爬虫——英雄皮肤

最新推荐文章于 2024-09-13 15:59:37 发布

whitewolf789

最新推荐文章于 2024-09-13 15:59:37 发布

阅读量164

点赞数

文章标签：爬虫 python 开发语言

本文链接：https://blog.csdn.net/whitewolf789/article/details/124828526

版权

import os
import time
import requests
import json
from selenium.webdriver import Chrome
from lxml import etree

def requests_get(href):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/101.0.4951.54 Safari/537.36'
    }
    resp = requests.get(url=href, headers=headers)
    if resp.status_code == 200:
        return resp
    else:
        print(resp.status_code)


def get_skin(num,name):
    char_list = ['*', '|', ':', '?', '/', '<', '>', '"', '\\']
    os.mkdir(f'./英雄皮肤/{name}')
    hero_href = f'https://game.gtimg.cn/images/lol/act/img/js/hero/{num}.js'
    resp = requests_get(hero_href)
    data = resp.json()
    # print(data['skins'],type(data['skins']))
    for skin in data['skins']:
        # print(skin['name'], skin['mainImg'])
        if len(skin['mainImg']) != 0:
            skin_img_url = skin['mainImg']
            resp = requests.get(url=skin_img_url)
            # 替换文件名中系统不支持的字符
            for c in char_list:
                if c in skin['name']:
                    skin['name'] = skin['name'].replace(c,'_')
            print(skin['name'])

            with open(f"./英雄皮肤/{name}/{skin['name']}.jpg", 'wb') as f:
                f.write(resp.content)


b = Chrome()
b.get('https://lol.qq.com/data/info-heros.shtml')
time.sleep(1)
root = etree.HTML(b.page_source)
b.close()
heroes = root.xpath('//ul[@class="imgtextlist"]/li')
for i in heroes:
    href = i.xpath('a/@href')
    serial_number = href[0].split('=')[1]
    print(serial_number)
    hero_name = i.xpath('a/p/text()')
    print(hero_name[0])
    get_skin(serial_number, hero_name[0])


```![共创建159个文件夹](https://img-blog.csdnimg.cn/46ce4e2af9774c25a38c601437f1c850.png)
将皮肤名中的特殊字符进行了替换![在这里插入图片描述](https://img-blog.csdnimg.cn/0013f34e520b4f28b42e2a0a3dc98ead.png)