rsshub 1.0.0-master.fdf137b → 1.0.0-master.fe775f5

package/lib/v2/lvv2/news.js

@@ -0,0 +1,75 @@
+const got = require('@/utils/got');
+const cheerio = require('cheerio');
+const { parseDate } = require('@/utils/parse-date');
+const timezone = require('@/utils/timezone');
+const { art } = require('@/utils/render');
+const path = require('path');
+
+const rootUrl = 'https://lvv2.com';
+
+const titleMap = {
+    'sort-realtime': {
+        't-month': '24小时榜 一月内',
+        't-week': '24小时榜 一周内',
+        't-day': '24小时榜 一天内',
+        't-hour': '24小时榜 一小时内',
+    },
+    'sort-hot': '热门',
+    'sort-new': '最新',
+    'sort-score': {
+        't-month': '得分 一月内',
+        't-week': '得分 一周内',
+        't-day': '得分 一天内',
+        't-hour': '得分 一小时内',
+    },
+};
+
+module.exports = async (ctx) => {
+    const channel = ctx.params.channel;
+    const sort = (channel === 'sort-realtime' || channel === 'sort-score') && !ctx.params.sort ? 't-week' : ctx.params.sort;
+    const url = `${rootUrl}/${channel}/${sort}`;
+
+    const response = await got(url);
+    const $ = cheerio.load(response.data);
+    const list = $('div.spacer > div')
+        .map((_, item) => ({
+            title: $(item).find('h3 > a.title').text().trim(),
+            author: $(item).find('a.author').text().trim(),
+            link: new URL($(item).find('h3.title > a.title').attr('href'), rootUrl).href.replace(/(https:\/\/lvv2\.com.*?)\/title.*/, '$1'),
+            pubDate: timezone(parseDate($(item).find('a.dateline > time').attr('datetime')), +8),
+        }))
+        .filter((_, item) => item.title !== '')
+        .get();
+
+    const items = await Promise.all(
+        list.map((item) =>
+            ctx.cache.tryGet(item.link, async () => {
+                if (item.link.indexOf('instant.lvv2.com') !== -1) {
+                    item.description = await ctx.cache.tryGet(item.link, async () => {
+                        const articleResponse = await got(item.link);
+                        const article = cheerio.load(articleResponse.data);
+
+                        const description = article('#_tl_editor')
+                            .html()
+                            .replace(/src=['|"]data.*?['|"]/g, '')
+                            .replace(/(<img.*?)data-src(.*?>)/g, '$1src$2');
+
+                        return description;
+                    });
+                } else {
+                    item.description = art(path.join(__dirname, 'templates/outlink.art'), {
+                        outlink: item.link,
+                    });
+                }
+
+                return item;
+            })
+        )
+    );
+
+    ctx.state.data = {
+        title: `lvv2 - ${sort ? titleMap[channel][sort] : titleMap[channel]}`,
+        link: url,
+        item: items,
+    };
+};

package/lib/v2/lvv2/radar.js

@@ -0,0 +1,79 @@
+module.exports = {
+    'lvv2.com': {
+        _name: 'LVV2',
+        '.': [
+            {
+                title: '热门',
+                docs: 'https://docs.rsshub.app/new-media.html#lvv2',
+                source: ['/sort-hot'],
+                target: '/lvv2/news/sort-hot',
+            },
+            {
+                title: '最新',
+                docs: 'https://docs.rsshub.app/new-media.html#lvv2',
+                source: ['/sort-new'],
+                target: '/lvv2/news/sort-new',
+            },
+            {
+                title: '得分',
+                docs: 'https://docs.rsshub.app/new-media.html#lvv2',
+                source: ['/sort-score', '/sort-score/:sort'],
+                target: (params) => {
+                    if (!params.sort) {
+                        return '/lvv2/news/sort-score';
+                    } else {
+                        return `/lvv2/news/sort-score/${params.sort}`;
+                    }
+                },
+            },
+            {
+                title: '24小时榜',
+                docs: 'https://docs.rsshub.app/new-media.html#lvv2',
+                source: ['/sort-realtime', '/sort-realtime/:sort'],
+                target: (params) => {
+                    if (!params.sort) {
+                        return '/lvv2/news/sort-realtime';
+                    } else {
+                        return `/lvv2/news/sort-realtime/${params.sort}`;
+                    }
+                },
+            },
+            {
+                title: '热门 24小时 Top 10',
+                docs: 'https://docs.rsshub.app/new-media.html#lvv2',
+                source: ['/', '/sort-hot'],
+                target: '/lvv2/top/sort-hot',
+            },
+            {
+                title: '最新 24小时 Top 10',
+                docs: 'https://docs.rsshub.app/new-media.html#lvv2',
+                source: ['/sort-new'],
+                target: '/lvv2/top/sort-new',
+            },
+            {
+                title: '得分 24小时 Top 10',
+                docs: 'https://docs.rsshub.app/new-media.html#lvv2',
+                source: ['/sort-score', '/sort-score/:sort'],
+                target: (params) => {
+                    if (!params.sort) {
+                        return '/lvv2/top/sort-score';
+                    } else {
+                        return `/lvv2/top/sort-score/${params.sort}`;
+                    }
+                },
+            },
+            {
+                title: '24小时榜 24小时 Top 10',
+                docs: 'https://docs.rsshub.app/new-media.html#lvv2',
+                source: ['/sort-realtime', '/sort-realtime/:sort'],
+                target: (params) => {
+                    if (!params.sort) {
+                        return '/lvv2/top/sort-realtime';
+                    } else {
+                        return `/lvv2/top/sort-realtime/${params.sort}`;
+                    }
+                },
+            },
+        ],
+    },
+};

