写个有意思的云函数玩玩
入驻云加社区的同学都知道有个云+社区作者排行榜 ,榜单数据大概每周一的九点左右更新。个人成就数据也是同步更新,总是打开页面访问有点麻烦哇,用个爬虫来抓取不就方便多了嘛...
之前一直想用云函数来做爬虫,无奈小程序云开发的云函数还未完全支持 puppeteer ,调用会报错。但是最近发现 TCB 的云函数支持 puppeteer 依赖,就决定用它了。 另外一个原因就是它也有免费额度 ?
云开发(Tencent CloudBase,TCB)是腾讯云提供的云原生一体化开发环境和工具平台,为开发者提供高可用、自动弹性扩缩的后端云服务,包含计算、存储、托管等 Serverless 化能力,可用于云端一体化开发多种端应用(小程序、公众号、Web 应用、Flutter 客户端等),帮助开发者统一构建和管理后端服务和云资源,避免了应用开发过程中繁琐的服务器搭建及运维,开发者可以专注于业务逻辑的实现,开发门槛更低,效率更高。
使用puppeteer打开社区个人首页截取指定区域并进行截图后上传至云存储,下载文件后直接返回图片数据
index.js
'use strict';
const puppeteer = require('puppeteer')
exports.main = async (event, context) => {
let param = {}
if (event.queryStringParameters) {
param = { ...event.queryStringParameters }
} else {
param = { ...event }
}
let uid = param.uid || '1683232'
let isImg = param.img || 0
let force = param.force || 0
console.log(uid, isImg, force)
const browser = await puppeteer.launch({
headless: true,
args: ['--no-sandbox', '--disable-setuid-sandbox'],
dumpio: false,
})
const page = await browser.newPage()
page.setUserAgent(
'Mozilla/5.0 (Linux; Android 10; Redmi K30 Pro Build/QKQ1.191117.002; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/78.0.3904.62 XWEB/2581 MMWEBSDK/200801 Mobile Safari/537.36'
)
await page.goto('https://cloud.tencent.com/developer/user/' + uid, {
waitUntil: 'networkidle0',
})
// 返回图片
if (isImg) {
await page.$eval(
'.uc-achievements',
(el, value) => el.setAttribute('style', value),
'width:200px;padding-bottom:10px;'
)
await page.$eval(
'.uc-achievement:nth-child(1)',
(el, value) => el.setAttribute('style', value),
'float:none;width:100%;'
)
await page.$eval(
'.uc-achievement:nth-child(2)',
(el, value) => el.setAttribute('style', value),
'float:none;width:100%;'
)
await page.$eval(
'.uc-achievement:nth-child(3)',
(el, value) => el.setAttribute('style', value),
'float:none;width:100%;'
)
let rec = await page.$('.uc-achievement:nth-child(4)')
if (rec) {
await page.$eval(
'.uc-achievement:nth-child(4)',
(el, value) => el.setAttribute('style', value),
'float:none;width:100%;'
)
}
let clip = await page.evaluate(() => {
let { x, y, width, height } = document
.querySelector('.uc-achievements')
.getBoundingClientRect()
x = x - 5
y = y - 130
height = height + 130
return {
x,
y,
width,
height,
}
})
await page.screenshot({
path: '/tmp/achievement.png',
clip: clip,
})
await browser.close()
const tcb = require("@cloudbase/node-sdk")
const fs = require("fs")
const app = tcb.init({ env: 'your env' })
// 判断是否已经存在文件
try {
let oldPic = await app.downloadFile({
fileID: 'cloud://xxx/achievement/' + uid + '.png'
})
// 存在
console.log('oldPic:' + oldPic)
// 是否覆盖上传
if (force) {
let res = await app.uploadFile({
cloudPath: "achievement/" + uid + ".png",
fileContent: fs.createReadStream('/tmp/achievement.png')
})
oldPic = await app.downloadFile({
fileID: res.fileID
})
}
return {
isBase64Encoded: true,
statusCode: 200,
headers: {
"content-type": "image/png"
},
body: oldPic.fileContent.toString('base64')
}
} catch (e) {
// 不存在的情况
console.log('e:' + e)
const res = await app.uploadFile({
cloudPath: "achievement/" + uid + ".png",
fileContent: fs.createReadStream('/tmp/achievement.png')
})
// console.log(res)
const result = await app.downloadFile({
fileID: res.fileID
})
console.log('result:' + result)
return {
isBase64Encoded: true,
statusCode: 200,
headers: {
"content-type": "image/png"
},
body: result.fileContent.toString('base64')
}
}
} else {
const staticInfo = await page.evaluate(() => {
const element = document.querySelector('.uc-achievements')
let rank = element.getElementsByClassName('uc-achievement-text').item(0)
.innerHTML
let like = element.getElementsByClassName('uc-achievement-text').item(1)
.innerHTML
let read = element.getElementsByClassName('uc-achievement-text').item(2)
.innerHTML
return { rank: rank, like: like, read: read }
})
await browser.close()
return staticInfo
}
};
云函数支持传入三个参数,uid 是你的社区用户ID,不传默认是博主的 ?
参数 | 说明 | 类型 | 可选值 | 默认值 |
---|---|---|---|---|
uid | 用户ID | number | -- | 博主uid |
img | 返回图片数据 | number | 1/0 | 0 |
force | 强制更新图片 | number | 1/0 | 0 |
HTTP访问服务地址
请求域名可以设置为自定义域名 因为默认域名仅用于开发测试,有请求频率限制,所以建议绑定自定义域名
昵称 | 成就 |
---|---|
py3study | |
腾讯云serverless团队 | |
amc |