rsshub 1.0.0-master.fb6d4f3 → 1.0.0-master.fb7e42c

package/lib/routes/bilibili/weekly-recommend.ts

@@ -1,6 +1,9 @@
 import { Route } from '@/types';
 import got from '@/utils/got';
-import utils from './utils';
+import utils, { getVideoUrl } from './utils';
+import { parseDuration } from '@/utils/helpers';
+import { config } from '@/config';
+import cache from './cache';
 
 export const route: Route = {
     path: '/weekly/:embed?',
@@ -46,10 +49,23 @@ async function handler(ctx) {
         title: 'B站每周必看',
         link: 'https://www.bilibili.com/h5/weekly-recommend',
         description: 'B站每周必看',
-        item: data.map((item) => ({
-            title: item.title,
-            description: utils.renderUGCDescription(embed, item.cover, `${weekly_name} ${item.title} - ${item.rcmd_reason}`, item.param, undefined, item.bvid),
-            link: weekly_number > 60 && item.bvid ? `https://www.bilibili.com/video/${item.bvid}` : `https://www.bilibili.com/video/av${item.param}`,
-        })),
+        item: data.map(async (item) => {
+            const subtitles = !config.bilibili.excludeSubtitles && item.bvid ? await cache.getVideoSubtitleAttachment(item.bvid) : [];
+            return {
+                title: item.title,
+                description: utils.renderUGCDescription(embed, item.cover, `${weekly_name} ${item.title} - ${item.rcmd_reason}`, item.param, undefined, item.bvid),
+                link: weekly_number > 60 && item.bvid ? `https://www.bilibili.com/video/${item.bvid}` : `https://www.bilibili.com/video/av${item.param}`,
+                attachments: item.bvid
+                    ? [
+                          {
+                              url: getVideoUrl(item.bvid),
+                              mime_type: 'text/html',
+                              duration_in_seconds: parseDuration(item.cover_right_text_1),
+                          },
+                          ...subtitles,
+                      ]
+                    : undefined,
+            };
+        }),
     };
 }

package/lib/routes/bjp/apod.ts

@@ -48,7 +48,7 @@ async function handler(ctx) {
                 pubDate: timezone(parseDate(e.find('span').text().replace('：', ''), 'YYYY-MM-DD'), 8),
             };
         })
-        .sort((a, b) => b.pubDate - a.pubDate)
+        .toSorted((a, b) => b.pubDate - a.pubDate)
         .slice(0, ctx.req.query('limit') ? Number.parseInt(ctx.req.query('limit'), 10) : 10);
 
     const items = await Promise.all(

package/lib/routes/bnext/index.ts

@@ -0,0 +1,58 @@
+import { Route } from '@/types';
+import parser from '@/utils/rss-parser';
+import type { Item } from 'rss-parser';
+
+const FEED_URL = 'https://rss.bnextmedia.com.tw/feed/bnext';
+
+export const route: Route = {
+    path: '/',
+    categories: ['traditional-media'],
+    example: '/bnext',
+    parameters: {},
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['www.bnext.com.tw'],
+            target: '/bnext',
+        },
+    ],
+    name: '最新文章',
+    maintainers: ['johan456789'],
+    handler,
+    url: 'www.bnext.com.tw',
+};
+
+async function handler() {
+    const feed = await parser.parseURL(FEED_URL);
+    const items = (feed.items as Item[]).map((item) => {
+        const enclosure = item.enclosure;
+        const enclosure_url = enclosure?.url;
+        const enclosure_type = enclosure?.type;
+        const enclosure_length = enclosure?.length ? Number(enclosure.length) : undefined;
+
+        return {
+            title: item.title ?? item.link ?? 'Untitled',
+            link: item.link,
+            description: item.content ?? item.summary ?? item.contentSnippet,
+            pubDate: item.isoDate ?? item.pubDate,
+            enclosure_url,
+            enclosure_type,
+            enclosure_length,
+        };
+    });
+
+    return {
+        title: feed.title ?? '數位時代 BusinessNext',
+        link: feed.link ?? 'https://www.bnext.com.tw',
+        description: feed.description ?? '',
+        item: items,
+        allowEmpty: true, // the official feed clears all items every day at 00:00 UTC+8
+    };
+}