package/lib/v2/lvv2/router.js

@@ -0,0 +1,4 @@
+module.exports = function (router) {
+    router.get('/news/:channel/:sort?', require('./news'));
+    router.get('/top/:channel/:sort?', require('./top'));
+};

package/lib/v2/lvv2/templates/outlink.art

@@ -0,0 +1 @@
+<a href='{{ outlink }}' target="_blank">文章链接</a>

package/lib/v2/lvv2/top.js

@@ -0,0 +1,77 @@
+const got = require('@/utils/got');
+const cheerio = require('cheerio');
+const { parseDate } = require('@/utils/parse-date');
+const timezone = require('@/utils/timezone');
+const { art } = require('@/utils/render');
+const path = require('path');
+
+const rootUrl = 'https://lvv2.com';
+
+const titleMap = {
+    'sort-realtime': {
+        't-month': '24小时榜 一月内',
+        't-week': '24小时榜 一周内',
+        't-day': '24小时榜 一天内',
+        't-hour': '24小时榜 一小时内',
+    },
+    'sort-hot': '热门',
+    'sort-new': '最新',
+    'sort-score': {
+        't-month': '得分 一月内',
+        't-week': '得分 一周内',
+        't-day': '得分 一天内',
+        't-hour': '得分 一小时内',
+    },
+};
+
+module.exports = async (ctx) => {
+    const channel = ctx.params.channel;
+    const sort = (channel === 'sort-realtime' || channel === 'sort-score') && !ctx.params.sort ? 't-week' : ctx.params.sort;
+    const url = `${rootUrl}/${channel}/${sort}`;
+
+    const response = await got(url);
+    const $ = cheerio.load(response.data);
+    const list = $('#top-content-news > div')
+        .map((_, item) => ({
+            title: $(item).find('div.md > a').text(),
+            link: new URL($(item).find('div.md > a').attr('href'), rootUrl).href.replace(/(https:\/\/lvv2\.com.*?)\/title.*/, '$1'),
+        }))
+        .get();
+
+    const items = await Promise.all(
+        list.map((item) =>
+            ctx.cache.tryGet(item.link, async () => {
+                const detailResponse = await got.get(item.link);
+                const content = cheerio.load(detailResponse.data);
+
+                item.pubDate = timezone(parseDate(content('time').attr('datetime')), +8);
+                item.author = content('a.author').text();
+                const link = content('h2.title > a.title').attr('href');
+                if (link.indexOf('instant.lvv2.com') !== -1) {
+                    item.description = await ctx.cache.tryGet(link, async () => {
+                        const articleResponse = await got(link);
+                        const article = cheerio.load(articleResponse.data);
+
+                        const description = article('#_tl_editor')
+                            .html()
+                            .replace(/(<img.*?)data-src(.*?>)/g, '$1src$2');
+
+                        return description;
+                    });
+                } else {
+                    item.description = art(path.join(__dirname, 'templates/outlink.art'), {
+                        outlink: link,
+                    });
+                }
+
+                return item;
+            })
+        )
+    );
+
+    ctx.state.data = {
+        title: `lvv2 - ${sort ? titleMap[channel][sort] : titleMap[channel]} 24小时点击 Top 10`,
+        link: url,
+        item: items,
+    };
+};

