Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat(route): add 湖南日报 #9417

Merged
merged 4 commits into from
Apr 1, 2022
Merged
Show file tree
Hide file tree
Changes from 3 commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 21 additions & 0 deletions docs/traditional-media.md
Original file line number Diff line number Diff line change
Expand Up @@ -875,6 +875,27 @@ Type 栏目:

</Route>

## 湖南日报

### 电子刊物

<Route author="nczitzk" example="/hnrb" path="/hnrb/:id?" :paramsDesc="['编号,见下表,默认为全部']">
nczitzk marked this conversation as resolved.
Show resolved Hide resolved

| 版 | 编号 |
| ------------ | -- |
| 全部 | |
| 第 01 版:头版 | 1 |
| 第 02 版:要闻 | 2 |
| 第 03 版:要闻 | 3 |
| 第 04 版:深度 | 4 |
| 第 05 版:市州 | 5 |
| 第 06 版:理论・学习 | 6 |
| 第 07 版:观察 | 7 |
| 第 08 版:时事 | 8 |
| 第 09 版:中缝 | 9 |

</Route>

## 华尔街见闻

### 华尔街见闻
Expand Down
85 changes: 85 additions & 0 deletions lib/v2/hnrb/index.js
Original file line number Diff line number Diff line change
@@ -0,0 +1,85 @@
const got = require('@/utils/got');
const cheerio = require('cheerio');
const timezone = require('@/utils/timezone');
const { parseDate } = require('@/utils/parse-date');

module.exports = async (ctx) => {
const id = ctx.params.id;

const rootUrl = 'https://hnrb.voc.com.cn';
const currentUrl = `${rootUrl}/hnrb_epaper`;

let response = await got({
method: 'get',
url: currentUrl,
});

response = await got({
method: 'get',
url: `${currentUrl}/${id ? response.data.match(/URL=(.*)"/)[1].replace(/node_\d+\.htm$/, `node_20${id}.htm`) : response.data.match(/URL=(.*)"/)[1]}`,
});

const $ = cheerio.load(response.data);

const matches = response.data.match(/images\/(\d{4}-\d{2}\/\d{2})\/\d{2}\/\d+_brief/);
const link = `${rootUrl}/hnrb_epaper/html/${matches[1]}`;

let items = $('tbody')
.eq(1)
.find('a')
.toArray()
.map((a) => `${link}/${$(a).attr('href').replace(/\.\//, '')}`)
.filter((a) => /div=-1$/.test(a));

if (!id) {
await Promise.all(
$('#pageLink')
.slice(1)
.toArray()
.map((p) => `${link}/${$(p).attr('href').replace(/\.\//, '')}`)
.map(async (p) => {
const pageResponse = await got({
method: 'get',
url: p,
});

const page = cheerio.load(pageResponse.data);

items.push(
...page('tbody')
.eq(1)
.find('a')
.toArray()
.map((a) => `${link}/${page(a).attr('href').replace(/\.\//, '')}`)
.filter((a) => /div=-1$/.test(a))
);
})
);
}

items = await Promise.all(
items.map((item) =>
ctx.cache.tryGet(item, async () => {
const detailResponse = await got({
method: 'get',
url: item,
});

const content = cheerio.load(detailResponse.data);

return {
link: item,
title: content('.font01').text(),
description: content('#ozoom').html(),
pubDate: timezone(parseDate(matches[1], 'YYYY-MM/DD'), +8),
};
})
)
);

ctx.state.data = {
title: `湖南日报${id ? ` - ${$('strong').first().parent().text()}` : ''}`,
link: currentUrl,
item: items,
};
};
3 changes: 3 additions & 0 deletions lib/v2/hnrb/maintainer.js
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
module.exports = {
'/:id?': ['nczitzk'],
};
13 changes: 13 additions & 0 deletions lib/v2/hnrb/radar.js
Original file line number Diff line number Diff line change
@@ -0,0 +1,13 @@
module.exports = {
'voc.com.cn': {
_name: '华声在线',
'.': [
{
title: '湖南日报',
docs: 'https://docs.rsshub.app/journal.html#hu-nan-ri-bao-dian-zi-kan-wu',
source: ['/'],
target: '/hnrb/:id',
},
],
},
};
3 changes: 3 additions & 0 deletions lib/v2/hnrb/router.js
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
module.exports = function (router) {
router.get('/:id?', require('./index'));
};