我正在尝试从网站获取HTML,但是伪娘无法获取HTML。相同的代码可用于我正在下载的其他多个站点。
是什么让该网站与众不同并不允许评估功能获得内容?
即使jQuery也无法访问此网站上的元素。下载的文件似乎确实具有iframe,但是我不确定是否是问题所在。
const puppeteer = require('puppeteer');
const fse = require('fs-extra');
const fs = require('fs');
const nodepath = require('path')
var url = 'http://example.com';
var oddsOutputPath = nodepath.join(__dirname, '..', 'public', 'outputdir');
console.log(oddsOutputPath);
fse.ensureDir(oddsOutputPath).then(() => { console.log('success!') }).catch(err => { console.error(err) });
function delay(timeout) {
return new Promise((resolve) => {
setTimeout(resolve, timeout);
});
}
(async () => {
const browser = await puppeteer.launch({
networkIdleTimeout: 0,
timeout: 360000,
headless: false,
ignoreHTTPSErrors: true,
args: [
'--no-sandbox'
]
});
const page = await browser.newPage();
await page.setRequestInterception(true);
page.on('request', request => {
if (['image', /* 'stylesheet', */ 'font'].indexOf(request.resourceType()) !== -1) {
request.abort();
} else {
request.continue();
}
});
try {
await page.setViewport({ width: 1366, height: 653 });
await page.goto(url, { waitUntil: 'networkidle2', timeout: 360000 });
await delay(45000);
outputPath = oddsOutputPath + "/init.html";
let html = await page.evaluate(() => document.body.innerHTML);
fs.writeFileSync(outputPath, html);
console.log('script has ended');
await delay(5000);
} catch (e) {
var error = "'" + e + "'";
console.log(error)
process.exit()
}
finally {
await browser.close();
}
})();
答案 0 :(得分:1)
您要访问的页面将其大部分内容加载到iframe中。
我建议直接访问iframe以抓取其内容:
git apply stash2@{N}