package/lib/routes/bnext/namespace.ts

@@ -0,0 +1,7 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: '數位時代 BusinessNext',
+    url: 'bnext.com.tw',
+    lang: 'zh-TW',
+};

package/lib/routes/bookwalker/namespace.ts

@@ -0,0 +1,9 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: 'BOOKWALKER電子書',
+    url: 'bookwalker.com.tw',
+    categories: ['shopping'],
+    description: '',
+    lang: 'zh-TW',
+};

package/lib/routes/bookwalker/search.ts

@@ -0,0 +1,114 @@
+import { type Data, type DataItem, type Route, ViewType } from '@/types';
+
+import { art } from '@/utils/render';
+import ofetch from '@/utils/ofetch';
+
+import { type CheerioAPI, type Cheerio, load } from 'cheerio';
+import type { Element } from 'domhandler';
+import { type Context } from 'hono';
+import path from 'node:path';
+
+export const handler = async (ctx: Context): Promise<Data> => {
+    const { filter = 'order=sell_desc' } = ctx.req.param();
+    const limit: number = Number.parseInt(ctx.req.query('limit') ?? '24', 10);
+
+    const baseUrl: string = 'https://www.bookwalker.com.tw';
+    const targetUrl: string = new URL(`search?${filter}`, baseUrl).href;
+
+    const response = await ofetch(targetUrl);
+    const $: CheerioAPI = load(response);
+    const language = $('html').attr('lang') ?? 'zh-TW';
+
+    const items: DataItem[] = $('div.bwbook_package')
+        .slice(0, limit)
+        .toArray()
+        .map((el): Element => {
+            const $el: Cheerio<Element> = $(el);
+
+            const name: string = $el.find('h4.bookname').text();
+            const price: string = $el.find('h5.bprice').text();
+            const authorStr: string = $el.find('h5.booknamesub').text().trim();
+
+            const title: string = `${name} - ${authorStr} ${price}`;
+            const image: string | undefined = $el
+                .find('img')
+                .attr('data-src')
+                ?.replace(/_\d+(\.\w+)$/, '$1');
+            const description: string | undefined = art(path.join(__dirname, 'templates/description.art'), {
+                images: image
+                    ? [
+                          {
+                              src: image,
+                              alt: name,
+                          },
+                      ]
+                    : undefined,
+            });
+            const linkUrl: string | undefined = $el.find('div.bwbookitem a').attr('href');
+            const authors: DataItem['author'] = authorStr.split(/,/).map((a) => ({
+                name: a,
+            }));
+
+            const processedItem: DataItem = {
+                title,
+                description,
+                link: linkUrl ? new URL(linkUrl, baseUrl).href : undefined,
+                author: authors,
+                content: {
+                    html: description,
+                    text: description,
+                },
+                image,
+                banner: image,
+                language,
+            };
+
+            return processedItem;
+        });
+
+    return {
+        title: $('title').text(),
+        description: $('meta[property="og:description"]').attr('content'),
+        link: targetUrl,
+        item: items,
+        allowEmpty: true,
+        image: $('meta[property="og:image"]').attr('content'),
+        author: $('meta[property="og:site_name"]').attr('content'),
+        language,
+        id: $('meta[property="og:url"]').attr('content'),
+    };
+};
+
+export const route: Route = {
+    path: '/search/:filter?',
+    name: '搜尋',
+    url: 'www.bookwalker.com.tw',
+    maintainers: ['nczitzk'],
+    handler,
+    example: '/bookwalker/search/order=sell_desc&s=34',
+    parameters: {
+        filter: {
+            description: '过滤器，默认为 `order=sell_desc`，即依發售日新至舊排序',
+        },
+    },
+    description: `::: tip
+订阅 [依發售日新至舊排序的文學小說](https://www.bookwalker.com.tw/search?order=sell_desc&s=34)，其源网址为 \`https://www.bookwalker.com.tw/search?order=sell_desc&s=34\`，请参考该 URL 指定部分构成参数，此时路由为 [\`/bookwalker/search/order=sell_desc&s=34\`](https://rsshub.app/bookwalker/search/order=sell_desc&s=34)。
+:::`,
+    categories: ['shopping'],
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportRadar: true,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['www.bookwalker.com.tw/search'],
+            target: '/bookwalker/search',
+        },
+    ],
+    view: ViewType.Articles,
+};

