From d2eb2b994684dad7c2c5b0beb92e53b46e89b984 Mon Sep 17 00:00:00 2001 From: lenafx Date: Thu, 4 Dec 2025 15:39:25 +0100 Subject: [PATCH] headless now also returns network requests --- src/shared/headless.js | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/src/shared/headless.js b/src/shared/headless.js index 9d9fd0e..784bf22 100644 --- a/src/shared/headless.js +++ b/src/shared/headless.js @@ -31,7 +31,6 @@ async function initHeadless() { "--no-first-run", "--no-zygote", "--single-process", - "--disable-software-rasterizer", "--disable-client-side-phishing-detection", "--no-default-browser-check", @@ -85,6 +84,15 @@ async function scrape(url, handler, options = {}) { if (!browser) await initHeadless(); const page = await context.newPage(); + const requests = []; + + page.on("request", req => { + requests.push({ + url: req.url(), + method: req.method(), + type: req.resourceType() + }); + }); await page.route("**/*", (route) => { const req = route.request(); @@ -137,8 +145,8 @@ async function scrape(url, handler, options = {}) { await new Promise(r => setTimeout(r, renderWaitTime)); } - return await handler(page); - + const result = await handler(page); + return { result, requests }; } catch (error) { console.error(`Error durante el scraping de ${url}:`, error); return null;