30行Python代碼爬取LOL全英雄皮膚

受到~wangweijun的20行Python代碼爬取王者榮耀全英雄皮膚的啓發
我去試試同樣的方法爬取LOL皮膚，果然方法大同小異，畢竟都是騰訊系的
首先進入LOL官網
進入資料庫

獲取全英雄的詳細列表，包括ID、綽號、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)

以火女皮膚地址爲例

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

找到規律big後面是英雄ID，000、001、002是皮膚編碼，只要編輯好這些圖片地址，就可以了
接下來完整的代碼
現在要存放的地方建一個名爲“lol”的文件夾即可

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)  # 獲取英雄列表json文件

herolist_json = herolist.json()  # 轉化爲json格式
hero_name = list(map(lambda x: x['name'], herolist.json()['hero']))  # 提取英雄的綽號
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']))  # 提取英雄的編號

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'}

# 下載圖片
def downloadPic():
    i = 0
    for j in hero_number:
        # 創建文件夾
        os.mkdir("E:\\Picture\\lol\\" + hero_name[i]+"-"+hero_title[i])
        # 進入創建好的文件夾
        os.chdir("E:\\Picture\\lol\\" + hero_name[i]+"-"+hero_title[i])
        i += 1
        for k in range(20):
        	# 拼接url，如果K小於10中間加兩個“0”，否則一個“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('超時，執行下一個請求')
            # 請求url
            if im.status_code == 200:
                open(str(k) + '.jpg', 'wb').write(im.content)  # 寫入文件
   

downloadPic()

成果如下



下面這種方法可以爬到皮膚名字

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

print("努力成爲爬蟲大神")
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("開始爬{}".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)  # 寫入文件
                except error.URLError as e:
                    if isinstance(e.reason,socket.timeout):
                        print('超時，執行下一個請求')
    except:
        continue
timeend=time.time()
print("一共用時：{}秒".format(timeend-timestart))