rsshub 1.0.0-master.f6c2ebb → 1.0.0-master.f70afef

package/lib/routes/ajcass/shxyj.ts

@@ -0,0 +1,73 @@
+import { Route } from '@/types';
+import got from '@/utils/got';
+import { load } from 'cheerio';
+import { parseDate } from '@/utils/parse-date';
+
+export const route: Route = {
+    path: '/shxyj/:year?/:issue?',
+    categories: ['journal'],
+    example: '/ajcass/shxyj/2024/1',
+    parameters: { year: 'Year of the issue, `null` for the lastest', issue: 'Issue number, `null` for the lastest' },
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    name: '社会学研究',
+    maintainers: ['CNYoki'],
+    handler,
+};
+
+async function handler(ctx) {
+    let { year, issue } = ctx.req.param();
+
+    if (!year) {
+        const response = await got('https://shxyj.ajcass.com/');
+        const $ = load(response.body);
+        const latestIssueText = $('p.hod.pop').first().text();
+
+        const match = latestIssueText.match(/(\d{4}) Vol\.(\d+):/);
+        if (match) {
+            year = match[1];
+            issue = match[2];
+        } else {
+            throw new Error('无法获取最新的 year 和 issue');
+        }
+    }
+
+    const url = `https://shxyj.ajcass.com/Magazine/?Year=${year}&Issue=${issue}`;
+    const response = await got(url);
+    const $ = load(response.body);
+
+    const items = $('#tab tr')
+        .toArray()
+        .map((item) => {
+            const $item = $(item);
+            const articleTitle = $item.find('a').first().text().trim();
+            const articleLink = $item.find('a').first().attr('href');
+            const summary = $item.find('li').eq(1).text().replace('[摘要]', '').trim();
+            const authors = $item.find('li').eq(2).text().replace('作者：', '').trim();
+            const pubDate = parseDate(`${year}-${Number.parseInt(issue) * 2}`);
+
+            if (articleTitle && articleLink) {
+                return {
+                    title: articleTitle,
+                    link: `https://shxyj.ajcass.com${articleLink}`,
+                    description: summary,
+                    author: authors,
+                    pubDate,
+                };
+            }
+            return null;
+        })
+        .filter((item) => item !== null);
+
+    return {
+        title: `社会学研究 ${year}年第${issue}期`,
+        link: url,
+        item: items,
+    };
+}

package/lib/routes/ali213/namespace.ts

@@ -0,0 +1,9 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: '游侠网',
+    url: 'ali213.net',
+    categories: ['game'],
+    description: '',
+    lang: 'zh-CN',
+};