package/lib/v2/nbd/article.js

@@ -0,0 +1,50 @@
+const cheerio = require('cheerio');
+const got = require('@/utils/got');
+const timezone = require('@/utils/timezone');
+const { parseDate } = require('@/utils/parse-date');
+module.exports = async (ctx) => {
+    const url = 'https://www.nbd.com.cn/columns/332';
+    const response = await got({
+        method: 'get',
+        url,
+        headers: {
+            Referer: 'https://www.nbd.com.cn',
+        },
+    });
+
+    const $ = cheerio.load(response.data);
+    const $list = $('li.u-news-title').slice(0, 15).get();
+    const description = $('head title').text().trim();
+
+    const resultItem = await Promise.all(
+        $list.map(async (item) => {
+            const title = $(item).find('a').text().trim();
+            const itemUrl = 'https:' + $(item).find('a').attr('href');
+
+            const single = await ctx.cache.tryGet(itemUrl, async () => {
+                const detail = await got({
+                    method: 'get',
+                    url: itemUrl,
+                    headers: {
+                        Referer: 'https://www.nbd.com.cn',
+                    },
+                });
+                const $ = cheerio.load(detail.data);
+                return {
+                    title,
+                    link: itemUrl,
+                    pubDate: timezone(parseDate(detail.data.match(/"pubDate": "(.*)"/)[1]), +8),
+                    description: $('div.g-article').html(),
+                };
+            });
+            return single;
+        })
+    );
+
+    ctx.state.data = {
+        title: '重磅原创-每经网',
+        link: url,
+        item: resultItem,
+        description,
+    };
+};

package/lib/{routes → v2}/nbd/index.js

@@ -1,11 +1,14 @@
 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 || '3';
+    const id = ctx.params.id ?? '3';
 
-    const rootUrl = 'http://www.nbd.com.cn';
+    const rootUrl = 'https://www.nbd.com.cn';
     const currentUrl = `${rootUrl}/columns/${id}`;
+
     const response = await got({
         method: 'get',
         url: currentUrl,
@@ -14,12 +17,12 @@ module.exports = async (ctx) => {
     const $ = cheerio.load(response.data);
 
     const list = $('.u-news-title a')
-        .slice(0, 10)
         .map((_, item) => {
             item = $(item);
+
             return {
                 title: item.text(),
-                link: item.attr('href'),
+                link: 'https:' + item.attr('href'),
             };
         })
         .get();
@@ -34,7 +37,7 @@ module.exports = async (ctx) => {
                 const content = cheerio.load(detailResponse.data);
 
                 item.description = content('.g-articl-text').html();
-                item.pubDate = new Date(detailResponse.data.match(/"pubDate": "(.*)"/)[1]).toUTCString();
+                item.pubDate = timezone(parseDate(detailResponse.data.match(/"pubDate": "(.*)"/)[1]), +8);
 
                 return item;
             })

package/lib/v2/nbd/maintainer.js

@@ -0,0 +1,4 @@
+module.exports = {
+    '/daily': ['MeXunco'],
+    '/:id?': ['nczitzk'],
+};

package/lib/v2/nbd/radar.js

@@ -0,0 +1,19 @@
+module.exports = {
+    'nbd.com.cn': {
+        _name: '每经网',
+        '.': [
+            {
+                title: '分类',
+                docs: 'https://docs.rsshub.app/finance.html#mei-jing-wang',
+                source: '/',
+                targer: '/nbd',
+            },
+            {
+                title: '重磅原创',
+                docs: 'https://docs.rsshub.app/finance.html#mei-jing-wang',
+                source: '/',
+                targer: '/nbd/daily',
+            },
+        ],
+    },
+};

package/lib/v2/nbd/router.js

@@ -0,0 +1,4 @@
+module.exports = (router) => {
+    router.get('/daily', require('./article'));
+    router.get('/:id?', require('./index'));
+};

package/lib/v2/nikkei-cn/index.js

@@ -14,6 +14,8 @@ const cleanContent = (language, content) => {
     }
 };
 
