30行Python代码爬取LOL全英雄皮肤

受到~wangweijun的20行Python代码爬取王者荣耀全英雄皮肤的启发
我去试试同样的方法爬取LOL皮肤，果然方法大同小异，毕竟都是腾讯系的
首先进入LOL官网
进入资料库

获取全英雄的详细列表，包括ID、绰号、英文名、中文名等等

url = 'https://game.gtimg.cn/images/lol/act/img/js/heroList/hero_list.js'
herolist = requests.get(url)

以火女皮肤地址为例

https://game.gtimg.cn/images/lol/act/img/skin/big1000.jpg
https://game.gtimg.cn/images/lol/act/img/skin/big1001.jpg
https://game.gtimg.cn/images/lol/act/img/skin/big1002.jpg

找到规律big后面是英雄ID，000、001、002是皮肤编码，只要编辑好这些图片地址，就可以了
接下来完整的代码
现在要存放的地方建一个名为“lol”的文件夹即可

import os
import requests
from urllib import error
import socket

url = 'https://game.gtimg.cn/images/lol/act/img/js/heroList/hero_list.js'
herolist = requests.get(url)  # 获取英雄列表json文件

herolist_json = herolist.json()  # 转化为json格式
hero_name = list(map(lambda x: x['name'], herolist.json()['hero']))  # 提取英雄的绰号
hero_title = list(map(lambda x: x['title'], herolist.json()['hero']))  # 提取英雄的名字
hero_number = list(map(lambda x: x['heroId'], herolist.json()['hero']))  # 提取英雄的编号

headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.120 Safari/537.36'}

# 下载图片
def downloadPic():
    i = 0
    for j in hero_number:
        # 创建文件夹
        os.mkdir("E:\\Picture\\lol\\" + hero_name[i]+"-"+hero_title[i])
        # 进入创建好的文件夹
        os.chdir("E:\\Picture\\lol\\" + hero_name[i]+"-"+hero_title[i])
        i += 1
        for k in range(20):
        	# 拼接url，如果K小于10中间加两个“0”，否则一个“0”
            if k < 10:
                onehero_link = 'https://game.gtimg.cn/images/lol/act/img/skin/big' + str(j) + '00' + str(k) + '.jpg'
            else:
                onehero_link = 'https://game.gtimg.cn/images/lol/act/img/skin/big' + str(j) + '0' + str(k) + '.jpg'
            try:
                im = requests.get(onehero_link,headers=headers)
            except error.URLError as e:
                if isinstance(e.reason,socket.timeout):
                    print('超时，执行下一个请求')
            # 请求url
            if im.status_code == 200:
                open(str(k) + '.jpg', 'wb').write(im.content)  # 写入文件
   

downloadPic()

成果如下



下面这种方法可以爬到皮肤名字

import urllib.request
import jsonpath
import json
import os
import time
from urllib import error
import socket,requests

print("努力成为爬虫大神")
timestart=time.time()
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.120 Safari/537.36'}

if not os.path.exists("json"):
    os.mkdir("json")
for s in range(555, 600):
    try:
        hero_urls = 'https://game.gtimg.cn/images/lol/act/img/js/hero/'+str(s)+'.js'
        j_name = 'json/zms'+str(s)+'.json'
        urllib.request.urlretrieve(url=hero_urls, filename=j_name)
        obj = json.load(open(j_name, 'r', encoding='utf-8'))
        hero_name = jsonpath.jsonpath(obj, '$.hero..name')
        hero_title = jsonpath.jsonpath(obj, '$.hero..title')
        skins_name = jsonpath.jsonpath(obj, '$.skins..name')
        skins_mainImg = jsonpath.jsonpath(obj, '$.skins..mainImg')
        print("开始爬{}".format(hero_name[0]))
        docname = hero_title[0] + " " + hero_name[0]
        if not os.path.exists(docname):
            os.mkdir(docname)
        for i in range(len(skins_name)):
            if skins_mainImg[i] != "":
                try:
                    im = requests.get(skins_mainImg[i],headers=headers)
                    open(docname + "/" + skins_name[i] + ".jpg", 'wb').write(im.content)  # 写入文件
                except error.URLError as e:
                    if isinstance(e.reason,socket.timeout):
                        print('超时，执行下一个请求')
    except:
        continue
timeend=time.time()
print("一共用时：{}秒".format(timeend-timestart))