RSSHub/lib/v2/jianshu/utils.js

59 lines
1.9 KiB
JavaScript
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

const got = require('@/utils/got');
const cheerio = require('cheerio');
const { parseDate } = require('@/utils/parse-date');
const timezone = require('@/utils/timezone');
// 加载文章页
const load = async (link) => {
const response = await got.get(link);
const $ = cheerio.load(response.data);
// 解析日期
const pubDate = timezone(parseDate($('time').attr('datetime')), +8);
// 去除样式
$('.image-container, .image-container-fill').removeAttr('style');
// 处理视频
$('.video-package').each((index, elem) => {
const $item = $(elem);
const desc = $item.find('.video-description').html();
const url = $item.attr('data-video-url');
$item.html(`
<p>${desc}</p>
<iframe frameborder="0" src="${url}" allowFullScreen="true"></iframe>
`);
});
// 提取内容
const description = $('article').html();
return { description, pubDate };
};
const ProcessFeed = (list, caches) => {
const host = 'https://www.jianshu.com';
return Promise.all(
list.map((item) => {
const $ = cheerio.load(item);
const $title = $('.title');
// 还原相对链接为绝对链接
const itemUrl = new URL($title.attr('href'), host).toString();
// 使用tryGet方法从缓存获取内容。
// 当缓存中无法获取到链接内容的时候则使用load方法加载文章内容
return caches.tryGet(itemUrl, async () => {
const other = await load(itemUrl);
// 合并解析后的结果集作为该篇文章最终的输出结果
return {
title: $title.text(),
link: itemUrl,
author: $('.nickname').text(),
...other,
};
});
})
);
};
module.exports = {
ProcessFeed,
};