rsshub 1.0.0-master.f71451d → 1.0.0-master.f72af1b

package/lib/routes/chikubi/search.ts

@@ -0,0 +1,39 @@
+import { Route, Data } from '@/types';
+import { getPosts } from './utils';
+import got from '@/utils/got';
+
+export const route: Route = {
+    path: '/search/:keyword',
+    categories: ['multimedia'],
+    example: '/chikubi/search/ギャップ',
+    parameters: { keyword: 'Keyword' },
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    name: 'Search',
+    maintainers: ['SnowAgar25'],
+    handler,
+};
+
+async function handler(ctx): Promise<Data> {
+    const { keyword } = ctx.req.param();
+    const baseUrl = 'https://chikubi.jp';
+    const searchUrl = `${baseUrl}/wp-json/wp/v2/search?search=${keyword}`;
+
+    const response = await got.get(searchUrl);
+    const searchResults = response.data;
+
+    const postIds = searchResults.map((item) => item.id.toString());
+    const items = await getPosts(postIds);
+
+    return {
+        title: `Search: ${keyword} - chikubi.jp`,
+        link: `${baseUrl}/search/${encodeURIComponent(keyword)}`,
+        item: items,
+    };
+}

package/lib/routes/chikubi/tag.ts

@@ -0,0 +1,41 @@
+import { Route, Data } from '@/types';
+import { getBySlug, getPostsBy } from './utils';
+
+export const route: Route = {
+    path: '/tag/:keyword',
+    categories: ['multimedia'],
+    example: '/chikubi/tag/ドリームチケット',
+    parameters: { keyword: 'Keyword' },
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    name: 'Tag',
+    maintainers: ['SnowAgar25'],
+    handler,
+    radar: [
+        {
+            title: 'Tag',
+            source: ['chikubi.jp/tag/:keyword'],
+            target: '/tag/:keyword',
+        },
+    ],
+};
+
+async function handler(ctx): Promise<Data> {
+    const baseUrl = 'https://chikubi.jp';
+    const { keyword } = ctx.req.param();
+    const { id, name } = await getBySlug('tag', keyword);
+
+    const items = await getPostsBy('tag', id);
+
+    return {
+        title: `Tag: ${name} - chikubi.jp`,
+        link: `${baseUrl}/category/${keyword}`,
+        item: items,
+    };
+}

