rsshub 1.0.0-master.f9003f9 → 1.0.0-master.f917bdc

package/lib/routes/readwise/list.ts

@@ -0,0 +1,152 @@
+import ConfigNotFoundError from '@/errors/types/config-not-found';
+import ofetch from '@/utils/ofetch';
+import { Route } from '@/types';
+import { config } from '@/config';
+import { parseDate } from '@/utils/parse-date';
+
+export const route: Route = {
+    path: '/list/:routeParams?',
+    categories: ['reading'],
+    example: '/readwise/list/location=new&category=article',
+    parameters: { routeParams: 'Parameter combinations, see the description above.' },
+    features: {
+        requireConfig: [
+            {
+                name: 'READWISE_ACCESS_TOKEN',
+                optional: false,
+                description: 'Visit `https://readwise.io/access_token` to get your access token.',
+            },
+        ],
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['read.readwise.io'],
+            target: '/list',
+        },
+    ],
+    name: 'Reader Document List',
+    maintainers: ['xbot'],
+    handler,
+    description: `Specify options (in the format of query string) in parameter \`routeParams\` to filter documents.
+
+| Parameter                  | Description                                                                            |   Values                                                                                    |  Default                             |
+| -------------------------- | -------------------------------------------------------------------------------------- |   ----------------------------------------------------------------------------------------- |  ----------------------------------- |
+| \`location\`               | The document's location.                                                               |   \`new\`/\`later\`/\`shortlist\`/\`archive\`/\`feed\`                                      |                                      |
+| \`category\`               | The document's category.                                                               |   \`article\`/\`email\`/\`rss\`/\`highlight\`/\`note\`/\`pdf\`/\`epub\`/\`tweet\`/\`video\` |                                      |
+| \`updatedAfter\`           | Fetch only documents updated after this date.                                          |   string (formatted as ISO 8601 date)                                                       ||
+| \`tag\`                    | The document's tag, can be specified once or multiple times.                           |||
+| \`tagStrategy\`            | If multiple tags are specified, should the documents match all of them or any of them. |   \`any\`/\`all\`                                                                           |  \`any\`                             |
+
+Customise parameter values to fetch specific documents, for example:
+
+\`\`\`
+https://rsshub.app/readwise/list/location=new&category=article
+\`\`\`
+
+fetches articles in the Inbox.
+
+\`\`\`
+https://rsshub.app/readwise/list/category=article&tag=shortlist&tag=AI&tagStrategy=all
+\`\`\`
+
+fetches articles tagged both by \`shortlist\` and \`AI\`. `,
+};
+
+const TAG_STRATEGY_ALL = 'all'; // Items with tags matching all the given ones can then be returned.
+const TAG_STRATEGY_ANY = 'any'; // Items with tags matching any of the given ones can be returned.
+
+async function handler(ctx) {
+    if (!config.readwise || !config.readwise.accessToken) {
+        throw new ConfigNotFoundError('Readwise access token is missing');
+    }
+
+    let apiUrl = 'https://readwise.io/api/v3/list/?';
+    let tag, tagStrategy;
+
+    if (ctx.req.param('routeParams')) {
+        const urlSearchParams = new URLSearchParams(ctx.req.param('routeParams'));
+
+        const location = urlSearchParams.get('location');
+        const category = urlSearchParams.get('category');
+        const updatedAfter = urlSearchParams.get('updatedAfter');
+
+        tag = urlSearchParams.get('tag');
+        tagStrategy = urlSearchParams.get('tagStrategy') === TAG_STRATEGY_ANY || urlSearchParams.get('tagStrategy') === TAG_STRATEGY_ALL ? urlSearchParams.get('tagStrategy') : TAG_STRATEGY_ANY;
+
+        if (location) {
+            apiUrl += `location=${location}&`;
+        }
+        if (category) {
+            apiUrl += `category=${category}&`;
+        }
+        if (updatedAfter) {
+            apiUrl += `updatedAfter=${updatedAfter}&`;
+        }
+    }
+
+    const fullData = [];
+
+    async function fetchNextPage(url) {
+        const response = await ofetch(url, {
+            headers: {
+                Authorization: `Token ${config.readwise.accessToken}`,
+            },
+        });
+
+        fullData.push(...response.results);
+
+        if (response.nextPageCursor) {
+            await fetchNextPage(apiUrl + `pageCursor=${response.nextPageCursor}`);
+        }
+    }
+
+    await fetchNextPage(apiUrl);
+
+    const items = fullData
+        .filter((item) => {
+            if (!tag) {
+                return true; // No tag filter applied
+            }
+
+            // Check if item.tags exist and match the criteria based on tagStrategy
+            const itemTags = item.tags;
+
+            if (!itemTags) {
+                return false; // If item has no tags and tag filter is applied, exclude it
+            }
+
+            if (Array.isArray(tag)) {
+                if (tagStrategy === TAG_STRATEGY_ANY) {
+                    // Filter if any of the tags match
+                    return tag.some((t) => Object.values(itemTags).some((tagObj) => tagObj.name === t));
+                } else if (tagStrategy === TAG_STRATEGY_ALL) {
+                    // Filter if all tags match
+                    return tag.every((t) => Object.values(itemTags).some((tagObj) => tagObj.name === t));
+                }
+            } else {
+                const tagName = tag;
+                return Object.values(itemTags).some((tagObj) => tagObj.name === tagName);
+            }
+
+            return false;
+        })
+        .map((item) => ({
+            title: item.title,
+            link: item.source_url,
+            description: item.summary,
+            pubDate: parseDate(item.created_at),
+            author: item.author,
+        }));
+
+    return {
+        allowEmpty: true,
+        title: 'Readwise Reader',
+        link: 'https://read.readwise.io',
+        item: items,
+    };
+}

