diff --git a/spiders/segmentfault/screenshot.png b/spiders/segmentfault/screenshot.png new file mode 100644 index 00000000..c26747bd Binary files /dev/null and b/spiders/segmentfault/screenshot.png differ diff --git a/spiders/segmentfault/segmentfault_spider.js b/spiders/segmentfault/segmentfault_spider.js new file mode 100644 index 00000000..9fbc20dc --- /dev/null +++ b/spiders/segmentfault/segmentfault_spider.js @@ -0,0 +1,30 @@ +const puppeteer = require('puppeteer'); + +(async () => { + const browser = await (puppeteer.launch({ + timeout: 15000 + })); + + const url = 'https://segmentfault.com/newest'; + + const page = await browser.newPage(); + + await page.goto(url); + await page.waitFor(2000); + + await page.screenshot({path: 'screenshot.png'}); + + const titles = await page.evaluate(sel => { + let results = []; + document.querySelectorAll('.news-list .news-item .news__item-title').forEach(el => { + results.push({ + title: el.innerText + }) + }); + return results; + }); + + console.log(titles); + + browser.close(); +})(); \ No newline at end of file