简单几步爬取王者高清壁纸

王者作为当今热门的游戏，深受各类人群的喜爱，有些人喜欢收集王者高清壁纸放在桌面，那么怎么才能从网络海量图库中收集可用的高清壁纸呢？下面就看看我是怎么样通过爬虫的手段实现高清壁纸收集的。

# coding=utf-8

import requests
import os
import re


url = 'https://pvp.qq.com/web201605/js/herolist.json'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.74 Safari/537.36 Edg/99.0.1150.55'
}
rsp = requests.get(url, headers=headers)
# print(rsp.text)
print(rsp.status_code)
# print(rsp.json())
for index in rsp.json():
    # 获取英雄名字和id
    hero_name = index['cname']
    hero_id = index['ename']

    # filename = f'{hero_name}\\'
    # if not os.path.exists(filename):
    #     os.mkdir(filename)

    index_url = f'https://pvp.qq.com/web201605/herodetail/{hero_id}.shtml'
    # print(hero_name, hero_id, index_url)
    rsp1 = requests.get(url=index_url, headers=headers)
    # rsp1.encoding = 'gbk'
    rsp1.encoding = rsp1.apparent_encoding#自动识别编码
    # print(rsp1.text)
    temp = '<ul class="pic-pf-list pic-pf-list3" data-imgname="(.*?)">'
    title_list = re.findall('<ul class="pic-pf-list pic-pf-list3" data-imgname="(.*?)">', rsp1.text)[0]
    title_list = re.sub('&\d+', '', title_list).split('|')

    for num in range(1, len(title_list) + 1):

        img_url = f'https://game.gtimg.cn/images/yxzj/img201606/skin/hero-info/{hero_id}/{hero_id}-bigskin-{num}.jpg'
        img_title = title_list[num - 1]

        img_data = requests.get(url=img_url, headers=headers).content
        with open('photo/' + img_title + '.jpg', 'wb') as f:
            print(f'=====================正在爬取{hero_name}的皮肤========================')
            f.write(img_data)
        # print(img_title, img_url)