Wallhaven.cc | 超级高清又好看的图片

Posted 2022-08-01 婉儿hye

Wallhaven|为什么都夸它是世界上最惊艳的壁纸网站？也许你之前还在通过百度搜索壁纸，或者是使用国内的一些图片资源站，相信你也曾被那些复杂的积分制度或者收费方式折磨不堪，但有了 Wallhaven 之后，你所要做的就是把这个网站收藏好就行了。这次，我们将尝试通过简单的代码保存全站的图片~~~（介于没有WiFi，只做部分下载）

import time
from pyquery import PyQuery
import os
import asyncio
import aiohttp
import warnings


# 获取一个请求里的所有图片页面详情链接
async def url_pages(page):
    async with semaphore:
        _url = https://wallhaven.cc/toplist?page=.format(page)
        async with session.get(_url) as response:
            result = await response.text()
            status = response.status
            while status == 429:
                await asyncio.sleep(2)
                async with session.get(_url) as resp:
                    result = await resp.text()
                    status = resp.status
            for _item in PyQuery(result)(.thumb-listing-page li).items():
                async with lock:
                    img_url.append(_item(.preview).attr(href))


# 获取图片昵称、链接
async def get_img_link(_url):
    async with session.get(_url) as response:
        html = await response.text()
        status = response.status
        while status == 429:
            await asyncio.sleep(2)
            async with session.get(_url) as resp:
                html = await resp.text()
                status = resp.status
        _url = PyQuery(html)(#wallpaper).attr(src)
        img_name = os.path.basename(_url)
        return _url, img_name

# 下载图片
async def img_save():
    async with semaphore:
        flag = 3
        while flag:
            if not len(img_url):
                await asyncio.sleep(5)
                flag = flag - 1
                continue
            _url = img_url.pop(0)
            url, name = await get_img_link(_url)
            global number
            number = number + 1
            print("下载第张 --> ".format(number, name))
            if os.path.exists(name):
                continue
            async with session.get(url) as res:
                with open(name, wb) as f:
                    f.write(await res.read())


# 主方法
async def scrape_main():
    global session
    session = aiohttp.ClientSession()
    scrape_index_tasks = [asyncio.ensure_future(img_save()) for i in range(20)]
    scrape_index_tasks.extend([asyncio.ensure_future(url_pages(page)) for page in range(1, pages+1)])
    await asyncio.wait(scrape_index_tasks)
    await session.close()
    print("任务爬取结束O(∩_∩)O~  共爬取张图片".format(number))


if __name__ == __main__:
    warnings.filterwarnings("ignore", category=DeprecationWarning)
    semaphore = asyncio.Semaphore(30)
    start_time = time.time()
    save_path = os.getcwd() + "\\wallpaper"
    if not os.path.exists(save_path):
        os.mkdir(save_path)
    os.chdir(save_path)

    number = 0
    img_url = []
    session = None
    lock = asyncio.Lock()

    # 这个是输入的下载页数，最多201页，一页24张图片
    pages = 3

    asyncio.get_event_loop().run_until_complete(scrape_main())
    print(f"累计耗时time.time()-start_time:.2fs")

箴言：因为这些东西是非常简单的。不要抱怨自己学不会，那是因为你没有足够用心。