Node.js学习笔记

异步获取内容更加高效快速，面对大量图片文字等文件数据，可以使用异步协程获取的方式

import asyncio
import aiohttp
import aiofiles  # 异步保存的文件
from datetime import datetime
from lxml import etree

print(datetime.now())


async def get_page(url, session):
    response = await session.get(url)
    resText = await response.text()
    html = etree.HTML(resText)
    return html


async def get_img_info(html):
    img_names = []
    img_urls = []
    for i in range(1, 61):
        img_name = html.xpath(f'//ul[@id="img-list-outer"]/li[{i}]/a/img/@alt')
        img_url = html.xpath(f'//ul[@id="img-list-outer"]/li[{i}]/a/img/@data-original')
        img_names.append(img_name[0])
        img_urls.append('https:' + img_url[0])
    return img_names, img_urls


async def save_img(img_info,session):
    imgnames, imgs = img_info
    for i in range(len(imgs)):
        async with aiofiles.open('美女\\' + imgnames[i] + '.jpg', 'wb') as f:
            async with session.get(imgs[i]) as img_res:
               img = await img_res.read()
               await f.write(img)


async def main():
        urls = []
        for i in range(1,11):
            url = f'https://soso.nipic.com/?q=%E7%BE%8E%E5%A5%B3&page={i}'
            urls.append(url)
        async with aiohttp.ClientSession() as session:
            res = await asyncio.wait([get_page(url,session)for url in urls])
            res2 = await asyncio.wait([get_img_info(html.result()) for html in res[0]])
            await asyncio.wait([save_img(info.result(),session) for info in res2[0]])

asyncio.run(main())
print(datetime.now())