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

package/lib/routes/deeplearning/templates/description.art

@@ -0,0 +1,21 @@
+{{ if images }}
+  {{ each images image }}
+    {{ if image?.src }}
+      <figure>
+        <img
+          {{ if image.alt }}
+            alt="{{ image.alt }}"
+          {{ /if }}
+        src="{{ image.src }}">
+      </figure>
+    {{ /if }}
+  {{ /each }}
+{{ /if }}
+
+{{ if intro }}
+  <blockquote>{{ intro }}</blockquote>
+{{ /if }}
+
+{{ if description }}
+  {{@ description }}
+{{ /if }}

package/lib/routes/deeplearning/the-batch.ts

@@ -0,0 +1,296 @@
+import { Route } from '@/types';
+import { getCurrentPath } from '@/utils/helpers';
+const __dirname = getCurrentPath(import.meta.url);
+
+import cache from '@/utils/cache';
+import ofetch from '@/utils/ofetch';
+import { load } from 'cheerio';
+import { parseDate } from '@/utils/parse-date';
+import { art } from '@/utils/render';
+import path from 'node:path';
+
+export const handler = async (ctx) => {
+    const { tag } = ctx.req.param();
+    const limit = ctx.req.query('limit') ? Number.parseInt(ctx.req.query('limit'), 10) : 1;
+
+    const rootUrl = 'https://www.deeplearning.ai';
+    const currentUrl = new URL(`the-batch${tag ? `/tag/${tag.replace(/^tag\//, '').replace(/\/$/, '')}` : ''}/`, rootUrl).href;
+
+    const response = await ofetch(currentUrl);
+
+    const $ = load(response);
+
+    const language = $('html').prop('lang');
+
+    const data = JSON.parse($('script#__NEXT_DATA__').text());
+
+    const nextBuildId = data.buildId;
+    const posts = data.props?.pageProps?.posts ?? [];
+
+    let items = posts.slice(0, limit).map((item) => {
+        const title = item.title;
+        const description = art(path.join(__dirname, 'templates/description.art'), {
+            images: item.feature_image
+                ? [
+                      {
+                          src: item.feature_image,
+                          alt: item.feature_image_alt,
+                      },
+                  ]
+                : undefined,
+            intro: item.excerpt ?? item.custom_excerpt,
+        });
+        const image = item.feature_image;
+        const guid = `the-batch-${item.slug}`;
+
+        return {
+            title,
+            description,
+            pubDate: parseDate(item.published_at),
+            link: new URL(`_next/data/${nextBuildId}/the-batch/${item.slug}.json`, rootUrl).href,
+            category: item.tags.map((t) => t.name),
+            guid,
+            id: guid,
+            content: {
+                html: description,
+                text: item.excerpt ?? item.custom_excerpt,
+            },
+            image,
+            banner: image,
+            language,
+        };
+    });
+
+    items = await Promise.all(
+        items.map((item) =>
+            cache.tryGet(item.link, async () => {
+                const detailResponse = await ofetch(item.link);
+
+                const post = detailResponse.pageProps?.cmsData?.post ?? undefined;
+
+                if (!post) {
+                    return item;
+                }
+
+                const $$ = load(post.html);
+
+                $$('a').each((_, ele) => {
+                    if (ele.attribs.href?.includes('utm_campaign')) {
+                        const url = new URL(ele.attribs.href);
+                        url.searchParams.delete('utm_campaign');
+                        url.searchParams.delete('utm_source');
+                        url.searchParams.delete('utm_medium');
+                        url.searchParams.delete('_hsenc');
+                        ele.attribs.href = url.href;
+                    }
+                });
+
+                const title = post.title;
+                const description = art(path.join(__dirname, 'templates/description.art'), {
+                    images: post.feature_image
+                        ? [
+                              {
+                                  src: post.feature_image,
+                                  alt: post.feature_image_alt,
+                              },
+                          ]
+                        : undefined,
+                    intro: post.excerpt ?? post.custom_excerpt,
+                    description: $$.html(),
+                });
+                const guid = `the-batch-${post.slug}`;
+                const image = post.feature_image;
+
+                item.title = title;
+                item.description = description;
+                item.pubDate = parseDate(post.published_at);
+                item.link = new URL(`the-batch/${post.slug}`, rootUrl).href;
+                item.category = post.tags.map((t) => t.name);
+                item.author = post.authors.map((a) => a.name).join('/');
