-
Notifications
You must be signed in to change notification settings - Fork 7.7k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
feat(route): add route UK Parliament Commons Library research by topic (
#16941) * feat(route): add route UK Parliament Lords Library Research by Topic * chore(route): rename parameter from tag to topic. * feat(route): add route UK Parliament Commons Library Research by Topic * chore(route): update parameters desc. * fix: close browser after puppeteer usage ---------
- Loading branch information
Showing
1 changed file
with
55 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,55 @@ | ||
import { load } from 'cheerio'; | ||
import { Route } from '@/types'; | ||
import puppeteer from '@/utils/puppeteer'; | ||
import timezone from '@/utils/timezone'; | ||
|
||
export const route: Route = { | ||
path: '/commonslibrary/type/:topic?', | ||
categories: ['government'], | ||
example: '/parliament.uk/commonslibrary/type/research-briefing', | ||
parameters: { topic: 'research by topic, string, example: [research-briefing|data-dashboard]' }, | ||
features: { | ||
requireConfig: false, | ||
requirePuppeteer: true, | ||
antiCrawler: false, | ||
supportBT: false, | ||
supportPodcast: false, | ||
supportScihub: false, | ||
}, | ||
name: 'Commonlibrary', | ||
maintainers: ['AntiKnot'], | ||
handler, | ||
}; | ||
|
||
async function handler(ctx) { | ||
const { topic } = ctx.req.param(); | ||
const baseUrl = 'https://commonslibrary.parliament.uk/type'; | ||
const url = `${baseUrl}/${topic}/`; | ||
const browser = await puppeteer(); | ||
const page = await browser.newPage(); | ||
await page.setRequestInterception(true); | ||
page.on('request', (request) => { | ||
request.resourceType() === 'document' ? request.continue() : request.abort(); | ||
}); | ||
await page.goto(url, { | ||
waitUntil: 'domcontentloaded', | ||
}); | ||
|
||
const html = await page.evaluate(() => document.documentElement.innerHTML); | ||
await page.close(); | ||
const $ = load(html); | ||
const items = $('article.card--horizontal') | ||
.map((_, article) => ({ | ||
title: $(article).find('.card__text a').text().trim(), | ||
link: $(article).find('.card__text a').attr('href'), | ||
description: $(article).find('p').last().text().trim(), | ||
pubDate: timezone($(article).find('.card__date time').attr('datetime')), | ||
})) | ||
.toArray(); | ||
browser.close(); | ||
return { | ||
title: `parliament - lordslibrary - ${topic}`, | ||
link: baseUrl, | ||
item: items, | ||
}; | ||
} |