rsshub 1.0.0-master.f9ec483 → 1.0.0-master.fa04a11

package/lib/routes/abc/index.ts

@@ -3,7 +3,7 @@ import { getCurrentPath } from '@/utils/helpers';
 const __dirname = getCurrentPath(import.meta.url);
 
 import cache from '@/utils/cache';
-import got from '@/utils/got';
+import ofetch from '@/utils/ofetch';
 import { load } from 'cheerio';
 import { parseDate } from '@/utils/parse-date';
 import { art } from '@/utils/render';
@@ -11,6 +11,7 @@ import path from 'node:path';
 
 export const route: Route = {
     path: '/:category{.+}?',
+    example: '/wa',
     radar: [
         {
             source: ['abc.net.au/:category*'],
@@ -23,14 +24,14 @@ export const route: Route = {
     name: 'Channel & Topic',
     categories: ['traditional-media'],
     description: `
-  :::tip
+::: tip
   All Topics in [Topic Library](https://abc.net.au/news/topics) are supported, you can fill in the field after \`topic\` in its URL, or fill in the \`documentId\`.
 
   For example, the URL for [Computer Science](https://www.abc.net.au/news/topic/computer-science) is \`https://www.abc.net.au/news/topic/computer-science\`, the \`category\` is \`news/topic/computer-science\`, and the \`documentId\` of the Topic is \`2302\`, so the route is [/abc/news/topic/computer-science](https://rsshub.app/abc/news/topic/computer-science) and [/abc/2302](https://rsshub.app/abc/2302).
 
   The supported channels are all listed in the table below. For other channels, please find the \`documentId\` in the source code of the channel page and fill it in as above.
-  :::`,
-    maintainers: ['nczitzk'],
+:::`,
+    maintainers: ['nczitzk', 'pseudoyu'],
     handler,
 };
 
@@ -50,18 +51,18 @@ async function handler(ctx) {
         documentId = category;
         const feedUrl = new URL(`news/feed/${documentId}/rss.xml`, rootUrl).href;
 
-        const { data: feedResponse } = await got(feedUrl);
+        const feedResponse = await ofetch(feedUrl);
         currentUrl = feedResponse.match(/<link>([\w-./:?]+)<\/link>/)[1];
     }
 
-    const { data: currentResponse } = await got(currentUrl);
+    const currentResponse = await ofetch(currentUrl);
 
     const $ = load(currentResponse);
 
     documentId = documentId ?? $('div[data-uri^="coremedia://collection/"]').first().prop('data-uri').split(/\//).pop();
 
-    const { data: response } = await got(apiUrl, {
-        searchParams: {
+    const response = await ofetch(apiUrl, {
+        query: {
             name: 'PaginationArticles',
             documentId,
             size: limit,
@@ -71,7 +72,7 @@ async function handler(ctx) {
     let items = response.collection.slice(0, limit).map((i) => {
         const item = {
             title: i.title.children ?? i.title,
-            link: new URL(i.link.to, rootUrl).href,
+            link: i.link.startsWith('https://') ? i.link : new URL(i.link, rootUrl).href,
             description: art(path.join(__dirname, 'templates/description.art'), {
                 image: i.image
                     ? {
@@ -99,7 +100,7 @@ async function handler(ctx) {
         items.map((item) =>
             cache.tryGet(item.link, async () => {
                 try {
-                    const { data: detailResponse } = await got(item.link);
+                    const detailResponse = await ofetch(item.link);
 
                     const content = load(detailResponse);
 
@@ -173,7 +174,7 @@ async function handler(ctx) {
         )
     );
 
-    const icon = new URL($('link[rel="apple-touch-icon"]').prop('href'), rootUrl).href;
+    const icon = new URL($('link[rel="apple-touch-icon"]').prop('href') || '', rootUrl).href;
 
     return {
         item: items,

package/lib/routes/accessbriefing/index.ts

@@ -123,9 +123,9 @@ export const route: Route = {
     handler,
     example: '/accessbriefing/latest/news',
     parameters: { category: 'Category, Latest News by default' },
-    description: `:::tip
+    description: `::: tip
   If you subscribe to [Latest News](https://www.accessbriefing.com/latest/news)，where the URL is \`https://www.accessbriefing.com/latest/news\`, extract the part \`https://www.accessbriefing.com/\` to the end, and use it as the parameter to fill in. Therefore, the route will be [\`/accessbriefing/latest/news\`](https://rsshub.app/accessbriefing/latest/news).
-  :::
+:::
 
