wallhaven网站图片下载

wallhaven网站图片下载

这个网站有很多好看的壁纸图片

import requests
from lxml import etree

from spider import Spider


keyword = "street"

for page in range(1, 196):
    print(f"下载第{page}页")
    # 721页
    url = f'https://wallhaven.cc/search?q={keyword}&categories=110&purity=100&sorting=random&order=desc&ai_art_filter=1&seed=NYJ5pC&page={page}'

    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36"
    }
    print(url)
    resp = requests.get(url, headers=headers)
    html = etree.HTML(resp.text)
    href_list = html.xpath('//ul//a[@class="preview"]/@href')
    reso_list = html.xpath('//ul//div[@class="thumb-info"]/span[1]/text()')
    print(href_list, len(href_list))
    print(reso_list, len(reso_list))
    task_list = []
    for href, reso in zip(href_list, reso_list):
        print(href, reso)
        html = etree.HTML(requests.get(href).text)
        download_url = html.xpath('//img[@id="wallpaper"]/@src')[0]
        save_name = download_url.split('/')[-1]
        save_path = f'./{keyword}/{save_name}'
        print('下载地址:', download_url)
        task_list.append((download_url, save_path))
    Spider(task_list=task_list, thread_num=3).run()