package/lib/routes/readwise/namespace.ts

@@ -0,0 +1,6 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: 'Readwise',
+    url: 'readwise.io',
+};

package/lib/routes/reuters/common.ts

@@ -1,4 +1,4 @@
-import { Route } from '@/types';
+import { Route, ViewType } from '@/types';
 import { getCurrentPath } from '@/utils/helpers';
 const __dirname = getCurrentPath(import.meta.url);
 
@@ -11,7 +11,8 @@ import path from 'node:path';
 
 export const route: Route = {
     path: '/:category/:topic?',
-    categories: ['traditional-media'],
+    categories: ['traditional-media', 'popular'],
+    view: ViewType.Articles,
     example: '/reuters/world/us',
     parameters: { category: 'find it in the URL, or tables below', topic: 'find it in the URL, or tables below' },
     features: {

package/lib/routes/reuters/namespace.ts

@@ -1,7 +1,7 @@
 import type { Namespace } from '@/types';
 
 export const namespace: Namespace = {
-    name: 'Reuters 路透社',
+    name: 'Reuters',
     url: 'reuters.com',
     description: `:::tip
 You can use \`sophi=true\` query parameter to invoke the **experimental** method, which can, if possible, fetch more articles(between 20 and 100) with \`limit\` given. But some articles from the old method might not be available.