+                item.guid = guid;
+                item.id = guid;
+                item.content = {
+                    html: description,
+                    text: post.excerpt ?? post.custom_excerpt,
+                };
+                item.image = image;
+                item.banner = image;
+                item.updated = parseDate(post.updated_at);
+                item.language = language;
+
+                return item;
+            })
+        )
+    );
+
+    const image = new URL($('meta[property="og:image"]').prop('content'), rootUrl).href;
+
+    return {
+        title: $('title').text(),
+        description: $('meta[property="og:description"]').prop('content'),
+        link: currentUrl,
+        item: items,
+        allowEmpty: true,
+        image,
+        author: $('meta[property="og:site_name"]').prop('content'),
+        language,
+    };
+};
+
+export const route: Route = {
+    path: '/the-batch/:tag{.+}?',
+    name: 'The Batch',
+    url: 'www.deeplearning.ai',
+    maintainers: ['nczitzk', 'juvenn', 'TonyRL'],
+    handler,
+    example: '/deeplearning/the-batch',
+    parameters: { tag: 'Tag, Weekly Issues by default' },
+    description: `::: tip
+  If you subscribe to [Data Points](https://www.deeplearning.ai/the-batch/tag/data-points/)，where the URL is \`https://www.deeplearning.ai/the-batch/tag/data-points/\`, extract the part \`https://www.deeplearning.ai/the-batch/tag\` to the end, which is \`data-points\`, and use it as the parameter to fill in. Therefore, the route will be [\`/deeplearning/the-batch/data-points\`](https://rsshub.app/deeplearning/the-batch/data-points).
+
+:::
+
+  | Tag                                                                    | ID                                                                   |
+  | ---------------------------------------------------------------------- | -------------------------------------------------------------------- |
+  | [Weekly Issues](https://www.deeplearning.ai/the-batch/)                | [*null*](https://rsshub.app/deeplearning/the-batch)                  |
+  | [Andrew's Letters](https://www.deeplearning.ai/the-batch/tag/letters/) | [letters](https://rsshub.app/deeplearning/the-batch/letters)         |
+  | [Data Points](https://www.deeplearning.ai/the-batch/tag/data-points/)  | [data-points](https://rsshub.app/deeplearning/the-batch/data-points) |
+  | [ML Research](https://www.deeplearning.ai/the-batch/tag/research/)     | [research](https://rsshub.app/deeplearning/the-batch/research)       |
+  | [Business](https://www.deeplearning.ai/the-batch/tag/business/)        | [business](https://rsshub.app/deeplearning/the-batch/business)       |
+  | [Science](https://www.deeplearning.ai/the-batch/tag/science/)          | [science](https://rsshub.app/deeplearning/the-batch/science)         |
+  | [AI & Society](https://www.deeplearning.ai/the-batch/tag/ai-society/)  | [ai-society](https://rsshub.app/deeplearning/the-batch/ai-society)   |
+  | [Culture](https://www.deeplearning.ai/the-batch/tag/culture/)          | [culture](https://rsshub.app/deeplearning/the-batch/culture)         |
+  | [Hardware](https://www.deeplearning.ai/the-batch/tag/hardware/)        | [hardware](https://rsshub.app/deeplearning/the-batch/hardware)       |
+  | [AI Careers](https://www.deeplearning.ai/the-batch/tag/ai-careers/)    | [ai-careers](https://rsshub.app/deeplearning/the-batch/ai-careers)   |
+
+  #### [Letters from Andrew Ng](https://www.deeplearning.ai/the-batch/tag/letters/)
+
+  | Tag                                                                                     | ID                                                                                     |
+  | --------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------- |
+  | [All](https://www.deeplearning.ai/the-batch/tag/letters/)                               | [letters](https://rsshub.app/deeplearning/the-batch/letters)                           |
+  | [Personal Insights](https://www.deeplearning.ai/the-batch/tag/personal-insights/)       | [personal-insights](https://rsshub.app/deeplearning/the-batch/personal-insights)       |
+  | [Technical Insights](https://www.deeplearning.ai/the-batch/tag/technical-insights/)     | [technical-insights](https://rsshub.app/deeplearning/the-batch/technical-insights)     |
+  | [Business Insights](https://www.deeplearning.ai/the-batch/tag/business-insights/)       | [business-insights](https://rsshub.app/deeplearning/the-batch/business-insights)       |
+  | [Tech & Society](https://www.deeplearning.ai/the-batch/tag/tech-society/)               | [tech-society](https://rsshub.app/deeplearning/the-batch/tech-society)                 |
