用python爬取王者荣耀皮肤

王者荣耀皮肤爬取

满满干货，可以在下方留言一起交流，有需要的拿去，正在持续学习，会更新爬虫相关的文章。

# -*- coding:utf-8 -*-
"""
Created at 21:27 at Mar 17,2020
@author: QingLiu
"""

import requests
import os
import json
import time

time.perf_counter()
def get_html():
    try:
        # 全英雄列表请求链接
        herolist_url = 'https://pvp.qq.com/web201605/js/herolist.json'
        # 隐藏头部
        kv = {'user-agent': 'Mozilla/5.0'}
        # 获取数据
        response = requests.get(herolist_url,headers=kv,timeout=20)   #或者提前response = requests.get(herolist_url).json()
        response.raise_for_status()
        txt = response.text
        py_txt = json.loads(txt)
        return py_txt
    except:
        print("异常")


def return_info(py_txt):
    # 根据英雄的皮肤链接，分析并下载英雄的皮肤
    save_dir = "D://honors//"
    if not os.path.exists(save_dir):
        os.mkdir(save_dir)

    for each in py_txt:
        if each.get('skin_name',False):
            # 获取皮肤列表，并做切分
            skin_names = each['skin_name'].split('|')
            hero_num = each['ename']  # 英雄序号
            hero_name = each['cname']  # 英雄名称
            for i in range(len(skin_names)):
                skin_name = skin_names[i]  # 单个皮肤名称
                # 生成文件存放地址
                save_file_name = save_dir + str(hero_num) + "-" + hero_name + "-" + skin_name + '.jpg'
                # 生成皮肤url链接
                skin_url_name = 'http://game.gtimg.cn/images/yxzj/img201606/skin/hero-info/{}/{}-bigskin-{}.jpg'.format(hero_num, hero_num, str(i+1))
                # 获取图片的位数据(二进制流数据)
                response = requests.get(skin_url_name)
                # 保存文件
                with open(save_file_name,'wb') as f:
                    f.write(response.content)
        elif each.get('hero_type2',False):
            hero_num = each['ename']  # 英雄序号
            hero_name = each['cname']  # 英雄名称
            # 生成文件存放地址
            save_file_name = save_dir + str(hero_num) + "-" + hero_name + "-" + '.jpg'
            # 生成皮肤url链接
            skin_url_name = 'http://game.gtimg.cn/images/yxzj/img201606/skin/hero-info/{}/{}-bigskin-1.jpg'.format(hero_num, hero_num)
            # 获取图片的位数据(二进制流数据)
            response = requests.get(skin_url_name)
            # 保存文件
            with open(save_file_name, 'wb') as f:
                f.write(response.content)
        else:
            print('没有爬取完')

def main():
    py = get_html()
    return_info(py)
    print(f"爬取时间共运行{time.perf_counter()}")

if __name__ == '__main__':
    main()

为梦起航