Python爬取王者荣耀英雄图片及装备

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 requests
from bs4 import BeautifulSoup
def 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 requests
from bs4 import BeautifulSoup
def 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")
发布了46 篇原创文章 · 获赞 48 · 访问量 20万+

猜你喜欢

转载自blog.csdn.net/qq_43791724/article/details/104738700