+  | [DeepLearning.AI News](https://www.deeplearning.ai/the-batch/tag/deeplearning-ai-news/) | [deeplearning-ai-news](https://rsshub.app/deeplearning/the-batch/deeplearning-ai-news) |
+  | [AI Careers](https://www.deeplearning.ai/the-batch/tag/ai-careers/)                     | [ai-careers](https://rsshub.app/deeplearning/the-batch/ai-careers)                     |
+  | [Just For Fun](https://www.deeplearning.ai/the-batch/tag/just-for-fun/)                 | [just-for-fun](https://rsshub.app/deeplearning/the-batch/just-for-fun)                 |
+  | [Learning & Education](https://www.deeplearning.ai/the-batch/tag/learning-education/)   | [learning-education](https://rsshub.app/deeplearning/the-batch/learning-education)     |
+    `,
+    categories: ['programming'],
+
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportRadar: true,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['www.deeplearning.ai/the-batch', 'www.deeplearning.ai/the-batch/tag/:tag/'],
+            target: (params) => {
+                const tag = params.tag;
+
+                return `/the-batch${tag ? `/${tag}` : ''}`;
+            },
+        },
+        {
+            title: 'Weekly Issues',
+            source: ['www.deeplearning.ai/the-batch/'],
+            target: '/the-batch',
+        },
+        {
+            title: "Andrew's Letters",
+            source: ['www.deeplearning.ai/the-batch/tag/letters/'],
+            target: '/the-batch/letters',
+        },
+        {
+            title: 'Data Points',
+            source: ['www.deeplearning.ai/the-batch/tag/data-points/'],
+            target: '/the-batch/data-points',
+        },
+        {
+            title: 'ML Research',
+            source: ['www.deeplearning.ai/the-batch/tag/research/'],
+            target: '/the-batch/research',
+        },
+        {
+            title: 'Business',
+            source: ['www.deeplearning.ai/the-batch/tag/business/'],
+            target: '/the-batch/business',
+        },
+        {
+            title: 'Science',
+            source: ['www.deeplearning.ai/the-batch/tag/science/'],
+            target: '/the-batch/science',
+        },
+        {
+            title: 'AI & Society',
+            source: ['www.deeplearning.ai/the-batch/tag/ai-society/'],
+            target: '/the-batch/ai-society',
+        },
+        {
+            title: 'Culture',
+            source: ['www.deeplearning.ai/the-batch/tag/culture/'],
+            target: '/the-batch/culture',
+        },
+        {
+            title: 'Hardware',
+            source: ['www.deeplearning.ai/the-batch/tag/hardware/'],
+            target: '/the-batch/hardware',
+        },
+        {
+            title: 'AI Careers',
+            source: ['www.deeplearning.ai/the-batch/tag/ai-careers/'],
+            target: '/the-batch/ai-careers',
+        },
+        {
+            title: 'Letters from Andrew Ng - All',
+            source: ['www.deeplearning.ai/the-batch/tag/letters/'],
+            target: '/the-batch/letters',
+        },
+        {
+            title: 'Letters from Andrew Ng - Personal Insights',
+            source: ['www.deeplearning.ai/the-batch/tag/personal-insights/'],
+            target: '/the-batch/personal-insights',
+        },
+        {
+            title: 'Letters from Andrew Ng - Technical Insights',
+            source: ['www.deeplearning.ai/the-batch/tag/technical-insights/'],
+            target: '/the-batch/technical-insights',
+        },
+        {
+            title: 'Letters from Andrew Ng - Business Insights',
+            source: ['www.deeplearning.ai/the-batch/tag/business-insights/'],
+            target: '/the-batch/business-insights',
+        },
+        {
+            title: 'Letters from Andrew Ng - Tech & Society',
+            source: ['www.deeplearning.ai/the-batch/tag/tech-society/'],
+            target: '/the-batch/tech-society',
+        },
+        {
+            title: 'Letters from Andrew Ng - DeepLearning.AI News',
+            source: ['www.deeplearning.ai/the-batch/tag/deeplearning-ai-news/'],
+            target: '/the-batch/deeplearning-ai-news',
+        },
+        {
+            title: 'Letters from Andrew Ng - AI Careers',
+            source: ['www.deeplearning.ai/the-batch/tag/ai-careers/'],
+            target: '/the-batch/ai-careers',
+        },
+        {
+            title: 'Letters from Andrew Ng - Just For Fun',
+            source: ['www.deeplearning.ai/the-batch/tag/just-for-fun/'],
+            target: '/the-batch/just-for-fun',
+        },
+        {
+            title: 'Letters from Andrew Ng - Learning & Education',
+            source: ['www.deeplearning.ai/the-batch/tag/learning-education/'],
+            target: '/the-batch/learning-education',
+        },
+    ],
+};