package/lib/routes/ali213/news.ts

@@ -0,0 +1,269 @@
+import path from 'node:path';
+
+import { type CheerioAPI, type Cheerio, type Element, load } from 'cheerio';
+import { type Context } from 'hono';
+
+import { type DataItem, type Route, type Data, ViewType } from '@/types';
+
+import { art } from '@/utils/render';
+import cache from '@/utils/cache';
+import { getCurrentPath } from '@/utils/helpers';
+import ofetch from '@/utils/ofetch';
+import { parseDate } from '@/utils/parse-date';
+import timezone from '@/utils/timezone';
+
+const __dirname = getCurrentPath(import.meta.url);
+
+export const handler = async (ctx: Context): Promise<Data> => {
+    const { category = 'new' } = ctx.req.param();
+    const limit: number = Number.parseInt(ctx.req.query('limit') ?? '30', 10);
+
+    const rootUrl: string = 'https://www.ali213.net';
+    const targetUrl: string = new URL(`news/${category.endsWith('/') ? category : `${category}/`}`, rootUrl).href;
+
+    const response = await ofetch(targetUrl);
+    const $: CheerioAPI = load(response);
+    const language: string = $('html').prop('lang') ?? 'zh-CN';
+
+    let items: DataItem[] = $('div.n_lone')
+        .slice(0, limit)
+        .toArray()
+        .map((item): DataItem => {
+            const $item: Cheerio<Element> = $(item);
+
+            const aEl: Cheerio<Element> = $item.find('h2.lone_t a');
+
+            const title: string = aEl.prop('title') || aEl.text();
+            const link: string | undefined = aEl.prop('href');
+
+            const imageEl: Cheerio<Element> = $item.find('img');
+            const imageSrc: string | undefined = imageEl?.prop('src');
+            const imageAlt: string | undefined = imageEl?.prop('alt');
+
+            const intro: string = $item.find('div.lone_f_r_t').text();
+
+            const description: string = art(path.join(__dirname, 'templates/description.art'), {
+                images: imageEl
+                    ? [
+                          {
+                              src: imageSrc,
+                              alt: imageAlt,
+                          },
+                      ]
+                    : undefined,
+                intro,
+            });
+
+            const author: DataItem['author'] = $item.find('div.lone_f_r_f span').last().text().split(/：/).pop();
+
+            return {
+                title,
+                description,
+                pubDate: parseDate($item.find('div.lone_f_r_f span').first().text()),
+                link,
+                author,
+                content: {
+                    html: description,
+                    text: $item.find('div.lone_f_r_t').text(),
+                },
+                image: imageSrc,
+                banner: imageSrc,
+                language,
+            };
+        });
+
+    items = (
+        await Promise.all(
+            items.map((item) => {
+                if (!item.link && typeof item.link !== 'string') {
+                    return item;
+                }
+
+                return cache.tryGet(item.link, async (): Promise<DataItem> => {
+                    try {
+                        const detailResponse = await ofetch(item.link);
+                        const $$: CheerioAPI = load(detailResponse);
+
+                        const title: string = $$('h1.newstit').text();
+                        const image: string | undefined = $$('div#Content img').first().prop('src');
+
+                        const mediaContent: Cheerio<Element> = $$('div#Content p span img');
+                        const media: Record<string, Record<string, string>> = {};
+
+                        if (mediaContent.length) {
+                            mediaContent.each((_, el) => {
+                                const $$el: Cheerio<Element> = $$(el);
+
+                                const pEl: Cheerio<Element> = $$el.closest('p');
+
+                                const mediaUrl: string | undefined = $$el.prop('src');
+                                const mediaType: string | undefined = mediaUrl?.split(/\./).pop();
+
+                                if (mediaType && mediaUrl) {
+                                    media[mediaType] = { url: mediaUrl };
+
+                                    pEl.replaceWith(
+                                        art(path.join(__dirname, 'templates/description.art'), {
+                                            images: [
+                                                {
+                                                    src: mediaUrl,
+                                                },
+                                            ],
+                                        })
+                                    );
+                                }
+                            });
