爬虫豆瓣音乐 top250

最新推荐文章于 2024-05-13 15:07:13 发布

小陈＃！

最新推荐文章于 2024-05-13 15:07:13 发布

阅读量318

点赞数

文章标签： python 爬虫

本文链接：https://blog.csdn.net/Arensin/article/details/112464991

版权

豆瓣音乐top250爬取，并将内容写入文件

from urllib.request import Request, urlopen
import bs4
import requests
import re
import json
import xlwt

workbook = xlwt.Workbook(encoding='utf-8')
worksheet = workbook.add_sheet('sheet1', cell_overwrite_ok=True)
worksheet.write(0, 0, label='歌名')
worksheet.write(0, 1, label='歌手')
worksheet.write(0, 2, label='时间')
worksheet.write(0, 3, label='类型')
worksheet.write(0, 4, label='评分')
z = 1
url=('https://music.douban.com/top250?start=0')#.format(i)
header = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36'}
ret = Request(url=url, headers=header)
html = urlopen(ret)
bs = bs4.BeautifulSoup(html, 'html.parser')



alls = bs.find_all('div',{'class':'pl2'})
for x in alls:
    music_name = x.find('a').get_text()
    leixing = x.find('p').get_text().split('/ ')
    score = x.find('span',{'class':'rating_nums'}).get_text()
    singer = leixing[0]
    time = leixing[1]
    type = leixing[-1]
    # print(leixing)

    worksheet.write(z,0,music_name)
    worksheet.write(z,1, singer)
    worksheet.write(z,2,time)
    worksheet.write(z,3,type)
    worksheet.write(z,4,score)
    z += 1
workbook.save('yinyue.xls')