import requests
from lxml import html
import os
url = 'https://game.gtimg.cn/images/lol/act/img/js/heroList/hero_list.js'
#UA伪装: 让爬虫对应的请求载体标识伪装成一款浏览器,将对应的User-Agent封装到字典
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/106.0.0.0 Safari/537.36'
}
response = requests.get(url,headers=headers)
page_text = response.json()
print(page_text)
if not os.path.exists('./lol'):
os.makedirs('./lol')
hero_list = page_text['hero']
print(hero_list)
for hero in hero_list:
print(hero)
path = './lol/'+hero['name'] + '/'
os.makedirs(path)
audio = requests.get(hero['selectAudio'],headers=headers).content
#取文件名
name = hero['selectAudio'].split('/')[-1]
#print(name)
with open(path+name,'wb') as fp:
fp.write(audio)
print('下载完成')
运行第二次时，需要将lol文件夹删除才能继续运行
标签：联盟,hero,name,lol,headers,英雄,print,path,下载 From： https://www.cnblogs.com/145g/p/16897304.html