+                        }
+
+                        const description: string = art(path.join(__dirname, 'templates/description.art'), {
+                            description: $$('div#Content').html() ?? '',
+                        });
+
+                        const extraLinks = $$('div.extend_read ul li a')
+                            .toArray()
+                            .map((el) => {
+                                const $$el: Cheerio<Element> = $$(el);
+
+                                return {
+                                    url: $$el.prop('href'),
+                                    type: 'related',
+                                    content_html: $$el.prop('title') || $$el.text(),
+                                };
+                            })
+                            .filter((_): _ is { url: string; type: string; content_html: string } => true);
+
+                        return {
+                            ...item,
+                            title,
+                            description,
+                            pubDate: timezone(parseDate($$('div.newstag_l').text().split(/\s/)[0]), +8),
+                            content: {
+                                html: description,
+                                text: $$('div#Content').html() ?? '',
+                            },
+                            image,
+                            banner: image,
+                            language,
+                            media: Object.keys(media).length > 0 ? media : undefined,
+                            _extra: {
+                                links: extraLinks.length > 0 ? extraLinks : undefined,
+                            },
+                        };
+                    } catch {
+                        return item;
+                    }
+                });
+            })
+        )
+    ).filter((_): _ is DataItem => true);
+
+    const author = '游侠网';
+    const title = $('div.news-list-title').text();
+    const feedImage = new URL('news/images/ali213_app_big.png', rootUrl).href;
+
+    return {
+        title: `${author} - ${title}`,
+        description: title,
+        link: targetUrl,
+        item: items,
+        allowEmpty: true,
+        image: feedImage,
+        author,
+        language,
+        id: targetUrl,
+    };
+};
+
+export const route: Route = {
+    path: '/news/:category?',
+    name: '资讯',
+    url: 'www.ali213.net',
+    maintainers: ['nczitzk'],
+    handler,
+    example: '/ali213/news/new',
+    parameters: {
+        category: '分类，默认为 `new`，即最新资讯，可在对应分类页 URL 中找到',
+    },
+    description: `::: tip
+若订阅 [游戏资讯](https://www.ali213.net/news/game/)，网址为 \`https://www.ali213.net/news/game/\`，请截取 \`https://www.ali213.net/news/\` 到末尾 \`/\` 的部分 \`game\` 作为 \`category\` 参数填入，此时目标路由为 [\`/ali213/news/game\`](https://rsshub.app/ali213/news/game)。
+:::
+
+| 分类名称 | 分类 ID |
+| -------- | ------- |
+| 最新资讯 | new     |
+| 评测     | pingce  |
+| 游戏     | game    |
+| 动漫     | comic   |
+| 影视     | movie   |
+| 科技     | tech    |
+| 电竞     | esports |
+| 娱乐     | amuse   |
+| 手游     | mobile  |
+`,
+    categories: ['game'],
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportRadar: true,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['www.ali213.net/news/:category'],
+            target: (params) => {
+                const category = params.category;
+
+                return `/news/${category ? `/${category}` : ''}`;
+            },
+        },
+        {
+            title: '最新资讯',
+            source: ['www.ali213.net/news/new'],
+            target: '/news/new',
+        },
+        {
+            title: '评测',
+            source: ['www.ali213.net/news/pingce'],
+            target: '/news/pingce',
+        },
+        {
+            title: '游戏',
+            source: ['www.ali213.net/news/game'],
+            target: '/news/game',
+        },
+        {
+            title: '动漫',
+            source: ['www.ali213.net/news/comic'],
+            target: '/news/comic',
+        },
+        {
+            title: '影视',
+            source: ['www.ali213.net/news/movie'],
+            target: '/news/movie',
+        },
+        {
+            title: '科技',
+            source: ['www.ali213.net/news/tech'],
+            target: '/news/tech',
+        },
+        {
+            title: '电竞',
+            source: ['www.ali213.net/news/esports'],
+            target: '/news/esports',
+        },
+        {
+            title: '娱乐',
+            source: ['www.ali213.net/news/amuse'],
+            target: '/news/amuse',
+        },
+        {
+            title: '手游',
+            source: ['www.ali213.net/news/mobile'],
+            target: '/news/mobile',
+        },
+    ],
+    view: ViewType.Articles,
+};