package/lib/routes/rss3/index.ts

@@ -0,0 +1,148 @@
+import { Route } from '@/types';
+
+import ofetch from '@/utils/ofetch';
+
+export const route: Route = {
+    path: '/:account/:network?/:tag?',
+    categories: ['social-media'],
+    example: '/rss3/vitalik.eth',
+    name: 'Account Activities',
+    maintainers: ['DIYgod'],
+    url: 'docs.rss3.io/api-reference#tag/decentralized/GET/decentralized/%7Baccount%7D',
+    handler,
+    description: 'Retrieve the activities associated with a specified account in the decentralized system.',
+    parameters: {
+        account: {
+            description: 'Retrieve activities from the specified account. This account is a unique identifier within the decentralized system.',
+        },
+        network: {
+            description: 'Retrieve activities from the specified network.',
+            default: 'all',
+            options: [
+                {
+                    value: 'all',
+                    label: 'All',
+                },
+                {
+                    value: 'arbitrum',
+                    label: 'Arbitrum',
+                },
+                {
+                    value: 'arweave',
+                    label: 'Arweave',
+                },
+                {
+                    value: 'avax',
+                    label: 'Avax',
+                },
+                {
+                    value: 'base',
+                    label: 'Base',
+                },
+                {
+                    value: 'binance-smart-chain',
+                    label: 'Binance Smart Chain',
+                },
+                {
+                    value: 'crossbell',
+                    label: 'Crossbell',
+                },
+                {
+                    value: 'ethereum',
+                    label: 'Ethereum',
+                },
+                {
+                    value: 'farcaster',
+                    label: 'Farcaster',
+                },
+                {
+                    value: 'gnosis',
+                    label: 'Gnosis',
+                },
+                {
+                    value: 'linea',
+                    label: 'Linea',
+                },
+                {
+                    value: 'optimism',
+                    label: 'Optimism',
+                },
+                {
+                    value: 'polygon',
+                    label: 'Polygon',
+                },
+                {
+                    value: 'vsl',
+                    label: 'VSL',
+                },
+            ],
+        },
+        tag: {
+            description: 'Retrieve activities from the specified tag.',
+            default: 'all',
+            options: [
+                {
+                    value: 'all',
+                    label: 'All',
+                },
+                {
+                    value: 'collectible',
+                    label: 'collectible',
+                },
+                {
+                    value: 'exchange',
+                    label: 'exchange',
+                },
+                {
+                    value: 'metaverse',
+                    label: 'metaverse',
+                },
+                {
+                    value: 'rss',
+                    label: 'rss',
+                },
+                {
+                    value: 'social',
+                    label: 'social',
+                },
+                {
+                    value: 'transaction',
+                    label: 'transaction',
+                },
+                {
+                    value: 'unknown',
+                    label: 'unknown',
+                },
+            ],
+        },
+    },
+};
+
+async function handler(ctx) {
+    const { account, network, tag } = ctx.req.param();
+
+    const { data } = await ofetch(
+        `https://gi.rss3.io/decentralized/${account}?${new URLSearchParams({
+            limit: '20',
+            ...(network && network !== 'all' && { network }),
+            ...(tag && tag !== 'all' && { tag }),
+        })}`
+    );
+
+    return {
+        title: `${account} activities`,
+        link: 'https://rss3.io',
+        item: data.map((item) => ({
+            title: `New ${item.tag} ${item.type} action on ${item.network}`,
+            description: `New ${item.tag} ${item.type} action on ${item.network}<br /><br />From: ${item.from}<br/>To: ${item.to}`,
+            link: item.actions?.[0]?.related_urls?.[0],
+            guid: item.id,
+            author: [
+                {
+                    name: item.owner,
+                    avatar: `https://cdn.stamp.fyi/avatar/eth:${item.owner}`,
+                },
+            ],
+        })),
+    };
+}

package/lib/routes/rss3/namespace.ts

@@ -0,0 +1,7 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: 'RSS3',
+    url: 'rss3.io',
+    description: 'The RSS3 Network is the a decentralized network designed to promote the free flow of information on the Open Web .',
+};

package/lib/routes/rsshub/routes.ts

@@ -1,12 +1,28 @@
-import { Route } from '@/types';
-import got from '@/utils/got';
-import { load } from 'cheerio';
+import { Route, ViewType } from '@/types';
+import ofetch from '@/utils/ofetch';
+import * as cheerio from 'cheerio';
 
 export const route: Route = {
     path: '/routes/:lang?',
     categories: ['program-update', 'popular'],
+    view: ViewType.Notifications,
     example: '/rsshub/routes/en',
-    parameters: { lang: 'Language, `zh` means Chinese docs, other values or null means English docs, `en` by default' },
+    parameters: {
+        lang: {
+            description: 'Language',
+            options: [
+                {
+                    label: 'Chinese',
+                    value: 'zh',
+                },
+                {
+                    label: 'English',
+                    value: 'en',
+                },
+            ],
+            default: 'en',
+        },
+    },
     radar: [
         {
             source: ['docs.rsshub.app/*'],
@@ -50,11 +66,9 @@ async function handler(ctx) {
     ];
     const all = await Promise.all(
         types.map(async (type) => {
-            const response = await got(`https://docs.rsshub.app/${lang}routes/${type}`);
-
-            const data = response.data;
+            const response = await ofetch(`https://docs.rsshub.app/${lang}routes/${type}`);
 