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

@@ -0,0 +1,13 @@
+{{ if images }}
+  {{ each images image }}
+    {{ if image?.src }}
+      <figure>
+        <img
+          {{ if image.alt }}
+            alt="{{ image.alt }}"
+          {{ /if }}
+        src="{{ image.src }}">
+      </figure>
+    {{ /if }}
+  {{ /each }}
+{{ /if }}

package/lib/routes/booru/mmda.ts

@@ -21,6 +21,7 @@ export const route: Route = {
         supportBT: false,
         supportPodcast: false,
         supportScihub: false,
+        nsfw: true,
     },
     radar: [
         {

package/lib/routes/buaa/jiaowu.ts

@@ -115,7 +115,7 @@ function getItems(list) {
                 const { data: descrptionResponse } = await got(item.link);
                 const $descrption = load(descrptionResponse);
                 const desc = $descrption('#main > div.content > div.search_height > div.search_con:has(p)').html();
-                item.description = desc?.replace(/(\r|\n)+/g, '<br />');
+                item.description = desc?.replaceAll(/(\r|\n)+/g, '<br />');
                 item.author = $descrption('#main > div.content > div.search_height > span.search_con').text().split('发布者:').at(-1) || '教务部';
                 return item;
             })

package/lib/routes/bullionvault/gold-news.ts

@@ -21,7 +21,7 @@ export const handler = async (ctx: Context): Promise<Data> => {
 
     let items: DataItem[] = [];
 
-    items = $('section#block-views-latest-articles-block div.media, section#block-system-main table.views-table tr')
+    items = $('section#block-bootstrap-views-block-latest-articles-block div.media, div.gold-news-content table tr')
         .slice(0, limit)
         .toArray()
         .map((el): Element => {
@@ -66,8 +66,8 @@ export const handler = async (ctx: Context): Promise<Data> => {
                     const detailResponse = await ofetch(item.link);
                     const $$: CheerioAPI = load(detailResponse);
 
-                    const title: string = $$('header h1').text();
-                    const description: string | undefined = $$('div[property="content:encoded"]').html() ?? '';
+                    const title: string = $$('article.article h1').text();
+                    const description: string | undefined = $$('div.content').html() ?? '';
                     const pubDateStr: string | undefined = $$('div.submitted').text().split(/,/).pop();
                     const categories: string[] = $$('meta[name="news_keywords"]').attr('content')?.split(/,/) ?? [];
                     const authorEls: Element[] = $$('div.view-author-bio').toArray();
@@ -160,7 +160,7 @@ export const route: Route = {
             ],
         },
     },
-    description: `:::tip
+    description: `::: tip
 If you subscribe to [Gold Price News](https://www.bullionvault.com/gold-news/gold-price-news)，where the URL is \`https://www.bullionvault.com/gold-news/gold-price-news\`, extract the part \`https://www.bullionvault.com/gold-news/\` to the end, and use it as the parameter to fill in. Therefore, the route will be [\`/bullionvault/gold-news/gold-price-news\`](https://rsshub.app/bullionvault/gold-news/gold-price-news).
 :::
 

package/lib/routes/cast/index.ts

@@ -94,7 +94,7 @@ async function handler(ctx) {
     } else {
         const buildUnitScript = $('script[parseType="bulidstatic"]');
         const queryUrl = `${baseUrl}${buildUnitScript.attr('url')}`;
-        const queryData = JSON.parse(buildUnitScript.attr('querydata')?.replace(/'/g, '"') ?? '{}');
+        const queryData = JSON.parse(buildUnitScript.attr('querydata')?.replaceAll("'", '"') ?? '{}');
         queryData.paramJson = `{"pageNo":1,"pageSize":${limit}}`;
 
