第四节：爬取王者荣耀英雄皮肤实战

课程目标

• 爬取王者荣耀英雄皮肤实战

课程内容

编码实现

爬虫部分

python">import requests  # 导入requests库，用于发送HTTP请求
from fake_useragent import UserAgent  # 导入UserAgent库，用于生成随机的User-Agent
import time  # 导入time库，用于添加延时
import bs4  # 导入BeautifulSoup库，用于解析HTMLimport os  # 导入os库，用于操作文件系统# 设置目标网页的URL
url = "https://pvp.qq.com/web201605/herolist.shtml" # 创建UserAgent对象，用于生成随机User-Agent
us = UserAgent()# 设置HTTP请求的headers，模拟浏览器访问
headers = {"accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7","accept-language": "zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6","cache-control": "max-age=0","priority": "u=0, i","sec-ch-ua": "\"Chromium\";v=\"128\", \"Not;A=Brand\";v=\"24\", \"Microsoft Edge\";v=\"128\"","sec-ch-ua-mobile": "?0","sec-ch-ua-platform": "\"Windows\"","sec-fetch-dest": "document","sec-fetch-mode": "navigate","sec-fetch-site": "none","sec-fetch-user": "?1","upgrade-insecure-requests": "1","user-agent": us.random  # 使用UserAgent生成的随机User-Agent
}# 发送GET请求获取网页内容
res = requests.get(url=url, headers=headers)# 修改相应内容解码，因为网页编码可能是GBK
html_text = res.content.decode('gbk')# 使用BeautifulSoup解析HTML内容
soup = bs4.BeautifulSoup(html_text, 'html.parser')# 找到包含英雄列表的<ul>标签
ul = soup.find("ul", {"class": "herolist clearfix"})# 找到所有<li>标签，代表每个英雄
lis = ul.find_all('li')# 设置图片保存的目录
save_dir = "imgs"
os.makedirs(save_dir, exist_ok=True)  # 如果目录不存在，则创建它# 遍历每个英雄的<li>标签
for li in lis:# 获取英雄图片的URLsrc = li.a.img.get('src')# 获取英雄的名字name = li.a.img.get('alt')# 补全图片URLsrc_url = "https:" + src# 发送请求下载图片img_res = requests.get(src_url, headers=headers)# 定义图片保存的路径base = os.path.join(save_dir, f"{name}.jpg")# 打开文件并写入图片内容with open(base, "wb") as f:f.write(img_res.content)# 打印下载完成的信息print(f"{name} 皮肤下载完成，保存路径为 {base}")# 等待1秒，防止请求过快time.sleep(1)