实现思路：分为两部分，第一部分，获取网页上数据并使用xlwt生成excel（当然你也可以选择保存到数据库），第二部分获取网页数据使用IO流将图片保存到本地
一、爬取所有英雄属性并生成excel
1.代码
import json
import requests
import xlwt
# 设置头部信息，防止被检测出是爬虫
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.116 Safari/537.36'
}
url = "https://game.gtimg.cn/images/lol/act/img/js/heroList/hero_list.js"
response = requests.get(url=url, headers=headers).text
loads = json.loads(response)
dic = loads['hero']
# 创建一个workbook 设置编码
workbook = xlwt.Workbook(encoding='utf-8')
# 创建一个worksheet
worksheet = workbook.add_sheet('LOL')
try:
for i in range(len(dic)):
# 设置单元格宽度大小
worksheet.col(i).width = 4000
# 设置单元格高度大小
style = xlwt.easyxf('font:height 300')
worksheet.row(i).set_style(style)
# 第一行用于写入表头
if i == 0:
worksheet.write(i, 0, '编号')
worksheet.write(i, 1, '名称')
worksheet.write(i, 2, '英文名')
worksheet.write(i, 3, '中文名')
worksheet.write(i, 4, '角色')
worksheet.write(i, 5, '物攻')
worksheet.write(i, 6, '物防')
worksheet.write(i, 7, '魔攻')
worksheet.write(i, 8, '魔防')
continue
worksheet.write(i, 0, dic[i - 1]['heroId'])
worksheet.write(i, 1, dic[i - 1]['name'])
worksheet.write(i, 2, dic[i - 1]['alias'])
worksheet.write(i, 3, dic[i - 1]['title'])
roles_ = dic[i - 1]['roles']
roles = []
for data in roles_:
if 'mage' == data:
roles.append('法师')
if 'tank' == data:
roles.append('坦克')
if 'fighter' == data:
roles.append('战士')
if 'marksman' == data:
roles.append('ADC')
if 'assassin' == data:
roles.append('刺客')
if 'support' == data:
roles.append('辅助')
worksheet.write(i, 4, str(roles))
worksheet.write(i, 5, dic[i - 1]['attack'])
worksheet.write(i, 6, dic[i - 1]['defense'])
worksheet.write(i, 7, dic[i - 1]['magic'])
worksheet.write(i, 8, dic[i - 1]['difficulty'])
# 保存
workbook.save('C:\\Users\\Jonsson\\Desktop\\lol.xls')
except Exception as e:
print(e)
2.效果
二、爬取所有英雄皮肤并保存到本地
1.代码
import json
import os
import requests
import xlwt
# 设置头部信息，防止被检测出是爬虫
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.116 Safari/537.36'
}
url = "https://game.gtimg.cn/images/lol/act/img/js/heroList/hero_list.js"
# 请求英雄列表的url地址
response = requests.get(url=url, headers=headers).text
loads = json.loads(response)
dic = loads['hero']
for data in dic:
id_ = data['heroId']
skinUrl = 'https://game.gtimg.cn/images/lol/act/img/js/hero/%s.js' % id_
# 请求每个英雄皮肤的url地址
skinResponse = requests.get(url=skinUrl, headers=headers).text
json_loads = json.loads(skinResponse)
hero_ = json_loads['hero']
save_path = './skin/%s-%s-%s' % (hero_["heroId"], hero_['name'], hero_['title'])
# 文件夹不存在，则创建文件夹
folder = os.path.exists(save_path)
if not folder:
os.makedirs(save_path)
skins_ = json_loads['skins']
for data in skins_:
if data['chromas'] == '0':
content = requests.get(url=data['mainImg'], headers=headers).content
try:
with open('%s/%s.jpg' % (save_path, data['name']), "wb") as f:
print("正在下载英雄：%s 皮肤名称：%s ..." % (hero_['name'], data['name']))
f.write(content)
except Exception as e:
print('下载失败')
print(e)
2.效果