-            const $ = load(data);
+            const $ = cheerio.load(response);
             const page = $('.page').toArray();
             const item = $('.routeBlock').toArray();
             return { page, item, type };
@@ -68,15 +82,23 @@ async function handler(ctx) {
         description: isEnglish ? 'Everything is RSSible' : '万物皆可 RSS',
         language: isEnglish ? 'en-us' : 'zh-cn',
         item: list.map(({ page, item, type }) => {
-            const $ = load(page);
-            item = $(item);
-            const h2Title = item.prevAll('h2').eq(0);
-            const h3Title = item.prevAll('h3').eq(0);
+            const $ = cheerio.load(page);
+            const $item = $(item);
+            const h2Title = $item.prevAll('h2').eq(0);
+            const h3Title = $item.prevAll('h3').eq(0);
+
+            $item.find('.VPBadge').each((_, ele) => {
+                const $ele = $(ele);
+                if ($ele.text().includes('Test')) {
+                    $ele.remove();
+                }
+            });
+
             return {
                 title: `${h2Title.text().trim()} - ${h3Title.text().trim()}`,
-                description: item.html(),
+                description: $item.html()?.replaceAll(/<!--.*?-->/g, ''),
                 link: `https://docs.rsshub.app/${lang}routes/${type}#${encodeURIComponent(h2Title.find('.header-anchor').attr('href') && h3Title.find('.header-anchor').attr('href')?.substring(1))}`,
-                guid: item.attr('id'),
+                guid: $item.attr('id'),
             };
         }),
     };

package/lib/routes/ruc/ai.ts

@@ -0,0 +1,87 @@
+import { Route } from '@/types';
+import ofetch from '@/utils/ofetch';
+import { load } from 'cheerio';
+import { parseDate } from '@/utils/parse-date';
+import timezone from '@/utils/timezone';
+import cache from '@/utils/cache';
+
+export const route: Route = {
+    path: '/ai/:category?',
+    categories: ['university'],
+    example: '/ruc/ai',
+    parameters: { category: '分类，见下方说明，默认为首页公告' },
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['ai.ruc.edu.cn/'],
+        },
+    ],
+    name: '高瓴人工智能学院',
+    maintainers: ['yinhanyan'],
+    handler: async (ctx) => {
+        const category = ctx.req.param('category')?.replace(/-/g, '/') ?? 'newslist/notice';
+        const baseURL = `http://ai.ruc.edu.cn/${category}/`;
+        const indexUrl = baseURL + 'index.htm';
+        const response = await ofetch(indexUrl);
+        const $ = load(response);
+        const pageTitle = $('title').text();
+        const list = $('div.fr li')
+            .toArray()
+            .map((item) => {
+                item = $(item);
+                const a = item.find('a').first();
+                const link = baseURL + a.attr('href');
+                return {
+                    link,
+                };
+            });
+
+        const items = await Promise.all(
+            list.map((item) =>
+                cache.tryGet(item.link, async () => {
+                    try {
+                        const response = await ofetch(item.link);
+                        const $ = load(response);
+                        const title = $('title').text();
+                        item.title = title;
+                        const titleDiv = $('div.tit');
+                        const date = titleDiv.find('span').first().text();
+                        item.pubDate = timezone(parseDate(/\d+-\d+-\d+/.exec(date)[0]), +8);
+                        const frame = $('div.fr');
+                        item.description = frame
+                            .children()
+                            .slice(3)
+                            .map((i, el) => $.html(el))
+                            .get()
+                            .join('');
+                    } catch {
+                        item.description = '';
+                    }
+
+                    return item;
+                })
+            )
+        );
+
+        return {
+            title: pageTitle,
+            link: indexUrl,
+            icon: 'https://www.ruc.edu.cn/favicon.ico',
+            logo: 'http://ai.ruc.edu.cn/images/cn_ruc_logo.png',
+            item: items,
+        };
+    },
+    url: 'ai.ruc.edu.cn/',
+    description: `:::tip
+  分类字段处填写的是对应中国人民大学高瓴人工智能学院分类页网址中介于 **\`http://ai.ruc.edu.cn/\`** 和 **/index.htm** 中间的一段，并将其中的 \`/\` 修改为 \`-\`。
+
+  如 [中国人民大学高瓴人工智能学院 - 新闻公告 - 学院新闻](http://ai.ruc.edu.cn/newslist/newsdetail/index.htm) 的网址为 \`http://ai.ruc.edu.cn/newslist/newsdetail/index.htm\` 其中介于 **\`http://ai.ruc.edu.cn/\`** 和 **/index.htm** 中间的一段为 \`newslist/newsdetail\`。随后，并将其中的 \`/\` 修改为 \`-\`，可以得到 \`newslist-newsdetail\`。所以最终我们的路由为 [\`/ruc/ai/newslist-newsdetail\`](https://rsshub.app/ruc/ai/newslist-newsdetail)
+    :::`,
+};

