puppeteer 嘗試

【簡介】

• Puppeteer 是一個 Node 庫，它提供了一個高級 API 來通過 DevTools 協議控制 Chromium 或 Chrome。Puppeteer 默認以 headless 模式運行，但是可以通過修改配置文件運行“有頭”模式。

• GitHub 網址：https://github.com/GoogleChrome/puppeteer

• 官網文檔：https://pptr.dev/

• 官方文檔中文版：https://zhaoqize.github.io/puppeteer-api-zh_CN/#?product=Puppeteer

【準備工作】

• 下載并安裝，選 LTS 版本即可：https://nodejs.org

• 安裝 puppeteer

npm?install?puppeteer?--registry=https://registry.npm.taobao.org

【51cto.js】

/*!
?*?walker@2019-07-13:?測試?puppeteer，得到網頁截圖和html
?*/

`use?strict`;

const?puppeteer?=?require('puppeteer');
const?fs?=?require("fs");

//?得到一個兩數之間的隨機整數，包括兩個數在內
function?GetRandInt(min,?max)?{
????min?=?Math.ceil(min);
????max?=?Math.floor(max);
????return?Math.floor(Math.random()?*?(max?-?min?+?1))?+?min;?//含最大值，含最小值?
}

//?下載一篇文章
async?function?DownOneArticle(page,?rawid)?{
????console.log('DownOneArticle?%s?...',?rawid);
????url?=?'https://blog.51cto.com/walkerqt/'?+?rawid;
????console.log('goto?%s?...',?url);
????await?page.goto(
????????url,
????????{
????????????//?timeout:?90*1000,
????????????referer:?'https://blog.51cto.com/walkerqt'
????????});
????let?selector?=?'div.artical-copyright';
????console.log('waitForSelector:?%s?...',?selector);
????await?page.waitForSelector(
????????selector,????//?指定等待?css
????????{
????????????timeout:?10?*?1000
????????}
????);
????await?page.waitFor(GetRandInt(2,?5)?*?1000);?????//?隨機睡眠幾秒

????await?page.screenshot({?path:?rawid?+?'.png'?});????//?保存截圖
????let?html?=?await?page.content();
????fs.writeFileSync(rawid?+?".html",?html);????????????//?保存網頁
}

(async?()?=>?{
????const?browser?=?await?puppeteer.launch({????????//?啟動瀏覽器
????????headless:?false,????//?是否啟用無頭模式
????????args:?[
????????????'--no-sandbox',
????????????//?'--proxy-server=http://192.168.30.3:8080'???//?代理
????????]
????});
????const?page?=?await?browser.newPage();

????let?url?=?'https://blog.51cto.com/walkerqt';????//?首頁
????console.log('goto?%s?...',?url);
????await?page.goto(url);
????let?xpath?=?'//*[@id="Tab"]/div[@class="artical-tit"]';
????console.log('waitForXPath:?%s?...',?xpath);
????await?page.waitForXPath(????????//?指定等待?xpath
????????xpath,
????????{
????????????timeout:?10?*?1000
????????}
????);
????await?page.waitFor(GetRandInt(2,?5)?*?1000);?????//?隨機睡眠幾秒

????let?rawidArray?=?['2419918',?'2415142',?'2413401',?'2396430']
????for?(let?idx?in?rawidArray)?{
????????try?{
????????????await?DownOneArticle(page,?rawidArray[idx]);
????????}?catch?(error)?{
????????????console.log('*?stack:\n?%s',?error.stack);
????????}
????}

????console.log("Good?boy!?Game?over!");
????await?browser.close();??????//?關閉瀏覽器
})();

【運行】

• 運行

node?51cto.js

【相關閱讀】

• mozilla 講 JavaScript 隨機數生成：https://developer.mozilla.org/zh-CN/docs/Web/JavaScript/Reference/Global_Objects/Math/random

• Node.js Tips
  

*** walker ***