enhanced anime backend

This commit is contained in:
2025-12-04 00:30:41 +01:00
parent bf27d173e9
commit 6973f1485d
10 changed files with 205 additions and 112 deletions

View File

@@ -5,9 +5,14 @@ let context;
const BLOCK_LIST = [
"google-analytics", "doubleclick", "facebook", "twitter",
"adsystem", "analytics", "tracker", "pixel", "quantserve", "newrelic"
"adsystem", "analytics", "tracker", "pixel", "quantserve", "newrelic",
"hotjar", "yandex", "ads", "widgets", "gravatar", "fonts.googleapis",
"map", "cdn.ampproject.org", "googletagmanager"
];
const ALLOWED_SCRIPTS = [];
async function initHeadless() {
if (browser) return;
@@ -25,7 +30,12 @@ async function initHeadless() {
"--mute-audio",
"--no-first-run",
"--no-zygote",
"--single-process"
"--single-process",
"--disable-software-rasterizer",
"--disable-client-side-phishing-detection",
"--no-default-browser-check",
"--no-experiments"
]
});
@@ -35,7 +45,6 @@ async function initHeadless() {
});
}
// ✅ Scroll infinito
async function turboScroll(page) {
await page.evaluate(() => {
return new Promise((resolve) => {
@@ -47,6 +56,7 @@ async function turboScroll(page) {
if (h === last) {
same++;
if (same >= 5) {
clearInterval(timer);
resolve();
}
@@ -55,11 +65,11 @@ async function turboScroll(page) {
last = h;
}
}, 20);
});
});
}
// ✅ Scrape principal
async function scrape(url, handler, options = {}) {
const {
waitUntil = "domcontentloaded",
@@ -67,56 +77,76 @@ async function scrape(url, handler, options = {}) {
timeout = 10000,
scrollToBottom = false,
renderWaitTime = 0,
loadImages = true
loadImages = true,
blockScripts = true
} = options;
if (!browser) await init();
if (!browser) await initHeadless();
const page = await context.newPage();
// 🔒 Bloqueo de recursos
await page.route("**/*", (route) => {
const req = route.request();
const url = req.url().toLowerCase();
const resUrl = req.url().toLowerCase();
const type = req.resourceType();
if (
type === "font" ||
type === "stylesheet" ||
type === "media" ||
type === "manifest"
) return route.abort();
type === "manifest" ||
type === "other" ||
if (BLOCK_LIST.some(k => url.includes(k))) return route.abort();
(blockScripts && type === "script" && !ALLOWED_SCRIPTS.some(k => resUrl.includes(k)))
) {
return route.abort("blockedbyclient", { timeout: 100 });
}
if (BLOCK_LIST.some(k => resUrl.includes(k))) {
return route.abort("blockedbyclient", { timeout: 100 });
}
if (!loadImages && (
type === "image" || url.match(/\.(jpg|jpeg|png|gif|webp|svg)$/)
)) return route.abort();
type === "image" || resUrl.match(/\.(jpg|jpeg|png|gif|webp|svg)$/)
)) {
return route.abort("blockedbyclient", { timeout: 100 });
}
route.continue();
});
await page.goto(url, { waitUntil, timeout });
try {
await page.goto(url, { waitUntil, timeout });
if (waitSelector) {
try {
await page.waitForSelector(waitSelector, { timeout });
} catch {}
if (waitSelector) {
try {
await page.waitForSelector(waitSelector, { timeout });
} catch (e) {
}
}
if (scrollToBottom) {
await turboScroll(page);
}
if (renderWaitTime > 0) {
await new Promise(r => setTimeout(r, renderWaitTime));
}
return await handler(page);
} catch (error) {
console.error(`Error durante el scraping de ${url}:`, error);
return null;
} finally {
await page.close();
}
if (scrollToBottom) {
await turboScroll(page);
}
if (renderWaitTime > 0) {
await new Promise(r => setTimeout(r, renderWaitTime));
}
const result = await handler(page);
await page.close();
return result;
}
async function closeScraper() {