import requests import json import pandas as pd import time from fake_useragent import UserAgent import random # -------------------------- 配置项 -------------------------- # 网易云音乐榜单ID（2025热歌榜/年度榜可替换此ID） # 热歌榜：3778678 | 年度榜：19723756 | 飙升榜：19723756 BOARD_ID = 3778678 # 请求间隔（防反爬） REQUEST_DELAY = 1.5 # 导出Excel文件名 OUTPUT_FILE = "2025网易云音乐热度分析.xlsx" # -------------------------- 核心爬虫函数 -------------------------- class NeteaseMusicSpider: def __init__(self): # 随机User-Agent（模拟浏览器） self.ua = UserAgent() self.headers = { "User-Agent": self.ua.random, "Referer": "https://music.163.com/", "Cookie": "appver=8.9.0; os=pc;" # 可替换成自己的Cookie（可选） } # 存储最终数据 self.music_data = [] def get_board_songs(self, board_id): """爬取指定榜单的歌曲列表""" # 榜单接口URL url = f"https://music.163.com/api/playlist/detail?id={board_id}" try: # 发送请求（添加随机延迟防封） time.sleep(random.uniform(REQUEST_DELAY, REQUEST_DELAY + 1)) response = requests.get(url, headers=self.headers, timeout=10) response.raise_for_status() # 抛出HTTP错误 # 解析JSON数据 data = json.loads(response.text) songs = data["result"]["tracks"] # 遍历提取核心信息 for song in songs: # 基础信息 song_info = { "排名": len(self.music_data) + 1, "歌曲名": song["name"], "歌手": "/".join([artist["name"] for artist in song["artists"]]), "专辑": song["album"]["name"], "时长": self.format_duration(song["duration"]), "播放量": self.get_play_count(song["id"]), # 单独获取播放量 "热度值": song.get("popularity", 0), # 热度指数 "收藏数": song.get("likedCount", 0), "评论数": self.get_comment_count(song["id"]) # 单独获取评论数 } self.music_data.append(song_info) print(f"已爬取：{song_info['排名']}. {song_info['歌曲名']} - {song_info['歌手']}") except Exception as e: print(f"爬取榜单失败：{e}") def get_play_count(self, song_id): """获取歌曲播放量（补充接口）""" try: url = f"https://music.163.com/api/song/detail/?id={song_id}&ids=[{song_id}]" response = requests.get(url, headers=self.headers, timeout=5) data = json.loads(response.text) # 部分歌曲播放量字段不同，做兼容 play_count = data["songs"][0].get("playCount", 0) return self.format_number(play_count) except: return "未知" def get_comment_count(self, song_id): """获取歌曲评论数""" try: url = f"https://music.163.com/api/v1/resource/comments/R_SO_4_{song_id}/?limit=1" response = requests.get(url, headers=self.headers, timeout=5) data = json.loads(response.text) comment_count = data.get("total", 0) return self.format_number(comment_count) except: return "未知" @staticmethod def format_duration(duration): """格式化时长（毫秒→分:秒）""" minutes = duration // 60000 seconds = (duration % 60000) // 1000 return f"{minutes}:{seconds:02d}" @staticmethod def format_number(num): """格式化数字（万/亿单位）""" if num >= 1e8: return f"{num / 1e8:.2f}亿" elif num >= 1e4: return f"{num / 1e4:.2f}万" else: return str(num) def save_to_excel(self): """将数据导出为Excel""" try: df = pd.DataFrame(self.music_data) # 按热度值降序排序 df = df.sort_values(by="热度值", ascending=False) # 保存Excel（忽略索引） df.to_excel(OUTPUT_FILE, index=False, engine="openpyxl") print(f"\n✅ 数据已成功导出至：{OUTPUT_FILE}") print(f"📊 共爬取 {len(self.music_data)} 首歌曲") except Exception as e: print(f"保存Excel失败：{e}") # -------------------------- 运行爬虫 -------------------------- if __name__ == "__main__": print("===== 2025网易云音乐热度爬虫开始运行 =====") spider = NeteaseMusicSpider() # 1. 爬取榜单数据 spider.get_board_songs(BOARD_ID) # 2. 数据清洗（去重） df_temp = pd.DataFrame(spider.music_data) df_temp = df_temp.drop_duplicates(subset=["歌曲名", "歌手"], keep="first") spider.music_data = df_temp.to_dict("records") # 3. 导出Excel spider.save_to_excel() print("===== 爬虫运行结束 =====")