   #### Latest
 

package/lib/routes/acfun/bangumi.ts

@@ -19,7 +19,7 @@ export const route: Route = {
     name: '番剧',
     maintainers: ['xyqfer'],
     handler,
-    description: `:::tip
+    description: `::: tip
 番剧 id 不包含开头的 aa。
 例如：\`https://www.acfun.cn/bangumi/aa5022158\` 的番剧 id 是 5022158，不包括开头的 aa。
 :::`,

package/lib/routes/aeaweb/index.ts

@@ -32,9 +32,9 @@ export const route: Route = {
     handler,
     description: `The URL of the journal [American Economic Review](https://www.aeaweb.org/journals/aer) is \`https://www.aeaweb.org/journals/aer\`, where \`aer\` is the id of the journal, so the route for this journal is \`/aeaweb/aer\`.
 
-  :::tip
+::: tip
   More jounals can be found in [AEA Journals](https://www.aeaweb.org/journals).
-  :::`,
+:::`,
 };
 
 async function handler(ctx) {

package/lib/routes/aeon/category.ts

@@ -1,13 +1,24 @@
 import { Route } from '@/types';
-import { load } from 'cheerio';
-import got from '@/utils/got';
-import { getData } from './utils';
+import ofetch from '@/utils/ofetch';
+import { getBuildId, getData } from './utils';
+import { parseDate } from '@/utils/parse-date';
 
 export const route: Route = {
     path: '/category/:category',
-    categories: ['new-media'],
+    categories: ['new-media', 'popular'],
     example: '/aeon/category/philosophy',
-    parameters: { category: 'Category' },
+    parameters: {
+        category: {
+            description: 'Category',
+            options: [
+                { value: 'philosophy', label: 'Philosophy' },
+                { value: 'science', label: 'Science' },
+                { value: 'psychology', label: 'Psychology' },
+                { value: 'society', label: 'Society' },
+                { value: 'culture', label: 'Culture' },
+            ],
+        },
+    },
     features: {
         requireConfig: false,
         requirePuppeteer: false,
@@ -18,34 +29,40 @@ export const route: Route = {
     },
     radar: [
         {
-            source: ['aeon.aeon.co/:category'],
+            source: ['aeon.co/:category'],
         },
     ],
     name: 'Categories',
     maintainers: ['emdoe'],
     handler,
-    description: `Supported categories: Philosophy, Science, Psychology, Society, and Culture.`,
 };
 
 async function handler(ctx) {
-    const url = `https://aeon.co/${ctx.req.param('category')}`;
-    const { data: response } = await got(url);
-    const $ = load(response);
+    const category = ctx.req.param('category').toLowerCase();
+    const url = `https://aeon.co/category/${category}`;
+    const buildId = await getBuildId();
+    const response = await ofetch(`https://aeon.co/_next/data/${buildId}/${category}.json`);
 
-    const data = JSON.parse($('script#__NEXT_DATA__').text());
+    const section = response.pageProps.section;
 
-    const list = data.props.pageProps.section.articles.edges.map((item) => ({
-        title: item.node.title,
-        author: item.node.authors.map((author) => author.displayName).join(', '),
-        link: `https://aeon.co/${item.node.type.toLowerCase()}s/${item.node.slug}`,
+    const list = section.articles.edges.map(({ node }) => ({
+        title: node.title,
+        description: node.standfirstLong,
+        author: node.authors.map((author) => author.displayName).join(', '),
+        link: `https://aeon.co/${node.type}s/${node.slug}`,
+        pubDate: parseDate(node.createdAt),
+        category: [node.section.title, ...node.topics.map((topic) => topic.title)],
+        image: node.image.url,
+        type: node.type,
+        slug: node.slug,
     }));
 