package/lib/routes/chikubi/utils.ts

@@ -0,0 +1,135 @@
+import { DataItem } from '@/types';
+import cache from '@/utils/cache';
+import got from '@/utils/got';
+import { load } from 'cheerio';
+import { parseDate } from '@/utils/parse-date';
+
+const CONTENT_TYPES = {
+    doujin: {
+        title: '.doujin-title',
+        description: ['.doujin-detail', '.section', '.area-buy > a.btn'],
+    },
+    video: {
+        title: '.video-title',
+        description: ['.video-data', '.section', '.lp-samplearea a.btn'],
+    },
+    article: {
+        title: '.article_title',
+        description: ['.article_icatch', '.article_contents'],
+    },
+};
+
+function getContentType(link: string): keyof typeof CONTENT_TYPES {
+    const typePatterns = {
+        doujin: ['/cg/', '/comic/', '/voice/'],
+        video: ['/nipple-video/'],
+        article: ['/post-'],
+    };
+
+    for (const [type, patterns] of Object.entries(typePatterns)) {
+        if (patterns.some((pattern) => link.includes(pattern))) {
+            return type as keyof typeof CONTENT_TYPES;
+        }
+    }
+
+    throw new Error(`Unknown content type for link: ${link}`);
+}
+
+export async function processItems(list): Promise<DataItem[]> {
+    const items = await Promise.all(
+        list.map((item) =>
+            cache.tryGet(item.link, async () => {
+                const detailResponse = await got(item.link);
+                const $ = load(detailResponse.data);
+
+                const contentType = getContentType(item.link);
+                const selectors = CONTENT_TYPES[contentType];
+
+                const title = $(selectors.title).text().trim() || item.title;
+                const description = processDescription(selectors.description.map((selector) => $(selector).prop('outerHTML')).join(''));
+
+                const pubDateStr = $('meta[property="article:published_time"]').attr('content');
+                const pubDate = pubDateStr ? parseDate(pubDateStr) : undefined;
+
+                return {
+                    title,
+                    description,
+                    link: item.link,
+                    pubDate,
+                } as DataItem;
+            })
+        )
+    );
+
+    return items.filter((item): item is DataItem => item !== null);
+}
+
+function processDescription(description: string): string {
+    const $ = load(description);
+    return $('body')
+        .children()
+        .map((_, el) => $(el).clone().wrap('<div>').parent().html())
+        .toArray()
+        .join('');
+}
+
+const WP_REST_API_URL = 'https://chikubi.jp/wp-json/wp/v2';
+
+export async function getPosts(ids?: string[]): Promise<DataItem[]> {
+    const url = `${WP_REST_API_URL}/posts${ids?.length ? `?include=${ids.join(',')}` : ''}`;
+
+    const cachedData = await cache.tryGet(url, async () => {
+        const response = await got(url);
+        const data = JSON.parse(response.body);
+
+        if (!Array.isArray(data)) {
+            throw new TypeError('No posts found for the given IDs');
+        }
+
+        return data.map(({ title, link, date, content }) => ({
+            title: title.rendered,
+            link,
+            pubDate: parseDate(date),
+            description: processDescription(content.rendered),
+        }));
+    });
+
+    return (Array.isArray(cachedData) ? cachedData : []).filter((item): item is DataItem => item !== null);
+}
+
+const API_TYPES = {
+    tag: 'tags',
+    category: 'categories',
+};
+
+export async function getBySlug<T extends keyof typeof API_TYPES>(type: T, slug: string): Promise<{ id: number; name: string }> {
+    const url = `${WP_REST_API_URL}/${API_TYPES[type]}?slug=${encodeURIComponent(slug)}`;
+    const { body } = await got(url);
+    const data = JSON.parse(body);
+
+    if (data?.[0]) {
+        const { id, name } = data[0];
+        return { id, name };
+    }
+    throw new Error(`No ${type} found for slug: ${slug}`);
+}
+
+export async function getPostsBy<T extends keyof typeof API_TYPES>(type: T, id: number): Promise<DataItem[]> {
+    const url = `${WP_REST_API_URL}/posts?${API_TYPES[type]}=${id}`;
+    const cachedData = await cache.tryGet(url, async () => {
+        const { body } = await got(url);
+        const data = JSON.parse(body);
+
+        if (Array.isArray(data) && data.length > 0) {
+            return data.map(({ title, link, date, content }) => ({
+                title: title.rendered,
+                link,
+                pubDate: parseDate(date),
+                description: processDescription(content.rendered),
+            }));
+        }
+        return [];
+    });
+
+    return (Array.isArray(cachedData) ? cachedData : []).filter((item): item is DataItem => item !== null);
+}

package/lib/routes/chinaisa/index.ts

@@ -1,6 +1,6 @@
 import { Route } from '@/types';
 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';
 
@@ -170,10 +170,15 @@ async function handler(ctx) {
     const apiArticleUrl = new URL('gxportal/xfpt/portal/viewArticleById', rootUrl).href;
     const currentUrl = new URL(`gxportal/xfgl/portal/list.html?columnId=${id}`, rootUrl).href;
 
-    const { data: response } = await got.post(apiUrl, {
-        form: {
-            params: encodeURI(`{"columnId":"${id}"}`),
+    const response = await ofetch(apiUrl, {
+        method: 'POST',
+        headers: {
+            'Content-Type': 'application/x-www-form-urlencoded',
         },
+        body: new URLSearchParams({
+            params: encodeURI(`{"columnId":"${id}"}`),
+        }),
+        parseResponse: JSON.parse,
     });
 
     let $ = load(response.articleListHtml);
@@ -195,10 +200,15 @@ async function handler(ctx) {
     items = await Promise.all(
         items.map((item) =>
             cache.tryGet(item.link, async () => {
-                const { data: detailResponse } = await got.post(apiArticleUrl, {
-                    form: {
-                        params: encodeURI(`{"articleId":"${item.guid}","columnId":"${id}"}`),
+                const detailResponse = await ofetch(apiArticleUrl, {
+                    method: 'POST',
+                    headers: {
+                        'Content-Type': 'application/x-www-form-urlencoded',
                     },
+                    body: new URLSearchParams({
+                        params: encodeURI(`{"articleId":"${item.guid}","columnId":"${id}"}`),
+                    }),
+                    parseResponse: JSON.parse,
                 });
 
                 const articleContent = detailResponse.article_content;
@@ -220,7 +230,7 @@ async function handler(ctx) {
 
     const subtitle = $('div.head-tit').text();
 
