python(王者荣耀头像爬取)

# Author: Sooele
import os
import sys
import requests
from pyquery import PyQuery
url = 'https://pvp.qq.com/web201605/herolist.shtml'   ####
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.119 Safari/537.36'
}

html=requests.get(url,headers).content   ###content 转义
# print(html)
doc=PyQuery(html)
items=doc('.herolist > li').items()


###########创建文件目录,判断文件是否存在
try:
    os.mkdir('./test')
except Exception as e:
    print(e)

###循环
for item in items:
    # 继续下找，查找img标签，attr属性功能,scr
    url=item.find('img').attr('src')   ####find查找到img标签,attr追加属性src
    urls="https:"+url
    name=item.find('a').text()
    print(name)
    url_conetent=requests.get(urls,headers).content
    with open('./test/'+name+'.jpg','wb')as file:
        file.write(url_conetent)
        print(f'正在下：{name}...{urls}')
相关
