爬取酷狗音乐排行榜单

最新推荐文章于 2024-07-18 20:42:20 发布

MartinYangHJ

最新推荐文章于 2024-07-18 20:42:20 发布

阅读量598

点赞数

分类专栏： python

本文链接：https://blog.csdn.net/yhj198927/article/details/88828517

版权

python 专栏收录该内容

13 篇文章 0 订阅

订阅专栏

import time
import requests
from bs4 import BeautifulSoup
from pymongo import MongoClient

client=MongoClient()
songs=client.kugou_db.songs

header={
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36'
}
def get_info(url):
    wb_data=requests.get(url,headers=header)
    soup=BeautifulSoup(wb_data.text,'html.parser',from_encoding='utf-8')
    #soup.select()方法中对应的参数为：检查--》copy--》copy selector
    ranks=soup.select('.pc_temp_num')
    titles=soup.select('.pc_temp_songlist > ul > li > a')
    song_times=soup.select('.pc_temp_time')
    for rank,title,song_time in zip(ranks,titles,song_times):
        data={
            'rank': str(rank.get_text().strip()),
            'singer': title.get_text().split('-')[0].strip(),
            'song_name': title.get_text().split('-')[1].strip(),
            'time':song_time.get_text().strip(),
        }
        print(data)
        #存入数据库
        song_id=songs.insert(data)
        print(song_id)
        #output_html(data)
        print('----------------------------')
import  json
#存为Json文件
def output_html(data):
    jsObj = json.dumps(data,ensure_ascii=False).encode('utf-8')
    foutput = open('output1.json', 'a')
    foutput.write(jsObj)
    foutput.close()


if __name__ == '__main__':
    #range范围可以通过页面数据获取到，此处没有如此做
    urls=['http://www.kugou.com/yy/rank/home/{}-8888.html?from=rank'.format(str(i)) for i in range(1,24)]
    for url in urls:
        get_info(url)
        time.sleep(1)