def hero_skin():
import json
import os
import requests
from bs4 import BeautifulSoup
headers = {'user-agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Safari/537.36'}
hero_prefix = 'https://pvp.qq.com/web201605/herodetail/'
skin_prefix = 'http://game.gtimg.cn/images/yxzj/img201606/skin/hero-info/'
def get_heroes():
data_url = 'https://pvp.qq.com/web201605/js/herolist.json'
r = requests.get(data_url, headers)
return json.loads(r.text)
def process_hero(hero):
hero_id = str(hero['ename'])
hero_name = hero['cname']
hero_path = os.path.join("皮肤", hero_name)
if not os.path.isdir(hero_path): os.mkdir(hero_path)
hero_url = hero_prefix + hero_id + '.shtml'
r = requests.get(hero_url, headers)
text = r.text.encode('iso-8859-1').decode('gbk')
soup = BeautifulSoup(text, 'lxml')
skins = soup.select('ul.pic-pf-list.pic-pf-list3')[0].get('data-imgname').split('|')
for i in range(len(skins)):
# 页面信息是动态加载出来得，不能直接提取，需要拼装(下载大图)
img_url = skin_prefix + hero_id + '/' + hero_id + '-bigskin-' + str(i + 1) + '.jpg'
r = requests.get(img_url, headers)
with open(hero_path + '/' + skins[i] + '.jpg', 'wb+') as f:
f.write(r.content)
print(hero_name + '有' + str(len(skins)) + '张皮肤')
for hero in get_heroes():
process_hero(hero)
hero_skin()