         const { data } = await got.get<{ data: { html: string } }>(queryUrl, {

package/lib/routes/cbndata/information.ts

@@ -0,0 +1,250 @@
+import { type Data, type DataItem, type Route, ViewType } from '@/types';
+
+import { art } from '@/utils/render';
+import cache from '@/utils/cache';
+import ofetch from '@/utils/ofetch';
+import { parseDate } from '@/utils/parse-date';
+
+import { type CheerioAPI, load } from 'cheerio';
+import { type Context } from 'hono';
+import path from 'node:path';
+
+export const handler = async (ctx: Context): Promise<Data> => {
+    const { id = 'all' } = ctx.req.param();
+    const limit: number = Number.parseInt(ctx.req.query('limit') ?? '50', 10);
+
+    const baseUrl: string = 'https://www.cbndata.com';
+    const targetUrl: string = new URL(`information?tag_id=${id}`, baseUrl).href;
+    const apiUrl: string = new URL('api/v3/informations', baseUrl).href;
+
+    const targetResponse = await ofetch(targetUrl);
+    const $: CheerioAPI = load(targetResponse);
+    const language = $('html').attr('lang') ?? 'zh';
+
+    const response = await ofetch(apiUrl, {
+        query: {
+            page: 1,
+            per_page: limit,
+        },
+    });
+
+    let items: DataItem[] = [];
+
+    items = response.data.slice(0, limit).map((item): DataItem => {
+        const title: string = item.title;
+        const image: string | undefined = item.image;
+        const description: string | undefined = art(path.join(__dirname, 'templates/description.art'), {
+            images: image
+                ? [
+                      {
+                          src: image,
+                          alt: title,
+                      },
+                  ]
+                : undefined,
+        });
+        const pubDate: number | string = item.date;
+        const linkUrl: string | undefined = item.id ? `information/${item.id}` : undefined;
+        const categories: string[] = item.tags;
+        const guid: string = `cbndata-information-${item.id}`;
+        const updated: number | string = pubDate;
+
+        const processedItem: DataItem = {
+            title,
+            description,
+            pubDate: pubDate ? parseDate(pubDate) : undefined,
+            link: linkUrl ? new URL(linkUrl, baseUrl).href : undefined,
+            category: categories,
+            guid,
+            id: guid,
+            content: {
+                html: description,
+                text: description,
+            },
+            image,
+            banner: image,
+            updated: updated ? parseDate(updated) : undefined,
+            language,
+        };
+
+        return processedItem;
+    });
+
+    items = await Promise.all(
+        items.map((item) => {
+            if (!item.link) {
+                return item;
+            }
+
+            return cache.tryGet(item.link, async (): Promise<DataItem> => {
+                const detailResponse = await ofetch(item.link);
+
+                const dataStr: string | undefined = detailResponse.match(/<script>window\.__INITIAL_STATE__=(.*?);<\/script>/)?.[1];
+
+                if (!dataStr) {
+                    return item;
+                }
+
+                const data = JSON.parse(dataStr)?.data;
+
+                if (!data) {
+                    return item;
+                }
+
+                const title: string = data.title;
+                const description: string | undefined =
+                    item.description +
+                    art(path.join(__dirname, 'templates/description.art'), {
+                        description: data.content,
+                    });
+                const pubDate: number | string = data.date;
+                const linkUrl: string | undefined = data.id ? `information/${data.id}` : undefined;
+                const categories: string[] = [...new Set(((data.tags?.map((c) => c.name) ?? []) as string[]).filter(Boolean))];
+                const authors: DataItem['author'] = [
+                    {
+                        name: data.author,
+                        url: undefined,
+                        avatar: undefined,
+                    },
+                ];
+                const guid: string = `cbndata-information-${data.id}`;
+                const image: string | undefined = data.thumbnail_url;
+                const updated: number | string = pubDate;
+
+                const processedItem: DataItem = {
+                    title,
+                    description,
+                    pubDate: pubDate ? parseDate(pubDate) : undefined,
+                    link: linkUrl ? new URL(linkUrl, baseUrl).href : undefined,
+                    category: categories,
+                    author: authors,
+                    guid,
+                    id: guid,
+                    content: {
+                        html: description,
+                        text: description,
+                    },
+                    image,
