* refactor: use patchwright * refactor: migrate setRequestInterception and waitUntil * fix: overwrite ua * refactor: drop puppeteer cookie/requestfinished shims Migrate page.cookies/setCookie and browser.cookies/setCookie call sites to the native context APIs (page.context().cookies/addCookies), rewrite requestfinished handlers to await request.response() instead of consuming the synchronous puppeteer-shaped payload, and remove the now-redundant browser.close context-cleanup wrapper. Playwright already handles all of these natively; the shims existed only for the puppeteer -> playwright migration. * refactor: remove page.authenticate, page.setUserAgent, browser.newPage(), browser.userAgent() shims update cookie utility tests * refactor: replace browser instance with context in Playwright usage across multiple routes - Updated all instances of `browser` to `context` in Playwright-related functions for consistency and improved resource management. - Ensured proper closure of context after operations to prevent memory leaks. - Adjusted request interception methods to utilize the new context variable. * fix: direct type import * refactor: remove Puppeteer compatibility layers and unify page handling with Playwright * fix: test case * chore: bump patchright to v1.60.0 * chore: pin patchright to 1.59.1 nft can't resolve browser.json due to https://github.com/microsoft/playwright/pull/40093 * chore: pin to node 24.15 for playwright browser install on node 24.16 stucks due to https://github.com/microsoft/playwright/issues/40724 * fix: update patchright and patchright-core to version 1.60.2 and adjust minify-docker.js for compatibility * fix: import BrowserContext from patchright
67 lines
2.0 KiB
TypeScript
67 lines
2.0 KiB
TypeScript
import { load } from 'cheerio';
|
|
|
|
import type { Route } from '@/types';
|
|
import logger from '@/utils/logger';
|
|
import playwright from '@/utils/playwright';
|
|
|
|
import { BASE_URL, parseCompanyName, parseCompanyPosts } from './utils';
|
|
|
|
export const route: Route = {
|
|
path: '/company/:company_id/posts',
|
|
categories: ['social-media'],
|
|
example: '/linkedin/company/google/posts',
|
|
parameters: { company_id: "Company's LinkedIn profile ID" },
|
|
description: "Get company's LinkedIn posts by company ID",
|
|
features: {
|
|
requireConfig: false,
|
|
requirePuppeteer: true,
|
|
antiCrawler: false,
|
|
supportRadar: false,
|
|
supportBT: false,
|
|
supportPodcast: false,
|
|
supportScihub: false,
|
|
},
|
|
name: 'Company Posts',
|
|
maintainers: ['saifazmi'],
|
|
handler: async (ctx) => {
|
|
const company_id = ctx.req.param('company_id');
|
|
|
|
// Puppeteer setup
|
|
const context = await playwright();
|
|
const page = await context.newPage();
|
|
await page.route('**/*', (route) => {
|
|
const request = route.request();
|
|
request.resourceType() === 'document' ? route.continue() : route.abort();
|
|
});
|
|
|
|
const url = new URL(`${BASE_URL}/company/${company_id}`);
|
|
|
|
logger.http(`Requesting ${url.href}`);
|
|
await page.goto(url.href, {
|
|
waitUntil: 'domcontentloaded',
|
|
});
|
|
|
|
const response = await page.content();
|
|
await page.close();
|
|
|
|
const $ = load(response);
|
|
const companyName = parseCompanyName($);
|
|
const posts = parseCompanyPosts($);
|
|
|
|
await context.close();
|
|
|
|
return {
|
|
title: `LinkedIn - ${companyName}'s Posts`,
|
|
link: url.href,
|
|
description: `This feed gets ${companyName}'s posts from LinkedIn`,
|
|
item: posts.map((post) => ({
|
|
title: post.text,
|
|
description: post.text,
|
|
link: post.link,
|
|
pubDate: post.date,
|
|
updated: post.date,
|
|
})),
|
|
};
|
|
},
|
|
};
|