-    const { data: currentResponse } = await got(currentUrl);
+    const currentResponse = await ofetch(currentUrl);
 
     $ = load(currentResponse);
 

package/lib/routes/chlinlearn/daily-blog.ts

@@ -0,0 +1,55 @@
+import { Route } from '@/types';
+import ofetch from '@/utils/ofetch'; // 统一使用的请求库
+import { parseDate } from '@/utils/parse-date'; // 解析日期的工具函数
+import timezone from '@/utils/timezone';
+import CryptoJS from 'crypto-js';
+
+export const route: Route = {
+    path: '/daily-blog',
+    name: '值得一读技术博客',
+    maintainers: ['huyyi'],
+    categories: ['programming'],
+    example: '/chlinlearn/daily-blog',
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['daily-blog.chlinlearn.top/blogs/*'],
+            target: '/chlinlearn/daily-blog',
+        },
+    ],
+    handler: async () => {
+        const r = CryptoJS.lib.WordArray.random(8).toString(CryptoJS.enc.Hex);
+        const n = Date.now();
+        const o = CryptoJS.SHA256('pHVp671B0tLkW40KCwyPrb6W1GEMEGyT' + r + n).toString(CryptoJS.enc.Hex);
+        const data = await ofetch('https://daily-blog.chlinlearn.top/api/daily-blog/getBlogs/new?type=new&pageNum=1&pageSize=20', {
+            headers: {
+                Referer: 'https://daily-blog.chlinlearn.top/blogs/1',
+                'x-req-nonce': r,
+                'x-req-timestamp': n,
+                'x-req-key': o,
+            },
+        });
+        const items = data.rows.map((item) => ({
+            title: item.title,
+            link: item.url,
+            author: item.author,
+            img: item.icon,
+            pubDate: timezone(parseDate(item.publishTime), +8),
+        }));
+        return {
+            // 源标题
+            title: '值得一读技术博客',
+            // 源链接
+            link: 'https://daily-blog.chlinlearn.top/blogs/1',
+            // 源文章
+            item: items,
+        };
+    },
+};

package/lib/routes/chlinlearn/namespcae.ts

@@ -0,0 +1,6 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: 'chlinlearn的技术博客',
+    url: 'daily-blog.chlinlearn.top',
+};

package/lib/routes/chub/characters.ts

@@ -0,0 +1,64 @@
+import { Route } from '@/types';
+import ofetch from '@/utils/ofetch';
+import { parseDate } from '@/utils/parse-date';
+
+export const route: Route = {
+    path: '/characters',
+    categories: ['new-media'],
+    example: '/chub/characters',
+    name: 'Characters',
+    maintainers: ['flameleaf'],
+    handler,
+};
+
+async function handler() {
+    const hostURL = 'https://www.chub.ai/characters';
+    const apiURL = 'https://api.chub.ai/api/characters/search';
+    const data = await ofetch(apiURL, {
+        headers: { Accept: 'application/json' },
+        query: {
+            query: '',
+            first: 200,
+            page: 1,
+            sort: 'last_activity_at',
+            asc: 'false',
+            include_forks: 'false',
+            nsfw: 'true',
+            nsfl: 'true',
+            nsfw_only: 'false',
+            require_images: 'false',
+            require_example_dialogues: 'false',
+            require_alternate_greetings: 'false',
+            require_custom_prompt: 'false',
+            exclude_mine: 'false',
+            venus: 'true',
+            chub: 'true',
+            min_tokens: 50,
+            require_expressions: 'false',
+            require_lore: 'false',
+            mine_first: 'false',
+            require_lore_embedded: 'false',
+            require_lore_linked: 'false',
+            inclusive_or: 'false',
+            recommended_verified: 'false',
+        },
+    });
+    const nodes = data.nodes;
+
+    return {
+        allowEmpty: true,
+        title: 'Chub',
+        link: hostURL,
+        item: nodes.map((item) => ({
+            title: item.name,
+            description: `${item.tagline}<br><br>${item.description}`,
+            pubDate: parseDate(item.createdAt),
+            updated: parseDate(item.lastActivityAt),
+            link: `${hostURL}/${item.fullPath}`,
+            author: String(item.fullPath.split('/', 1)),
+            enclosure_url: item.avatar_url,
+            enclosure_type: `image/webp`,
+            category: item.topics,
+        })),
+    };
+}

