爬取虎牙小姐姐直播间封面

# -*- coding: utf-8 -*-
"""
Created on Wed Jun 23 20:55:33 2021

@author: xfw
"""
import requests
from lxml import etree
import os

# 打印当前系统路径
print(os.getcwd())
# 创建虎牙文件夹储存直播的图片。
if not os.path.exists('huya'):
    os.mkdir('huya')

# 定义请求头，模拟浏览器。
headers={ 
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.114 Safari/537.36"
    }
# 网页地址
url = 'https://www.huya.com/g/2168'

# 请求是否成功？
response = requests.get(url, headers=headers)
if response.status_code == 200:
    print('okay')
else:
    print('fail')
# 解析源代码，找到图片元素
html = etree.HTML(response.text)
girls = html.xpath('//li[@class="game-live-item"]//img[@class="pic"]')


for girl in girls:
    img_href = girl.xpath('./@data-original')[0].split('?')[0]
    name = girl.xpath('./@alt')[0]
    img = requests.get(url=img_href, headers=headers)
    with open( f'huya/{name}.jpg', 'wb') as f:
        f.write(img.content)
    print(name, 'downloaded over!')
print("###############################################")