谢谢你的关注,所以我写了一个小项目来抓取新闻网站并存储它们的主要文本。我尝试了许多解决方案来在我的项目中添加 json 而没有 consol.log 但总是在刮掉它之后只显示一个正文。所以我向你展示我的代码,这样你就可以帮助我如何让 json 包含所有三个新闻。
const { Cluster } = require('puppeteer-cluster');
const fs = require('fs');
const launchOptions = {
headless: false,
args: [
'--disable-gpu',
'--disable-dev-shm-usage',
'--disable-web-security',
'--disable-xss-auditor',
'--disable-accelerated-2d-canvas',
'--ignore-certifcate-errors',
'--ignore-certifcate-errors-spki-list',
'--no-zygote',
'--no-sandbox',
'--disable-setuid-sandbox',
'--disable-webgl',
],
ignoreHTTPSErrors: true,
waitUntil: 'networkidle2',
};
(async() => {
// Create a cluster with 2 workers
const cluster = await Cluster.launch({
monitor: true,
concurrency: Cluster.CONCURRENCY_PAGE,
maxConcurrency: 2,
puppeteerOptions: launchOptions,
});
// Define a task (in this case: screenshot of page)
await cluster.task(async({ page, data: url }) => {
await page.setRequestInterception(true);
page.on('request', (request) => {
if (['stylesheet', 'font', 'image', 'styles','other', 'media'].indexOf(request.resourceType()) !== -1) {
request.abort();
} else {
request.continue();
}
});
await page.goto(url);
const scrapedData = await page.$eval('div[class="entry-content clearfix"]', el => el.innerText)
fs.writeFileSync('test.json', JSON.stringify(scrapedData, null, 2))
});
// Add some pages to queue
cluster.queue('https://www.ettelaat.com/?p=526642');
cluster.queue('https://www.ettelaat.com/?p=526640');
cluster.queue('https://www.ettelaat.com/?p=526641');
// Shutdown after everything is done
await cluster.idle();
await cluster.close();
})();