package/lib/routes/deepmind/blog.ts

@@ -6,7 +6,7 @@ import parser from '@/utils/rss-parser';
 
 export const route: Route = {
     path: '/blog',
-    categories: ['new-media'],
+    categories: ['new-media', 'popular'],
     example: '/deepmind/blog',
     parameters: {},
     features: {

package/lib/routes/deepseek/namespace.ts

@@ -0,0 +1,8 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: 'Deepseek',
+    url: 'api-docs.deepseek.com',
+    description: 'Deepseek API 文档。',
+    lang: 'zh-CN',
+};

package/lib/routes/deepseek/news.ts

@@ -0,0 +1,88 @@
+import { Route, Data, DataItem } from '@/types';
+import ofetch from '@/utils/ofetch';
+import { load } from 'cheerio';
+import cache from '@/utils/cache';
+
+const ROOT_URL = 'https://api-docs.deepseek.com/zh-cn';
+
+const NEWS_LIST_SELECTOR = 'ul.menu__list > li:nth-child(2) ul > li.theme-doc-sidebar-item-link';
+const ARTICLE_CONTENT_SELECTOR = '.theme-doc-markdown > div > div';
+const ARTICLE_TITLE_SELECTOR = ARTICLE_CONTENT_SELECTOR + ' > h1';
+
+// 获取消息列表 / get article list
+const fetchPageContent = async (url: string) => {
+    const response = await ofetch(url);
+    return load(response);
+};
+
+// 提取正文内容 / extract article content
+const extractArticleInfo = ($article: cheerio.Root, pageURL: string) => {
+    const contentElement = $article(ARTICLE_CONTENT_SELECTOR);
+    const title = $article(ARTICLE_TITLE_SELECTOR).text();
+    $article(ARTICLE_TITLE_SELECTOR).remove(); // 移除标题，避免重复 / remove title to avoid duplication
+    const content = contentElement.html();
+    return { title, content, pageURL };
+};
+
+const parseDateString = (dateString: string) => {
+    const pubDate = new Date(dateString);
+    return pubDate.toUTCString();
+};
+
+// 创建消息 / create article
+const createDataItem = (item: cheerio.Element, $: cheerio.Root): Promise<DataItem> => {
+    const $item = $(item);
+    const link = $item.find('a').attr('href');
+    const dateString = $item.find('a').text().split(' ').at(-1);
+    const pageURL = new URL(link || '', ROOT_URL).href;
+
+    return cache.tryGet(pageURL, async () => {
+        const $article = await fetchPageContent(pageURL);
+        const { title, content } = extractArticleInfo($article, pageURL);
+        const pubDate = parseDateString(dateString);
+
+        return {
+            title,
+            link: pageURL,
+            pubDate,
+            description: content || undefined,
+        };
+    });
+};
+
+const handler = async (): Promise<Data> => {
+    const $ = await fetchPageContent(ROOT_URL);
+    const newsList = $(NEWS_LIST_SELECTOR);
+
+    const items: DataItem[] = await Promise.all(newsList.toArray().map((li) => createDataItem(li, $)));
+
+    return {
+        title: 'DeepSeek 新闻',
+        link: ROOT_URL,
+        item: items,
+        allowEmpty: true,
+    };
+};
+
+export const route: Route = {
+    path: '/news',
+    categories: ['programming'],
+    example: '/deepseek/news',
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['api-docs.deepseek.com'],
+            target: '/news',
+        },
+    ],
+    name: '新闻',
+    maintainers: ['1837634311'],
+    handler,
+};

