使用异步(asyncio,aiohttp)获取彼岸图网高清图片

本文链接：https://blog.csdn.net/weixin_49734406/article/details/123984809

使用异步(asyncio,aiohttp)获取彼岸图网高清图

网站:https://pic.netbian.com/

获取的是首页高清图，不是4k图，

思路：
1，先获取页面的缩略图的高清图片的网址
2，在从高清网址中提取高清图片的url和图片名字
3，下载保存

提醒：
我这里做了延时，代码中加了sleep(1,3)
如果有代理的话可以去掉加入代理请求
如果要获取分类的壁纸，改一下main里的url

# -*- coding: utf-8 -*-


import asyncio
import aiohttp
import aiofiles
import random
import re
import os


headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.75 Safari/537.36',
    "accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
    "referer": "https://pic.netbian.com/index_2.html",
    "cookie": "__yjs_duid=1_a1d59e22709861dce3d23f54cadd3a6d1648820743957; zkhanecookieclassrecord=%2C66%2C60%2C59%2C58%2C53%2C55%2C; yjs_js_security_passport=eb7ad7fe69a1cfbecb4dc9824221b4b829fc64b3_1649212502_js"
}
# 这里必须要带cookie请求，否则请求不到源码


# 从每个页面中获取图片的高清地址
async def get_page(url):
    async with aiohttp.ClientSession() as session:
        async with session.get(url, headers=headers) as resp:
            # print(await resp.text())
            page_parse = re.findall('<a href="(.*?)" target="_blank">.*?</b></a>', await resp.text())
            for page in page_parse:
                await get_img(page, session)

# 从高清地址中获取图片URL和标题
async def get_img(url, session):
    main_url = 'https://pic.netbian.com'						# 拼接完整的URL
    async with session.get(main_url + url, headers=headers) as resp:
        img_url = re.findall('<img src="(.*?)" data-pic=".*?" alt=".*?"', await resp.text())
        img_title = re.findall('<img src=".*?" data-pic=".*?" alt="(.*?)"', await resp.text())
        for image_url, image_title in zip(img_url, img_title):
            image_url = image_url.replace('thumb', 'pic')
            await download_img(image_url, image_title, session)

# 下载图片
async def download_img(url, title, session):
    main_url = 'https://pic.netbian.com'					# 拼接完整的图片URL
    async with session.get(main_url + url, headers=headers) as resp:
        async with aiofiles.open('壁纸_aiohttp/' + title + '.jpg', 'wb') as f:
            await f.write(await resp.read())
            print('>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>', title, 'Download Success!')
            await asyncio.sleep(random.randint(1, 3))

# 创建图片保存文件夹
def mkdir():
    if not os.path.exists('壁纸_aiohttp'):
        os.mkdir('壁纸_aiohttp')

# 主函数
def main():
    mkdir()
    urls = [                                                # 创建页面URL列表
        f'https://pic.netbian.com/index_{page}.html'
        for page in range(2, 12)                            # 页数是从2开始的，因为1页不带数字
    ]
    loop = asyncio.get_event_loop()
    tasks = [get_page(url) for url in urls]
    loop.run_until_complete(asyncio.wait(tasks))


if __name__ == '__main__':
    main()