-    const items = await getData(ctx, list);
+    const items = await getData(list);
 
     return {
-        title: `AEON | ${data.props.pageProps.section.title}`,
+        title: `AEON | ${section.title}`,
         link: url,
-        description: data.props.pageProps.section.metaDescription,
+        description: section.metaDescription,
         item: items,
     };
 }

package/lib/routes/aeon/namespace.ts

@@ -2,6 +2,6 @@ import type { Namespace } from '@/types';
 
 export const namespace: Namespace = {
     name: 'AEON',
-    url: 'aeon.aeon.co',
+    url: 'aeon.co',
     lang: 'en',
 };

package/lib/routes/aeon/templates/essay.art

@@ -1,3 +1,9 @@
-<img src="{{ banner }}" alt="">
+{{ if banner.url }}
+<figure>
+    <img src="{{ banner.url }}" alt="{{ banner.alt }}">
+    {{ if banner.caption }}
+    <figcaption>{{ banner.caption }}</figcaption>
+    {{ /if }}
+{{ /if }}
 {{@ authorsBio }}
-{{@ content}}
+{{@ content }}

package/lib/routes/aeon/templates/video.art

@@ -1,10 +1,10 @@
 {{ set video = article.hosterId }}
 {{ if article.hoster === 'vimeo' }}
-    {{ set video = "https://player.vimeo.com/video/" + video + "?dnt=1"}}
-{{ else if article.hoster == 'youtube' }}
+    {{ set video = "https://player.vimeo.com/video/" + video + "?dnt=1" }}
+{{ else if article.hoster === 'youtube' }}
     {{ set video = "https://www.youtube-nocookie.com/embed/" + video }}
 {{ /if }}
 
 <iframe width="672" height="377" src="{{ video }}" frameborder="0" allowfullscreen></iframe>
-{{@ article.credits}}
-{{@ article.description}}
+{{@ article.credits }}
+{{@ article.description }}

package/lib/routes/aeon/type.ts

@@ -1,13 +1,22 @@
 import { Route } from '@/types';
-import { load } from 'cheerio';
-import got from '@/utils/got';
-import { getData } from './utils';
+import ofetch from '@/utils/ofetch';
+import { getBuildId, getData } from './utils';
+import { parseDate } from '@/utils/parse-date';
 
 export const route: Route = {
     path: '/:type',
-    categories: ['new-media'],
+    categories: ['new-media', 'popular'],
     example: '/aeon/essays',
-    parameters: { type: 'Type' },
+    parameters: {
+        type: {
+            description: 'Type',
+            options: [
+                { value: 'essays', label: 'Essays' },
+                { value: 'videos', label: 'Videos' },
+                { value: 'audio', label: 'Audio' },
+            ],
+        },
+    },
     features: {
         requireConfig: false,
         requirePuppeteer: false,
@@ -18,7 +27,7 @@ export const route: Route = {
     },
     radar: [
         {
-            source: ['aeon.aeon.co/:type'],
+            source: ['aeon.co/:type'],
         },
     ],
     name: 'Types',
@@ -26,28 +35,30 @@ export const route: Route = {
     handler,
     description: `Supported types: Essays, Videos, and Audio.
 
-  Compared to the official one, the RSS feed generated by RSSHub not only has more fine-grained options, but also eliminates pull quotes, which can't be easily distinguished from other paragraphs by any RSS reader, but only disrupt the reading flow. This feed also provides users with a bio of the author at the top.
-
-  However, The content generated under \`audio\` does not contain links to audio files.`,
+  Compared to the official one, the RSS feed generated by RSSHub not only has more fine-grained options, but also eliminates pull quotes, which can't be easily distinguished from other paragraphs by any RSS reader, but only disrupt the reading flow. This feed also provides users with a bio of the author at the top.`,
 };
 
 async function handler(ctx) {
     const type = ctx.req.param('type');
-    const binaryType = type === 'videos' ? 'videos' : 'essays';
     const capitalizedType = type.charAt(0).toUpperCase() + type.slice(1);
 
+    const buildId = await getBuildId();
     const url = `https://aeon.co/${type}`;
-    const { data: response } = await got(url);
-    const $ = load(response);
-
-    const data = JSON.parse($('script#__NEXT_DATA__').text());
+    const response = await ofetch(`https://aeon.co/_next/data/${buildId}/${type}.json`);
 
-    const list = data.props.pageProps.articles.map((item) => ({
-        title: item.title,
-        link: `https://aeon.co/${binaryType}/${item.slug}`,
+    const list = response.pageProps.articles.map((node) => ({
+        title: node.title,
+        description: node.standfirstLong,
+        author: node.authors.map((author) => author.displayName).join(', '),
+        link: `https://aeon.co/${node.type}s/${node.slug}`,
+        pubDate: parseDate(node.createdAt),
+        category: [node.section.title, ...node.topics.map((topic) => topic.title)],
+        image: node.image.url,
+        type: node.type,
+        slug: node.slug,
     }));
 
