import requests
from bs4 import BeautifulSoup
import xlwt
headers={'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.88 Safari/537.36'}
url = "https://www.kugou.com/yy/rank/home/1-8888.html?from=rank"
html_code = requests.get(url,headers=headers)
html_code.encoding = "utf-8"
# print(html_code.text)
soup = BeautifulSoup(html_code.text,"html.parser")
li_all = soup.find(class_="pc_temp_songlist").find_all("li")
song_name = []
song_duration = []
for li_s in li_all:
song_name.append(li_s.get("title"))
for s_d in soup.find_all("span",attrs={"class":"pc_temp_time"}):
song_duration.append(s_d.get_text().replace("\n","").replace("\t",""))
print(song_name,song_duration)
print(len(song_name),len(song_duration))
head = ["歌曲名称","歌曲时长"]
workbook = xlwt.Workbook()
sheet = workbook.add_sheet("sheet1")
sheet.col(0).width = 8000
for i in range(len(head)):
sheet.write(0,i,head[i])
for i in range(len(song_name)):
sheet.write(i+1, 0, song_name[i])
for i in range(len(song_duration)):
sheet.write(i+1, 1, song_duration[i])
workbook.save("test.xlsx")
写出excel截图:
发现这篇文章的代码挺好的:
https://blog.csdn.net/springhammer/article/details/88650068