酷我音乐按页数爬取榜单top

import csv
import time
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.by import By

# 定义爬虫函数
def crawl_kuwo_top60(url):
    driver = webdriver.Chrome()
    driver.get(url)

    # 计数器，记录已爬取的页数
    page_count = 0

    while page_count < 3:  # 只爬取前三页
        # 等待一段时间，确保页面加载完成
        WebDriverWait(driver, 10).until(EC.presence_of_element_located((By.CSS_SELECTOR, ".page-wrap.pagination")))

        # 获取当前页面的HTML内容
        page_source = driver.page_source

        # 使用 BeautifulSoup 解析 HTML 内容
        soup = BeautifulSoup(page_source, 'html.parser')
        current_page_span = soup.find('span', class_='notCursor currentPage').text.strip()
        print("正在爬取第 " + current_page_span+" 页---")

        # 定位歌曲信息所在的标签
        songs = soup.find_all('li', class_='song_item flex_c')

        # 打开 CSV 文件，准备写入数据
        with open('kuwoTop100.csv', mode='a', newline='', encoding='utf-8') as file:
            writer = csv.writer(file)

            # 遍历歌曲信息，逐行写入 CSV 文件
            for song in songs:
                css_selector = "li > div.song_rank.flex_c > div "
                rank = song.select_one(css_selector).text.strip()
                title = song.select_one('.song_name > a').text.strip()
                artist = song.select_one('.song_artist > span').text.strip()
                times = song.select_one('.song_time > span').text.strip()
                writer.writerow([rank, title, artist, times])

        page_count += 1  # 计数器加一
        if page_count < 3:  # 只有在未达到三页时才点击下一页
            # 查找下一页按钮并点击
            next_button = driver.find_element(By.CSS_SELECTOR,
                                              ".page-wrap.pagination .li-page.iconfont.icon-icon_pagedown")
            # 点击下一页按钮
            driver.execute_script("arguments[0].click();", next_button)
            time.sleep(3)

url = 'https://www.kuwo.cn/playlist_detail/1082685104'
crawl_kuwo_top60(url)

页面点击下一页时，url并不会变，所以需要用使用JavaScript点击：有时，即使元素不可见，也可以使用JavaScript来模拟点击。

element = driver.find_element_by_css_selector("i.li-page.iconfont.icon-icon_pagedown")
driver.execute_script("arguments[0].click();", element)