-    const items = await getData(ctx, list);
+    const items = await getData(list);
 
     return {
         title: `AEON | ${capitalizedType}`,

package/lib/routes/aeon/utils.ts

@@ -3,28 +3,61 @@ const __dirname = getCurrentPath(import.meta.url);
 
 import cache from '@/utils/cache';
 import { load } from 'cheerio';
-import got from '@/utils/got';
+import ofetch from '@/utils/ofetch';
 import { art } from '@/utils/render';
 import path from 'node:path';
+import { config } from '@/config';
+import { parseDate } from '@/utils/parse-date';
 
-const getData = async (ctx, list) => {
+export const getBuildId = () =>
+    cache.tryGet(
+        'aeon:buildId',
+        async () => {
+            const response = await ofetch('https://aeon.co');
+            const $ = load(response);
+            const nextData = JSON.parse($('script#__NEXT_DATA__').text());
+            return nextData.buildId;
+        },
+        config.cache.routeExpire,
+        false
+    );
+
+const getData = async (list) => {
     const items = await Promise.all(
         list.map((item) =>
             cache.tryGet(item.link, async () => {
-                const { data: response } = await got(item.link);
-                const $ = load(response);
+                const buildId = await getBuildId();
+                const response = await ofetch(`https://aeon.co/_next/data/${buildId}/${item.type}s/${item.slug}.json?id=${item.slug}`);
 
-                const data = JSON.parse($('script#__NEXT_DATA__').text());
-                const type = data.props.pageProps.article.type.toLowerCase();
+                const data = response.pageProps.article;
+                const type = data.type.toLowerCase();
 
-                item.pubDate = new Date(data.props.pageProps.article.publishedAt).toUTCString();
+                item.pubDate = parseDate(data.publishedAt);
 
                 if (type === 'video') {
-                    item.description = art(path.join(__dirname, 'templates/video.art'), { article: data.props.pageProps.article });
+                    item.description = art(path.join(__dirname, 'templates/video.art'), { article: data });
                 } else {
-                    // Essay or Audio
-                    // But unfortunately, the method based on __NEXT_DATA__
-                    // does not include the information of the audio link.
+                    if (data.audio?.id) {
+                        const response = await ofetch('https://api.aeonmedia.co/graphql', {
+                            method: 'POST',
+                            body: {
+                                query: `query getAudio($audioId: ID!) {
+                                    audio(id: $audioId) {
+                                        id
+                                        streamUrl
+                                    }
+                                }`,
+                                variables: {
+                                    audioId: data.audio.id,
+                                },
+                                operationName: 'getAudio',
+                            },
+                        });
+
+                        delete item.image;
+                        item.enclosure_url = response.data.audio.streamUrl;
+                        item.enclosure_type = 'audio/mpeg';
+                    }
 
                     // Besides, it seems that the method based on __NEXT_DATA__
                     // does not include the information of the two-column
@@ -32,14 +65,11 @@ const getData = async (ctx, list) => {
                     // e.g. https://aeon.co/essays/how-to-mourn-a-forest-a-lesson-from-west-papua .
                     // But that's very rare.
 
-                    item.author = data.props.pageProps.article.authors.map((author) => author.name).join(', ');
-
-                    const article = data.props.pageProps.article;
-                    const capture = load(article.body);
-                    const banner = article.image?.url;
+                    const capture = load(data.body, null, false);
+                    const banner = data.image;
                     capture('p.pullquote').remove();
 
-                    const authorsBio = article.authors.map((author) => '<p>' + author.name + author.authorBio.replaceAll(/^<p>/g, ' ')).join('');
+                    const authorsBio = data.authors.map((author) => '<p>' + author.name + author.authorBio.replaceAll(/^<p>/g, ' ')).join('');
 
                     item.description = art(path.join(__dirname, 'templates/essay.art'), { banner, authorsBio, content: capture.html() });
                 }

