Python爬取英雄联盟官网图片

脚本下载图片预览—草丛三兄弟

#encoding = gbk
import re,os,requests,json
from selenium import webdriver
import pprint,time

# https://lol.qq.com/data/info-defail.shtml?id=103
# https://game.gtimg.cn/images/lol/act/img/skin/big103003.jpg
def down(img_url,hero_name):
	headers={'user-agent':'Mozilla/5.0'}
	response=requests.get(img_url,headers=headers)
	data=response.content
	os.makedirs(f'/home/liyipeng/spider/legend/{hero_name}',exist_ok=True)
	name_path=f'/home/liyipeng/spider/legend/{hero_name}/{time.time()}.jpg'
	with open(name_path,'wb') as f:
		f.write(data)


def get_name_id(hero_id,hero_name):
	url=f'https://game.gtimg.cn/images/lol/act/img/js/hero/{hero_id}.js'
	headers={'user-agent':'Mozilla/5.0'}
	response=requests.get(url,headers=headers)
	data_list = json.loads(response.text)
	print(type(data_list),'data_list')    #dict
	skins=data_list['skins']   #字典型通过keys访问值
	print(type(skins),'skins')     #list
	# pprint.pprint(skins)    #list 通过下标查看，由于list中又包含dict,先循环输出每个字典，再提取出mainimg
	print(len(skins))
	for v in skins:      #现在V是dict
		# print(type(v),'v')   #v是dict
		img_url1 = v['mainImg']   #未经挑选的url
		if len(img_url1)>3:
			img_url = img_url1  #现在是经过挑选的图片的url
			print(img_url)
			down(img_url,hero_name)     #开始传参下载


def get_heros():
	url = 'https://game.gtimg.cn/images/lol/act/img/js/heroList/hero_list.js'
	headers={'user-agent':'Mozilla/5.0'}
	response=requests.get(url,headers=headers)
	data_list = json.loads(response.text)
	print(type(data_list),'data_list')    #还是dict，keys取值
	# pprint.pprint(data_list)
	hero = data_list['hero']      #列表list ，循环取值
	# pprint.pprint(hero)          
	print(type(hero))
	for v in hero:                #两个dict, keys取值
		hero_id = v['heroId']       #英雄id
		n = v['name']
		t = v['title']
		hero_name = f'{n}-{t}'      #英雄name
		# print(hero_name,hero_id)
		get_name_id(hero_id,hero_name)    #开始传id，传name参数
		print(hero_name+'   开始下载')
		

	
get_heros()

总结一下，联盟官网比王者官网架构要复杂的多了，要做的提取工作也非常多 。

                                              ^(*￣(oo)￣)^