'] = music_url
    
    return music_info
 
# 定义要爬取的页面URL
url = 'https://www.essaydog.com/music/12345.html'
 
# 获取页面内容
html_content = get_page_content(url)
 
# 如果页面内容存在，则解析页面并提取音乐信息
if html_content:
    music_info = parse_and_extract_music_info(html_content)
    print(music_info)
else:
    print("页面内容获取失败")

这段代码首先定义了get_page_content函数来获取指定URL的页面内容，然后定义了parse_and_extract_music_info函数来解析页面并提取音乐信息。最后，我们设置了要爬取的页面URL，执行这两个函数，并打印提取到的音乐信息。