package/lib/routes/ruc/namespace.ts

@@ -1,6 +1,9 @@
 import type { Namespace } from '@/types';
 
 export const namespace: Namespace = {
-    name: '中国人民大学',
-    url: 'hr.ruc.edu.cn',
+    name: 'Renmin University of China',
+    url: 'ruc.edu.cn',
+    zh: {
+        name: '中国人民大学',
+    },
 };

package/lib/routes/samd/namespace.ts

@@ -0,0 +1,6 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: '深圳市医疗器械行业协会',
+    url: 'www.samd.org.cn',
+};

package/lib/routes/samd/news.ts

@@ -0,0 +1,74 @@
+import { Route, DataItem } from '@/types';
+import cache from '@/utils/cache';
+import { parseDate } from '@/utils/parse-date';
+import timezone from '@/utils/timezone';
+import { load } from 'cheerio';
+import ofetch from '@/utils/ofetch';
+
+const dict = { '434': '行业资讯', '436': '协会动态', '438': '重要通知', '440': '政策法规' };
+
+export const route: Route = {
+    path: 'news/:typeId',
+    categories: ['government'],
+    example: '/samd/news/440',
+    parameters: { type: '文章类型ID，见下表' },
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    description: `| 行业资讯 | 协会动态 | 重要通知 | 政策法规 |
+| --- | --- | --- | --- |
+| 434 | 436 | 438 | 440 |`,
+    name: '资讯信息',
+    maintainers: ['hualiong'],
+    handler: async (ctx) => {
+        const baseURL = 'https://www.samd.org.cn/home';
+        const typeId = ctx.req.param('typeId');
+
+        const { rows } = await ofetch('/GetNewsByTagId', {
+            baseURL,
+            method: 'POST',
+            query: {
+                page: 1,
+                rows: 10,
+                typeId,
+                status: 1,
+            },
+        });
+
+        const list: DataItem[] = rows.map((row) => ({
+            title: row.title,
+            category: [row.tag_names],
+            link: `${baseURL}/newsDetail?id=${row.auto_id}&typeId=${typeId}`,
+            image: row.img_url ? baseURL + row.img_url : null,
+        }));
+
+        const items = await Promise.all(
+            list.map((item) =>
+                cache.tryGet(item.link!, async () => {
+                    const $ = load(await ofetch(item.link!));
+
+                    const content = $('.content');
+                    item.author = content.find('.author span').text();
+                    item.pubDate = timezone(parseDate(content.find('.time').text(), '发布时间：YYYY-MM-DD HH:mm:ss'), +8);
+
+                    content.children('.titles').remove();
+                    content.children('.auxi').remove();
+                    item.description = content.html()!;
+
+                    return item;
+                })
+            )
+        );
+
+        return {
+            title: `${dict[typeId]} - 深圳市医疗器械行业协会`,
+            link: 'https://www.samd.org.cn/home/newsList',
+            item: items as DataItem[],
+        };
+    },
+};

package/lib/routes/sara/index.ts

@@ -1,7 +1,7 @@
 import { Route, DataItem } from '@/types';
 import cache from '@/utils/cache';
 import { load } from 'cheerio';
-import { ofetch } from 'ofetch';
+import ofetch from '@/utils/ofetch';
 
 const typeMap = {
     dynamic: '协会动态',

package/lib/routes/sciencedirect/cf-email.ts

@@ -23,7 +23,6 @@ const encodeCFEmail = (email) => {
  * The alogrithm is well-explained in https://andrewlock.net/simple-obfuscation-of-email-addresses-using-javascript/
  */
 export {
-    // eslint-disable-next-line lines-around-comment
     /**
      * Returns decoded email address using CloudFlare's email address obfuscation.
      * @param {String} encoded - encoded email, (`cfemail` attribute in `__cf_email__` tag)