CSC portal Playwright scraper + import 16 open government IT vacancies
This commit is contained in:
20
scripts/csc-scrape.ts
Normal file
20
scripts/csc-scrape.ts
Normal file
@@ -0,0 +1,20 @@
|
||||
import { chromium } from "playwright";
|
||||
|
||||
async function main() {
|
||||
const browser = await chromium.launch({ headless: true });
|
||||
const ctx = await browser.newContext({
|
||||
userAgent: "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36",
|
||||
viewport: { width: 1366, height: 900 },
|
||||
});
|
||||
const page = await ctx.newPage();
|
||||
const resp = await page.goto("https://csc.gov.ph/career/", { waitUntil: "domcontentloaded", timeout: 60000 });
|
||||
console.log("status:", resp?.status());
|
||||
await page.waitForTimeout(8000); // let any JS/Cloudflare settle
|
||||
console.log("title:", await page.title());
|
||||
const text = (await page.innerText("body").catch(() => "")).slice(0, 1500);
|
||||
console.log("---body preview---");
|
||||
console.log(text);
|
||||
await page.screenshot({ path: "/tmp/claude-1000/-home-josh-development-personal-tasks/c55d38eb-c0a2-4a78-b5c5-78f6d6ca1fa6/scratchpad/csc.png", fullPage: false });
|
||||
await browser.close();
|
||||
}
|
||||
main().catch((e) => { console.error(e); process.exit(1); });
|
||||
Reference in New Issue
Block a user