Files
RSSHub/lib/v2/sdu/sc.js
Levi Zim 958be6266e feat(route): 山东大学(威海)新闻网 (#9537)
* feat(sduwh): add extractors.

* feat(route): add route for 山东大学(威海)新闻网

* docs: for route sduwh/news

* docs: for route sduwh/news

(cherry picked from commit 831830167a)

* feat(radar): for route 山东大学(威海)新闻网

* refactor: change `got.get` to `got`.

* refactor: prefer `parseDate()` to `new Date()`

Co-authored-by: Tony <TonyRL@users.noreply.github.com>

* fix: incomplete URL substring sanitization.

Make CodeQL happy.

* fix(radar): fix target field.

* fix: change route /sduwh to /sdu/wh

* fix: remove superfluous slash character in url.

* feat: look for exact date first.

* feat: extract exact date from news extractor.

* feat: extract exact date from view extractor.

* feat: extractor for www.sdrj.sdu.edu.cn

* refactor: semantic separation of sduwh with sdu

* feat(radar): more accurate name

* docs: update documentation

* refactor: migrate to v2

* refactor: fix deprecated url.resolve

* fix: update docs url

Co-authored-by: Tony <TonyRL@users.noreply.github.com>

* fix: sdu not working routes

* fix: accurate `ctx.state.data.url`

Co-authored-by: Tony <TonyRL@users.noreply.github.com>

* fix: better error handling for extractors.

* fix: timezone

Co-authored-by: Tony <TonyRL@users.noreply.github.com>

* fix: better error handling.

Co-authored-by: Tony <TonyRL@users.noreply.github.com>
2022-04-17 00:01:39 +08:00

62 lines
1.9 KiB
JavaScript

const got = require('@/utils/got');
const cheerio = require('cheerio');
const { parseDate } = require('@/utils/parse-date');
const host = 'https://www.sc.sdu.edu.cn/';
const typelist = ['通知公告', '学术动态', '本科教育', '研究生教育'];
const urlList = ['tzgg.htm', 'kxyj/xsyg.htm', 'rcpy/bkjy.htm', 'rcpy/yjsjy.htm'];
module.exports = async (ctx) => {
const type = ctx.params.type ? parseInt(ctx.params.type) : 0;
const link = new URL(urlList[type], host).href;
const response = await got(link);
const $ = cheerio.load(response.data);
let item = $('.newlist01 li')
.map((_, e) => {
e = $(e);
const a = e.find('a');
let link = a.attr('href');
link = new URL(link, host).href;
return {
title: a.text().trim(),
link,
pubDate: parseDate(e.find('.date').text().trim()),
};
})
.get();
item = await Promise.all(
item.map((item) =>
ctx.cache.tryGet(item.link, async () => {
try {
const response = await got(item.link);
const $ = cheerio.load(response.data);
item.title = $('h3').text();
item.author =
$('.pr')
.text()
.trim()
.match(/作者:(.*)/)[1] || '山东大学软件学院';
$('h3, .pr').remove();
item.description = $('.content').html();
return item;
} catch (e) {
// intranet oa.sdu.edu.cn
return item;
}
})
)
);
ctx.state.data = {
title: `山东大学软件学院${typelist[type]}`,
description: $('title').text(),
link,
item,
};
};