package/lib/routes/dehenglaw/index.ts

@@ -90,13 +90,13 @@ export const route: Route = {
     handler,
     example: '/dehenglaw/CN/paper',
     parameters: { language: '语言，默认为中文，即 CN，可在对应分类页 URL 中找到，可选 CN 和 EN', category: '分类，默认为专业文章，即 paper，可在对应分类页 URL 中找到' },
-    description: `:::tip
+    description: `::: tip
   若订阅 [专业文章](https://dehenglaw.com/)，网址为 \`https://www.dehenglaw.com/CN/paper/0008/000902.aspx\`。截取 \`https://dehenglaw.com/\` 到末尾 \`/0008/000902.aspx\` 的部分 \`CN/paper\` 作为参数填入，此时路由为 [\`/dehenglaw/CN/paper\`](https://rsshub.app/dehenglaw/CN/paper)。
 
   | 专业文章 | 出版物  | 德恒论坛 |
   | -------- | ------- | -------- |
   | paper    | publish | luntan   |
-  :::`,
+:::`,
     categories: ['new-media'],
 
     features: {

package/lib/routes/diandong/news.ts

@@ -19,7 +19,7 @@ const titleMap = {
 
 export const route: Route = {
     path: '/news/:cate?',
-    categories: ['new-media'],
+    categories: ['new-media', 'popular'],
     example: '/diandong/news',
     parameters: { cate: '分类，见下表，默认为推荐' },
     features: {

package/lib/routes/digitalcameraworld/news.ts

@@ -5,7 +5,7 @@ import { parseDate } from '@/utils/parse-date';
 const host = 'https://www.digitalcameraworld.com';
 export const route: Route = {
     path: '/news',
-    categories: ['new-media'],
+    categories: ['new-media', 'popular'],
     example: '/digitalcameraworld/news',
     parameters: {},
     features: {

package/lib/routes/dingshao/namespace.ts

@@ -0,0 +1,7 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: '盯梢',
+    url: 'www.dingshao.cn',
+    lang: 'zh-CN',
+};

package/lib/routes/dingshao/share.ts

@@ -0,0 +1,53 @@
+import { Route } from '@/types';
+import ofetch from '@/utils/ofetch';
+import { parseDate } from '@/utils/parse-date';
+import type { Context } from 'hono';
+import { Value } from './types';
+
+export const route: Route = {
+    path: '/share/:shortId',
+    categories: ['other'],
+    example: '/dingshao/share/FzFypN',
+    parameters: {
+        shortId: '频道 ID',
+    },
+    radar: [
+        {
+            source: ['www.dingshao.cn/share/:shortId'],
+        },
+    ],
+    name: '频道',
+    maintainers: ['TonyRL'],
+    handler,
+};
+
+const baseUrl = 'https://www.dingshao.cn';
+
+async function handler(ctx: Context) {
+    const { shortId } = ctx.req.param();
+
+    const response = await ofetch<Value>(`${baseUrl}/api/v2/channel/get-channel-and-recent-messages-by-short-id`, {
+        method: 'POST',
+        body: {
+            shortId,
+        },
+    });
+
+    const items = response.value.bundle.channelMessages.map((message) => ({
+        title: message.excerpt.split('\n')[0],
+        description: message.content,
+        pubDate: parseDate(message.publishedAt),
+        category: message.tags,
+        link: `${baseUrl}/channel/${response.value.channel}/${message.id}`,
+    }));
+
+    const channelProfile = response.value.bundle.channels.find((channel) => channel.id === response.value.channel)?.profile;
+
+    return {
+        title: channelProfile?.name,
+        description: channelProfile?.description,
+        link: `${baseUrl}/share/${shortId}`,
+        image: channelProfile?.image,
+        item: items,
+    };
+}