package/lib/routes/chub/namespace.ts

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

package/lib/routes/cls/subject.ts

@@ -0,0 +1,153 @@
+import { Route } from '@/types';
+import { getCurrentPath } from '@/utils/helpers';
+const __dirname = getCurrentPath(import.meta.url);
+
+import cache from '@/utils/cache';
+import got from '@/utils/got';
+import { load } from 'cheerio';
+import { parseDate } from '@/utils/parse-date';
+import { art } from '@/utils/render';
+import path from 'node:path';
+
+import { rootUrl, getSearchParams } from './utils';
+
+export const handler = async (ctx) => {
+    const { id = '1103' } = ctx.req.param();
+    const limit = ctx.req.query('limit') ? Number.parseInt(ctx.req.query('limit'), 10) : 20;
+
+    const currentUrl = new URL(`subject/${id}`, rootUrl).href;
+    const apiUrl = new URL(`api/subject/${id}/article`, rootUrl).href;
+
+    const { data: response } = await got(apiUrl, {
+        searchParams: getSearchParams({
+            Subject_Id: id,
+        }),
+    });
+
+    let items = response.data.slice(0, limit).map((item) => {
+        const title = item.article_title;
+        const description = art(path.join(__dirname, 'templates/description.art'), {
+            intro: item.article_brief,
+        });
+        const guid = `cls-${item.article_id}`;
+        const image = item.article_img;
+
+        return {
+            title,
+            description,
+            pubDate: parseDate(item.article_time, 'X'),
+            link: new URL(`detail/${item.article_id}`, rootUrl).href,
+            category: item.subjects.map((s) => s.subject_name),
+            author: item.article_author,
+            guid,
+            id: guid,
+            content: {
+                html: description,
+                text: item.article_brief,
+            },
+            image,
+            banner: image,
+        };
+    });
+
+    items = await Promise.all(
+        items.map((item) =>
+            cache.tryGet(item.link, async () => {
+                const { data: detailResponse } = await got(item.link);
+
+                const $$ = load(detailResponse);
+
+                const data = JSON.parse($$('script#__NEXT_DATA__').text())?.props?.initialState?.detail?.articleDetail ?? undefined;
+
+                if (!data) {
+                    return item;
+                }
+
+                const title = data.title;
+                const description = art(path.join(__dirname, 'templates/description.art'), {
+                    images: data.images.map((i) => ({
+                        src: i,
+                        alt: title,
+                    })),
+                    intro: data.brief,
+                    description: data.content,
+                });
+                const guid = `cls-${data.id}`;
+                const image = data.images?.[0] ?? undefined;
+
+                item.title = title;
+                item.description = description;
+                item.pubDate = parseDate(data.ctime, 'X');
+                item.category = [...new Set(data.subject?.flatMap((s) => [s.name, ...(s.subjectCategory?.flatMap((c) => [c.columnName || [], c.name || []]) ?? [])]) ?? [])].filter(Boolean);
+                item.author = data.author?.name ?? item.author;
+                item.guid = guid;
+                item.id = guid;
+                item.content = {
+                    html: description,
+                    text: data.content,
+                };
+                item.image = image;
+                item.banner = image;
+                item.enclosure_url = data.audioUrl;
+                item.enclosure_type = item.enclosure_url ? `audio/${item.enclosure_url.split(/\./).pop()}` : undefined;
+                item.enclosure_title = title;
+
+                return item;
+            })
+        )
+    );
+
+    const { data: currentResponse } = await got(currentUrl);
+
+    const $ = load(currentResponse);
+
+    const data = JSON.parse($('script#__NEXT_DATA__').text())?.props?.initialProps?.pageProps?.subjectDetail ?? undefined;
+
+    const author = '财联社';
+    const image = data?.img ?? undefined;
+
+    return {
+        title: `${author} - ${data?.name ?? $('title').text()}`,
+        description: data?.description ?? undefined,
+        link: currentUrl,
+        item: items,
+        allowEmpty: true,
+        image,
+        author,
+    };
+};
+
+export const route: Route = {
+    path: '/subject/:id?',
+    name: '话题',
+    url: 'www.cls.cn',
+    maintainers: ['nczitzk'],
+    handler,
+    example: '/cls/subject/1103',
+    parameters: { category: '分类，默认为 1103，即A股盘面直播，可在对应话题页 URL 中找到' },
+    description: `:::tip
+  若订阅 [有声早报](https://www.cls.cn/subject/1151)，网址为 \`https://www.cls.cn/subject/1151\`。截取 \`https://www.cls.cn/subject/\` 到末尾的部分 \`1151\` 作为参数填入，此时路由为 [\`/cls/subject/1151\`](https://rsshub.app/cls/subject/1151)。
+  :::
+    `,
+    categories: ['finance'],
+
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportRadar: true,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['www.cls.cn/subject/:id'],
+            target: (params) => {
+                const id = params.id;
+
+                return `/subject${id ? `/${id}` : ''}`;
+            },
+        },
+    ],
+};

