Node批量爬取头条视频并保存方法

npm i
npm start

// 配置相关
module.exports = {
 originPath: 'https://www.ixigua.com', // 页面请求地址
 savePath: 'D:/videoZZ' // 存放路径
}

const puppeteer = require('puppeteer');
 
(async () => {
 const browser = await puppeteer.launch();
 const page = await browser.newPage();
 await page.goto('https://example.com');
 await page.screenshot({path: 'example.png'});
 
 await browser.close();
})();

const downloadVideo = async video => {
 // 判断视频文件是否已经下载
 if (!fs.existsSync(`${config.savePath}/${video.title}.mp4`)) {
 await getVideoData(video.src, 'binary').then(fileData => {
 console.log('下载视频中：', video.title)
 savefileToPath(video.title, fileData).then(res =>
 console.log(`${res}: ${video.title}`)
 )
 })
 } else {
 console.log(`视频文件已存在：${video.title}`)
 }
}

getVideoData (url, encoding) {
 return new Promise((resolve, reject) => {
 let req = http.get(url, function (res) {
 let result = ''
 encoding && res.setEncoding(encoding)
 res.on('data', function (d) {
 result += d
 })
 res.on('end', function () {
 resolve(result)
 })
 res.on('error', function (e) {
 reject(e)
 })
 })
 req.end()
 })
}

savefileToPath (fileName, fileData) {
 let fileFullName = `${config.savePath}/${fileName}.mp4`
 return new Promise((resolve, reject) => {
 fs.writeFile(fileFullName, fileData, 'binary', function (err) {
 if (err) {
 console.log('savefileToPath error:', err)
 }
 resolve('已下载')
 })
 })
}