+const getPubDate = (link) => timezone(parseDate(link.match(/(\d{4}-\d{2}-\d{2}-\d{2}-\d{2}-\d{2})/)[1], 'YYYY-MM-DD-HH-mm-ss'), +9);
+
 module.exports = async (ctx) => {
     const language = ctx.params.language ?? 'cn';
     const category = ctx.params.category ?? '';
@@ -33,9 +35,9 @@ module.exports = async (ctx) => {
         category === 'rss'
             ? response.data.match(/<link>(http:\/\/.*\.html)<\/link>/g).map((l) => ({
                   link: l.replace(/<(\/)?link>/g, '').replace(/http:/g, 'https:'),
+                  pubDate: getPubDate(l),
               }))
-            : $('dt a')
-                  .slice(0, ctx.query.limit ? parseInt(ctx.query.limit) : 25)
+            : $('dt a, p.newsDetailTtl a, ul.listStyle01 li a, table.sliderContent3 td a')
                   .toArray()
                   .map((item) => {
                       item = $(item);
@@ -43,9 +45,13 @@ module.exports = async (ctx) => {
                       const link = item.attr('href');
 
                       return {
-                          link: `${link.indexOf('http') === 0 ? '' : rootUrl}${link}`,
+                          link: `${link.startsWith('http') ? '' : rootUrl}${link}`,
+                          pubDate: getPubDate(link),
                       };
-                  });
+                  })
+                  .sort((a, b) => b.pubDate - a.pubDate) // desc
+                  .reduce((prev, cur) => (prev.length && prev[prev.length - 1].link === cur.link ? prev : [...prev, cur]), []) // deduplicate
+                  .slice(0, ctx.query.limit ? parseInt(ctx.query.limit) : 25);
 
     items = await Promise.all(
         items.map((item) =>
@@ -62,7 +68,6 @@ module.exports = async (ctx) => {
                 item.author = content('meta[name="author"]').attr('content');
                 item.title = content('meta[name="twitter:title"]').attr('content');
                 item.description = cleanContent(language, content('#contentDiv').html());
-                item.pubDate = timezone(parseDate(item.link.match(/(\d{4}-\d{2}-\d{2}-\d{2}-\d{2}-\d{2})/)[1], 'YYYY-MM-DD-HH-mm-ss'), +9);
 
                 return item;
             })

package/lib/v2/njnu/ceai/ceai.js

@@ -0,0 +1,44 @@
+const got = require('@/utils/got');
+const cheerio = require('cheerio');
+const util = require('./utils');
+
+module.exports = async (ctx) => {
+    const type = ctx.params.type;
+    let title, path;
+    switch (type) {
+        case 'xygg':
+            title = '学院公告';
+            path = '1651';
+            break;
+        case 'xyxw':
+            title = '学院新闻';
+            path = '1652';
+            break;
+        case 'xszx':
+            title = '学生资讯';
+            path = '1659';
+            break;
+    }
+    const base = 'http://ceai.njnu.edu.cn/Item/List.asp?ID=' + path;
+
+    const response = await got({
+        method: 'get',
+        url: base,
+        https: {
+            rejectUnauthorized: false,
+        },
+    });
+
+    const $ = cheerio.load(response.data);
+
+    const list = $('span a').get();
+
+    const result = await util.ProcessFeed(list, ctx.cache);
+
+    ctx.state.data = {
+        title: '南京师范大学计电人院 - ' + title,
+        link: 'http://ceai.njnu.edu.cn/',
+        description: '南京师范大学计电人院',
+        item: result,
+    };
+};

package/lib/v2/njnu/ceai/utils.js

@@ -0,0 +1,55 @@
+const got = require('@/utils/got');
+const cheerio = require('cheerio');
+const { parseDate } = require('@/utils/parse-date');
+const timezone = require('@/utils/timezone');
+
+// 专门定义一个function用于加载文章内容
+async function load(link) {
+    // 异步请求文章
+    const response = await got.get(link, {
+        https: {
+            rejectUnauthorized: false,
+        },
+    });
+    // 加载文章内容
+    const $ = cheerio.load(response.data);
+    const dateStr = $('#xw_xinxi span:nth-child(1)').text();
+    // 解析日期
+    const pubDate = timezone(parseDate(dateStr, 'YYYY-MM-DD', 'zh-cn'), +8);
+    // 提取内容
+    const description = $('#xw_content').html();
+
+    // 返回解析的结果
+    return { description, pubDate };
+}
+
+const ProcessFeed = async (list, caches) =>
+    await Promise.all(
+        // 遍历每一篇文章
+        list.map(async (item) => {
+            const $ = cheerio.load(item);
+
+            const $title = $('a');
+            // 还原相对链接为绝对链接
+            const itemUrl = $title.attr('href');
+
+            // 列表上提取到的信息
+            const single = {
+                title: $title.text(),
+                link: itemUrl,
+                author: '计算机与电子信息学院-人工智能学院',
+                guid: itemUrl,
+            };
+
+            // 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。
+            const other = await caches.tryGet(itemUrl, async () => 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 { ...single, ...other };
+        })
+    );
+
+module.exports = {
+    ProcessFeed,
+};

