4. 斗鱼首页图片

• 只用于技术研究，不允许非法用途

截图

​​

‍

源码

# 地址: https://www.douyu.com/g_LOL
# 获取抖音某频道照片
# 开发时间 2024/07/12

import requests
import re
from lxml import etree,html


def get_html():
    url = 'https://www.douyu.com/g_LOL'
    ## 添加请求头
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36'
    }
    resp = requests.get(url=url,headers=headers)
    tree = etree.HTML(resp.content.decode())
    return tree.xpath("//div[@class='layout-Module-container layout-Cover ListContent']/ul[@class='layout-Cover-list']/li")

def parse(node_list):
    lst = []
    count = 0
    for node in node_list:
       count = count+1
       str = html.tostring(node, pretty_print=True, encoding='unicode')
       lst.append((count,re.findall('<img loading="lazy" src="(.*?)"', str)[0]))
    return lst

if __name__ == '__main__':
    lst = parse(get_html())
    print(lst)

​​