本文共 1700 字，大约阅读时间需要 5 分钟。

在玩王者荣耀的时候一直想把装备合英雄的图片保存下来，但是官网的单个图片保存太慢一气之下写了个爬虫。

1.爬取装备

import requestsfrom bs4 import BeautifulSoupdef tupian(url):    headers = {        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.117 Safari/537.36'}    data = requests.get(url, headers=headers).content    soup = BeautifulSoup(data, 'lxml')    results = soup.find(attrs={"id": "Jlist-details"})    for res in results.select('li a img'):        #  图片的标题        title = res.get('alt')        # 图片的地址        url_img = res.get('src')        url_img = "http:" + url_img        print('开始下载='+title)        with open('F:\\input\\video\\装备\\'+title+'.jpg' , 'wb') as ouput:            ouput.write(requests.get(url_img,headers=headers).content);            print('下载完成=' + title)if __name__ == '__main__':    tupian("https://pvp.qq.com/web201605/item.shtml")

1.爬取英雄

import requestsfrom bs4 import BeautifulSoupdef tupian(url):    headers = {        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.117 Safari/537.36'}    data = requests.get(url, headers=headers).content    soup = BeautifulSoup(data, 'lxml')    results = soup.find(attrs={"class": "herolist"})    for res in results.select('li a img'):        #  图片的标题        title = res.get('alt')        # # 图片的地址        url_img = res.get('src')        url_img = "http:" + url_img        print('开始下载='+title)        with open('F:\\input\\video\\英雄\\'+title+'.jpg' , 'wb') as ouput:            ouput.write(requests.get(url_img,headers=headers).content);            print('下载完成=' + title)if __name__ == '__main__':     tupian("https://pvp.qq.com/web201605/herolist.shtml")

转载地址：http://lxkzi.baihongyu.com/