package/lib/v2/njnu/jwc/jwc.js

@@ -0,0 +1,43 @@
+const got = require('@/utils/got');
+const cheerio = require('cheerio');
+const util = require('./utils');
+
+module.exports = async (ctx) => {
+    const type = ctx.params.type;
+    let title, path;
+    switch (type) {
+        case 'jstz':
+            title = '教师通知';
+            path = 'jstz.htm';
+            break;
+        case 'xwdt':
+            title = '新闻动态';
+            path = 'xwdt.htm';
+            break;
+        case 'xstz':
+            title = '学生通知';
+            path = 'xstz.htm';
+    }
+    const base = 'http://jwc.njnu.edu.cn/index/' + path;
+
+    const response = await got({
+        method: 'get',
+        url: base,
+        https: {
+            rejectUnauthorized: false,
+        },
+    });
+
+    const $ = cheerio.load(response.data);
+
+    const list = $('.list_txt a').get();
+
+    const result = await util.ProcessFeed(list, ctx.cache);
+
+    ctx.state.data = {
+        title: '南京师范大学教务处 - ' + title,
+        link: 'http://jwc.njnu.edu.cn/',
+        description: '南京师范大学教务处',
+        item: result,
+    };
+};

package/lib/v2/njnu/jwc/utils.js

@@ -0,0 +1,59 @@
+const got = require('@/utils/got');
+const cheerio = require('cheerio');
+const { parseDate } = require('@/utils/parse-date');
+const timezone = require('@/utils/timezone');
+
+// 专门定义一个function用于加载文章内容
+async function load(link) {
+    // 异步请求文章
+    const response = await got.get(link, {
+        https: {
+            rejectUnauthorized: false,
+        },
+    });
+    // 加载文章内容
+    const $ = cheerio.load(response.data);
+    const dateStr = $('span+ span').text();
+    // 解析日期
+    const pubDate = timezone(parseDate(dateStr, 'YYYY-MM-DD', 'zh-cn'), +8);
+    // 提取内容
+    const description = $('form > div').html();
+
+    // 返回解析的结果
+    return { description, pubDate };
+}
+
+const ProcessFeed = async (list, caches) => {
+    const host = 'http://jwc.njnu.edu.cn/';
+
+    // 使用 Promise.all() 进行 async 并发
+    return await Promise.all(
+        // 遍历每一篇文章
+        list.map(async (item) => {
+            const $ = cheerio.load(item);
+
+            const $title = $('a');
+            // 还原相对链接为绝对链接
+            const itemUrl = new URL($title.attr('href'), host);
+
+            // 列表上提取到的信息
+            const single = {
+                title: $title.text(),
+                link: itemUrl,
+                author: '教务处',
+                guid: itemUrl,
+            };
+
+            // 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。
+            const other = await caches.tryGet(itemUrl, async () => 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 { ...single, ...other };
+        })
+    );
+};
+
+module.exports = {
+    ProcessFeed,
+};

package/lib/v2/njnu/maintainer.js

@@ -0,0 +1,4 @@
+module.exports = {
+    '/jwc/:type': ['Shujakuinkuraudo'],
+    '/ceai/:type': ['Shujakuinkuraudo'],
+};

package/lib/v2/njnu/radar.js

@@ -0,0 +1,21 @@
+module.exports = {
+    'njnu.edu.cn': {
+        _name: '南京师范大学',
+        ceai: [
+            {
+                title: '计算机与电子信息学院-人工智能学院',
+                docs: 'https://docs.rsshub.app/university.html#nan-jing-shi-fan-da-xue',
+                source: '/',
+                target: '/njnu/ceai/xygg',
+            },
+        ],
+        jwc: [
+            {
+                title: '教务通知',
+                docs: 'https://docs.rsshub.app/university.html#nan-jing-shi-fan-da-xue',
+                source: '/',
+                target: '/njnu/jwc/xwdt',
+            },
+        ],
+    },
+};

package/lib/v2/njnu/router.js

@@ -0,0 +1,4 @@
+module.exports = (router) => {
+    router.get('/jwc/:type', require('./jwc/jwc'));
+    router.get('/ceai/:type', require('./ceai/ceai'));
+};