+                    banner: image,
+                    updated: updated ? parseDate(updated) : undefined,
+                    language,
+                };
+
+                return {
+                    ...item,
+                    ...processedItem,
+                };
+            });
+        })
+    );
+
+    const tag: string = response.home_tags.find((t: { id: number; name: string }) => String(t.id) === id)?.name ?? '';
+    const title: string = `${tag ? `${tag}-` : ''}${$('title').text().trim()}`;
+
+    return {
+        title,
+        description: $('meta[name="description"]').attr('content'),
+        link: targetUrl,
+        item: items,
+        allowEmpty: true,
+        image: $('img.logo-logoImage').attr('src'),
+        author: title.split(/\|/).pop(),
+        language,
+        id: targetUrl,
+    };
+};
+
+export const route: Route = {
+    path: '/information/:id?',
+    name: '看点',
+    url: 'www.cbndata.com',
+    maintainers: ['nczitzk'],
+    handler,
+    example: '/cbndata/information/all',
+    parameters: {
+        id: {
+            description: '分类，默认为 `all`，即全部，可在对应分类页 URL 中找到',
+            options: [
+                {
+                    label: '全部',
+                    value: 'all',
+                },
+                {
+                    label: '美妆个护',
+                    value: '1',
+                },
+                {
+                    label: '服饰鞋包',
+                    value: '2559',
+                },
+                {
+                    label: '宠物',
+                    value: '2419',
+                },
+                {
+                    label: '营销',
+                    value: '2484',
+                },
+            ],
+        },
+    },
+    description: `::: tip
+订阅 [美妆个护](https://www.cbndata.com/information?tag_id=1)，其源网址为 \`https://www.cbndata.com/information?tag_id=1\`，请参考该 URL 指定部分构成参数，此时路由为 [\`/cbndata/information/1\`](https://rsshub.app/cbndata/information/1)。
+:::
+
+| 分类                                                        | ID                                                  |
+| ----------------------------------------------------------- | --------------------------------------------------- |
+| [全部](https://www.cbndata.com/information?tag_id=all)      | [all](https://rsshub.app/cbndata/information/all)   |
+| [美妆个护](https://www.cbndata.com/information?tag_id=1)    | [1](https://rsshub.app/cbndata/information/1)       |
+| [服饰鞋包](https://www.cbndata.com/information?tag_id=2559) | [2559](https://rsshub.app/cbndata/information/2559) |
+| [宠物](https://www.cbndata.com/information?tag_id=2419)     | [2419](https://rsshub.app/cbndata/information/2419) |
+| [营销](https://www.cbndata.com/information?tag_id=2484)     | [2484](https://rsshub.app/cbndata/information/2484) |
+`,
+    categories: ['new-media'],
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportRadar: true,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['www.cbndata.com/information'],
+            target: (params, url) => {
+                const urlObj: URL = new URL(url);
+                const id: string | undefined = urlObj.searchParams.get('tag_id') ?? undefined;
+
+                return `/information${id ? `/${id}` : ''}`;
+            },
+        },
+        {
+            title: '全部',
+            source: ['www.cbndata.com/information'],
+            target: '/information/all',
+        },
+        {
+            title: '美妆个护',
+            source: ['www.cbndata.com/information'],
+            target: '/information/1',
+        },
+        {
+            title: '服饰鞋包',
+            source: ['www.cbndata.com/information'],
+            target: '/information/2559',
+        },
+        {
+            title: '宠物',
+            source: ['www.cbndata.com/information'],
+            target: '/information/2419',
+        },
+        {
+            title: '营销',
+            source: ['www.cbndata.com/information'],
+            target: '/information/2484',
+        },
+    ],
+    view: ViewType.Articles,
+};

package/lib/routes/cbndata/namespace.ts

@@ -0,0 +1,9 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: 'CBNData',
+    url: 'cbndata.com',
+    categories: ['new-media'],
+    description: '第一财经商业数据中心（CBNData）',
+    lang: 'zh-CN',
+};

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

@@ -0,0 +1,17 @@
+{{ 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 description }}
+  {{@ description }}
+{{ /if }}

package/lib/routes/cccmc/index.ts

@@ -117,7 +117,7 @@ export const route: Route = {
     parameters: {
         category: '分类，默认为 `ywgg/tzgg`，即通知公告，可在对应分类页 URL 中找到, Category, `ywgg/tzgg`，即通知公告  by default',
     },
-    description: `:::tip
+    description: `::: tip
 若订阅 [综合政策](https://www.cccmc.org.cn/zcfg/zhzc/)，网址为 \`https://www.cccmc.org.cn/zcfg/zhzc/\`，请截取 \`https://www.cccmc.org.cn/\` 到末尾的部分 \`zcfg/zhzc\` 作为 \`category\` 参数填入，此时目标路由为 [\`/cccmc/zcfg/zhzc\`](https://rsshub.app/cccmc/zcfg/zhzc)。
 :::