package/lib/routes/cls/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/cnbc/rss.ts

@@ -65,7 +65,7 @@ async function handler(ctx) {
                     }
 
                     const meta = JSON.parse($('[type=application/ld+json]').last().text());
-                    item.author = meta.author ? meta.author.name ?? meta.author.map((a) => a.name).join(', ') : null;
+                    item.author = meta.author ? (meta.author.name ?? meta.author.map((a) => a.name).join(', ')) : null;
                     item.category = meta.keywords;
 
                     return item;

package/lib/routes/cnbeta/category.ts

@@ -0,0 +1,23 @@
+import { Route } from '@/types';
+import { handler } from './common';
+
+export const route: Route = {
+    name: '分类',
+    path: ['/category/:id'],
+    example: '/cnbeta/category/movie',
+    maintainers: ['nczitzk'],
+    parameters: {
+        id: '分类 id，可在对应分类页的 URL 中找到',
+    },
+    radar: [
+        {
+            source: ['cnbeta.com.tw/category/:id'],
+            target: (params) => `/cnbeta/category/${params.id.replace('.htm', '')}`,
+        },
+    ],
+    handler,
+    url: 'cnbeta.com.tw',
+    description: `| 影视  | 音乐  | 游戏 | 动漫  | 趣闻  | 科学    | 软件 |
+  | ----- | ----- | ---- | ----- | ----- | ------- | ---- |
+  | movie | music | game | comic | funny | science | soft |`,
+};

package/lib/routes/cnbeta/{type.ts → common.ts}

@@ -1,4 +1,3 @@
-import { Route } from '@/types';
 import cache from '@/utils/cache';
 import got from '@/utils/got';
 import { load } from 'cheerio';
@@ -7,22 +6,7 @@ import { parseDate } from '@/utils/parse-date';
 
 import { rootUrl, ProcessItems } from './utils';
 
-export const route: Route = {
-    path: ['/:type/:id', '/'],
-    radar: [
-        {
-            source: ['cnbeta.com.tw/'],
-            target: '',
-        },
-    ],
-    name: 'Unknown',
-    maintainers: [],
-    handler,
-    url: 'cnbeta.com.tw/',
-    url: 'cnbeta.com.tw/',
-};
-
-async function handler(ctx) {
+export async function handler(ctx) {
     const { type, id } = ctx.req.param();
 
     const currentUrl = type ? `${rootUrl}/${type}/${id}.htm` : rootUrl;

package/lib/routes/cnbeta/index.ts

@@ -0,0 +1,16 @@
+import { Route } from '@/types';
+import { handler } from './common';
+
+export const route: Route = {
+    name: '头条资讯',
+    path: ['/'],
+    example: '/cnbeta',
+    radar: [
+        {
+            source: ['cnbeta.com.tw/'],
+        },
+    ],
+    maintainers: ['kt286', 'HaitianLiu', 'nczitzk'],
+    handler,
+    url: 'cnbeta.com.tw',
+};

package/lib/routes/cnbeta/namespace.ts

@@ -3,4 +3,5 @@ import type { Namespace } from '@/types';
 export const namespace: Namespace = {
     name: 'cnBeta.COM',
     url: 'cnbeta.com.tw',
+    categories: ['new-media'],
 };