facebook-event-scraper-fetch
Version:
A slim module for scraping Facebook event data in milliseconds.
54 lines (53 loc) • 2.84 kB
JavaScript
var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, generator) {
function adopt(value) { return value instanceof P ? value : new P(function (resolve) { resolve(value); }); }
return new (P || (P = Promise))(function (resolve, reject) {
function fulfilled(value) { try { step(generator.next(value)); } catch (e) { reject(e); } }
function rejected(value) { try { step(generator["throw"](value)); } catch (e) { reject(e); } }
function step(result) { result.done ? resolve(result.value) : adopt(result.value).then(fulfilled, rejected); }
step((generator = generator.apply(thisArg, _arguments || [])).next());
});
};
Object.defineProperty(exports, "__esModule", { value: true });
exports.fetchEvent = void 0;
const fetchEvent = (url, proxy) => __awaiter(void 0, void 0, void 0, function* () {
try {
const headers = {
accept: 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8',
'accept-encoding': 'gzip, deflate, br',
'accept-language': 'en-US,en;q=0.6',
'cache-control': 'max-age=0',
// NOTE: These headers can be important for scraping sites that expect browser-like requests.
'sec-fetch-dest': 'document',
'sec-fetch-mode': 'navigate',
'sec-fetch-site': 'same-origin',
'sec-fetch-user': '?1',
'sec-gpc': '1',
'upgrade-insecure-requests': '1',
'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36'
};
// Note: Native fetch doesn't support proxy configuration directly in Node.js.
// For proxy support, you would need to use a proxy agent or configure it at the environment level.
if (proxy) {
console.warn('Proxy configuration is not supported with native fetch. Consider using a proxy agent or environment-level proxy configuration.');
}
const response = yield fetch(url, {
method: 'GET',
headers
});
if (!response.ok) {
// Throws an error for non-successful HTTP statuses (e.g., 404, 500).
throw new Error(`HTTP error! status: ${response.status}`);
}
return yield response.text();
}
catch (err) {
// For debugging, you might want to log the original error:
// if (process.env.NODE_ENV === 'development') {
// console.error('Original fetch error:', err.message ?? err);
// }
// Re-throw a generic, user-friendly error.
throw new Error('Error fetching event, make sure your URL is correct and the event is accessible to the public.');
}
});
exports.fetchEvent = fetchEvent;
;