package/lib/routes/dingshao/types.ts

@@ -0,0 +1,64 @@
+export interface Value {
+    value: {
+        channel: string;
+        recentMessages: string[];
+        bundle: Bundle;
+    };
+}
+
+interface Bundle {
+    channels: Channel[];
+    users: User[];
+    channelMessages: ChannelMessage[];
+    channelMessageInteractions: any[];
+}
+
+interface Channel {
+    id: string;
+    owner: string;
+    profile: Profile;
+    tags: string[];
+    script: Script;
+    private: boolean;
+    stats: Stats;
+    sharable: boolean;
+    lastPublishedAt: string;
+}
+
+interface Profile {
+    name: string;
+    description: string;
+    image: string;
+}
+
+interface Script {
+    homepage: string;
+}
+
+interface Stats {
+    subscribers: number;
+}
+
+interface User {
+    id: string;
+    profile: UserProfile;
+}
+
+interface UserProfile {
+    name: string;
+    image: string;
+}
+
+interface ChannelMessage {
+    id: string;
+    channel: string;
+    author: string;
+    tags: string[];
+    excerpt: string;
+    content: string;
+    likes: number;
+    private: boolean;
+    sharable: boolean;
+    script: boolean;
+    publishedAt: string;
+}

package/lib/routes/discord/discord-api.ts

@@ -1,7 +1,9 @@
+import { APIMessage } from 'discord-api-types/v10';
+import { RESTGetAPIGuildResult, RESTGetAPIGuildChannelsResult, RESTGetAPIChannelResult, RESTGetAPIChannelMessagesQuery, RESTGetAPIChannelMessagesResult } from 'discord-api-types/rest/v10';
+
+import { config } from '@/config';
 import cache from '@/utils/cache';
 import ofetch from '@/utils/ofetch';
-import { config } from '@/config';
-import { RESTGetAPIGuildResult, RESTGetAPIGuildChannelsResult, RESTGetAPIChannelResult, RESTGetAPIChannelMessagesQuery, RESTGetAPIChannelMessagesResult } from 'discord-api-types/rest/v10';
 
 export const baseUrl = 'https://discord.com';
 const apiUrl = `${baseUrl}/api/v10`;
@@ -48,3 +50,43 @@ export const getChannelMessages = (channelId, authorization, limit = 100) =>
         config.cache.routeExpire,
         false
     ) as Promise<RESTGetAPIChannelMessagesResult>;
+
+interface SearchGuildMessagesResult {
+    analytics_id: string;
+    doing_deep_historical_index: boolean;
+    total_results: number;
+    messages: APIMessage[][];
+}
+
+export const VALID_HAS_TYPES = new Set(['link', 'embed', 'poll', 'file', 'video', 'image', 'sound', 'sticker', 'snapshot'] as const);
+
+export type HasType = typeof VALID_HAS_TYPES extends Set<infer T> ? T : never;
+
+export interface SearchGuildMessagesParams {
+    content?: string;
+    author_id?: string;
+    mentions?: string;
+    has?: HasType[];
+    max_id?: string;
+    min_id?: string;
+    channel_id?: string;
+    pinned?: boolean;
+}
+
+export const searchGuildMessages = (guildId: string, authorization: string, params: SearchGuildMessagesParams) =>
+    cache.tryGet(
+        `discord:guilds:${guildId}:search:${JSON.stringify(params)}`,
+        () => {
+            const queryParams = {
+                ...params,
+                has: params.has?.length ? params.has : undefined,
+            };
+
+            return ofetch(`${apiUrl}/guilds/${guildId}/messages/search`, {
+                headers: { authorization },
+                query: queryParams,
+            });
+        },
+        config.cache.routeExpire,
+        false
+    ) as Promise<SearchGuildMessagesResult>;