package/lib/routes/afr/latest.ts

@@ -0,0 +1,69 @@
+import { Route } from '@/types';
+import type { Context } from 'hono';
+
+import cache from '@/utils/cache';
+import ofetch from '@/utils/ofetch';
+import { parseDate } from '@/utils/parse-date';
+import { assetsConnectionByCriteriaQuery } from './query';
+import { getItem } from './utils';
+
+export const route: Route = {
+    path: '/latest',
+    categories: ['traditional-media'],
+    example: '/afr/latest',
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['www.afr.com/latest', 'www.afr.com/'],
+        },
+    ],
+    name: 'Latest',
+    maintainers: ['TonyRL'],
+    handler,
+    url: 'www.afr.com/latest',
+};
+
+async function handler(ctx: Context) {
+    const limit = Number.parseInt(ctx.req.query('limit') ?? '10');
+    const response = await ofetch('https://api.afr.com/graphql', {
+        query: {
+            query: assetsConnectionByCriteriaQuery,
+            operationName: 'assetsConnectionByCriteria',
+            variables: {
+                brand: 'afr',
+                first: limit,
+                render: 'web',
+                types: ['article', 'bespoke', 'featureArticle', 'liveArticle', 'video'],
+                after: '',
+            },
+        },
+    });
+
+    const list = response.data.assetsConnectionByCriteria.edges.map(({ node }) => ({
+        title: node.asset.headlines.headline,
+        description: node.asset.about,
+        link: `https://www.afr.com${node.urls.published.afr.path}`,
+        pubDate: parseDate(node.dates.firstPublished),
+        updated: parseDate(node.dates.modified),
+        author: node.asset.byline,
+        category: [node.tags.primary.displayName, ...node.tags.secondary.map((tag) => tag.displayName)],
+        image: node.featuredImages && `https://static.ffx.io/images/${node.featuredImages.landscape16x9.data.id}`,
+    }));
+
+    const items = await Promise.all(list.map((item) => cache.tryGet(item.link, () => getItem(item))));
+
+    return {
+        title: 'Latest | The Australian Financial Review | AFR',
+        description: 'The latest news, events, analysis and opinion from The Australian Financial Review',
+        image: 'https://www.afr.com/apple-touch-icon-1024x1024.png',
+        link: 'https://www.afr.com/latest',
+        item: items,
+    };
+}

package/lib/routes/afr/namespace.ts

@@ -0,0 +1,7 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: 'The Australian Financial Review',
+    url: 'afr.com',
+    lang: 'en',
+};

package/lib/routes/afr/navigation.ts

@@ -0,0 +1,75 @@
+import { Route } from '@/types';
+import type { Context } from 'hono';
+
+import cache from '@/utils/cache';
+import ofetch from '@/utils/ofetch';
+import { parseDate } from '@/utils/parse-date';
+import { pageByNavigationPathQuery } from './query';
+import { getItem } from './utils';
+
+export const route: Route = {
+    path: '/navigation/:path{.+}',
+    categories: ['traditional-media'],
+    example: '/afr/navigation/markets',
+    parameters: {
+        path: 'Navigation path, can be found in the URL of the page',
+    },
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['www.afr.com/path*'],
+        },
+    ],
+    name: 'Navigation',
+    maintainers: ['TonyRL'],
+    handler,
+    url: 'www.afr.com',
+};
+
+async function handler(ctx: Context) {
+    const { path } = ctx.req.param();
+    const limit = Number.parseInt(ctx.req.query('limit') ?? '10');
+
+    const response = await ofetch('https://api.afr.com/api/content-audience/afr/graphql', {
+        query: {
+            query: pageByNavigationPathQuery,
+            operationName: 'pageByNavigationPath',
+            variables: {
+                input: { brandKey: 'afr', navigationPath: `/${path}`, renderName: 'web' },
+                firstStories: limit,
+                afterStories: '',
+            },
+        },
+    });
+
+    const list = response.data.pageByNavigationPath.page.latestStoriesConnection.edges.map(({ node }) => ({
+        title: node.headlines.headline,
+        description: node.overview.about,
+        link: `https://www.afr.com${node.urls.canonical.path}`,
+        pubDate: parseDate(node.dates.firstPublished),
+        updated: parseDate(node.dates.modified),
+        author: node.byline
+            .filter((byline) => byline.type === 'AUTHOR')
+            .map((byline) => byline.author.name)
+            .join(', '),
+        category: [node.tags.primary.displayName, ...node.tags.secondary.map((tag) => tag.displayName)],
+        image: node.images && `https://static.ffx.io/images/${node.images.landscape16x9.mediaId}`,
+    }));
+
+    const items = await Promise.all(list.map((item) => cache.tryGet(item.link, () => getItem(item))));
+
+    return {
+        title: response.data.pageByNavigationPath.page.seo.title,
+        description: response.data.pageByNavigationPath.page.seo.description,
+        image: 'https://www.afr.com/apple-touch-icon-1024x1024.png',
+        link: `https://www.afr.com/${path}`,
+        item: items,
+    };
+}