package/lib/routes/ali213/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/ali213/zl.ts

@@ -0,0 +1,226 @@
+import path from 'node:path';
+
+import { type CheerioAPI, type Cheerio, type Element, load } from 'cheerio';
+import { type Context } from 'hono';
+
+import { type DataItem, type Route, type Data, ViewType } from '@/types';
+
+import { art } from '@/utils/render';
+import cache from '@/utils/cache';
+import { getCurrentPath } from '@/utils/helpers';
+import ofetch from '@/utils/ofetch';
+import { parseDate } from '@/utils/parse-date';
+
+const __dirname = getCurrentPath(import.meta.url);
+
+export const handler = async (ctx: Context): Promise<Data> => {
+    const { category } = ctx.req.param();
+    const limit: number = Number.parseInt(ctx.req.query('limit') ?? '1', 10);
+
+    const rootUrl: string = 'https://www.ali213.net';
+    const apiRootUrl: string = 'https://mp.ali213.net';
+    const targetUrl: string = new URL(`/news/zl/${category ? (category.endsWith('/') ? category : `${category}/`) : ''}`, rootUrl).href;
+    const apiUrl: string = new URL('ajax/newslist', apiRootUrl).href;
+
+    const response = await ofetch(apiUrl, {
+        query: {
+            type: 'new',
+        },
+    });
+
+    const targetResponse = await ofetch(targetUrl);
+    const $: CheerioAPI = load(targetResponse);
+    const language: string = $('html').prop('lang') ?? 'zh';
+
+    let items: DataItem[] = JSON.parse(response.replace(/^\((.*)\)$/, '$1'))
+        .data.slice(0, limit)
+        .map((item): DataItem => {
+            const title: string = item.Title;
+            const description: string = art(path.join(__dirname, 'templates/description.art'), {
+                intro: item.GuideRead ?? '',
+            });
+            const guid: string = `ali213-zl-${item.ID}`;
+            const image: string | undefined = item.PicPath ? `https:${item.PicPath}` : undefined;
+
+            const author: DataItem['author'] = item.xiaobian;
+
+            return {
+                title,
+                description,
+                pubDate: parseDate(item.addtime * 1000),
+                link: item.url ? `https:${item.url}` : undefined,
+                author,
+                guid,
+                id: guid,
+                content: {
+                    html: description,
+                    text: item.GuideRead ?? '',
+                },
+                image,
+                banner: image,
+                language,
+            };
+        });
+
+    items = (
+        await Promise.all(
+            items.map((item) => {
+                if (!item.link && typeof item.link !== 'string') {
+                    return item;
+                }
+
+                return cache.tryGet(item.link, async (): Promise<DataItem> => {
+                    const detailResponse = await ofetch(item.link);
+                    const $$: CheerioAPI = load(detailResponse);
+
+                    const title: string = $$('h1.newstit').text();
+
+                    let description: string = $$('div#Content').html() ?? '';
+
+                    const pageLinks: string[] = [];
+                    $$('a.currpage')
+                        .parent()
+                        .find('a:not(.currpage)')
+                        .each((_, el) => {
+                            const href = $$(el).attr('href');
+                            if (href) {
+                                pageLinks.push(href);
+                            }
+                        });
+
+                    const pageContents = await Promise.all(
+                        pageLinks.map(async (link) => {
+                            const response = await ofetch(new URL(link, item.link).href);
+                            const $$$: CheerioAPI = load(response);
+
+                            return $$$('div#Content').html() ?? '';
+                        })
+                    );
+
+                    description += pageContents.join('');
+
+                    description = art(path.join(__dirname, 'templates/description.art'), {
+                        description,
+                    });
+
+                    const extraLinks = $$('div.extend_read a')
+                        .toArray()
+                        .map((el) => {
+                            const $$el: Cheerio<Element> = $$(el);
+
+                            return {
+                                url: $$el.prop('href'),
+                                type: 'related',
+                                content_html: $$el.text(),
+                            };
+                        })
+                        .filter((_): _ is { url: string; type: string; content_html: string } => true);
+
+                    return {
+                        title,
+                        description,
+                        pubDate: item.pubDate,
+                        category: $$('.category')
+                            .toArray()
+                            .map((c) => $$(c).text()),
+                        author: item.author,
+                        doi: $$('meta[name="citation_doi"]').prop('content') || undefined,
+                        guid: item.guid,
+                        id: item.guid,
+                        content: {
+                            html: description,
+                            text: description,
+                        },
+                        image: item.image,
+                        banner: item.image,
+                        language,
+                        _extra: {
+                            links: extraLinks.length > 0 ? extraLinks : undefined,
+                        },
+                    };
+                });
+            })
+        )
+    ).filter((_): _ is DataItem => true);
+
+    const title: string = $('title').text();
+    const feedImage: string = new URL('news/images/dxhlogo.png', rootUrl).href;
+
+    return {
+        title,
+        description: $('meta[name="description"]').prop('content'),
+        link: targetUrl,
+        item: items,
+        allowEmpty: true,
+        image: feedImage,
+        author: title.split(/_/).pop(),
+        language,
+        id: targetUrl,
+    };
+};
+
+export const route: Route = {
+    path: '/zl/:category?',
+    name: '大侠号',
+    url: 'www.ali213.net',
+    maintainers: ['nczitzk'],
+    handler,
+    example: '/ali213/zl',
+    parameters: {
+        category: '分类，默认为首页，可在对应分类页 URL 中找到',
+    },
+    description: `::: tip
+若订阅 [游戏](https://www.ali213.net/news/zl/game/)，网址为 \`https://www.ali213.net/news/zl/game/\`，请截取 \`https://www.ali213.net/news/zl/\` 到末尾 \`/\` 的部分 \`game\` 作为 \`category\` 参数填入，此时目标路由为 [\`/ali213/zl/game\`](https://rsshub.app/ali213/zl/game)。
+:::
+
+| 首页                                     | 游戏                                         | 动漫                                           | 影视                                           | 娱乐                                           |
+| ---------------------------------------- | -------------------------------------------- | ---------------------------------------------- | ---------------------------------------------- | ---------------------------------------------- |
+| [index](https://www.ali213.net/news/zl/) | [game](https://www.ali213.net/news/zl/game/) | [comic](https://www.ali213.net/news/zl/comic/) | [movie](https://www.ali213.net/news/zl/movie/) | [amuse](https://www.ali213.net/news/zl/amuse/) |
+`,
+    categories: ['game'],
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportRadar: true,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['www.ali213.net/news/zl/:category'],
+            target: (params) => {
+                const category = params.category;
+
+                return `/ali213/zl${category ? `/${category}` : ''}`;
+            },
+        },
+        {
+            title: '首页',
+            source: ['www.ali213.net/news/zl/'],
+            target: '/zl',
+        },
+        {
+            title: '游戏',
+            source: ['www.ali213.net/news/zl/game/'],
+            target: '/zl/game',
+        },
+        {
+            title: '动漫',
+            source: ['www.ali213.net/news/zl/comic/'],
+            target: '/zl/comic',
+        },
+        {
+            title: '影视',
+            source: ['www.ali213.net/news/zl/movie/'],
+            target: '/zl/movie',
+        },
+        {
+            title: '娱乐',
+            source: ['www.ali213.net/news/zl/amuse/'],
+            target: '/zl/amuse',
+        },
+    ],
+    view: ViewType.Articles,
+};

package/lib/routes/aliresearch/information.ts

@@ -6,7 +6,7 @@ import { parseDate } from '@/utils/parse-date';
 
 export const route: Route = {
     path: '/information/:type?',
-    categories: ['new-media'],
+    categories: ['new-media', 'popular'],
     example: '/aliresearch/information',
     parameters: { type: '类型，见下表，默认为新闻' },
     features: {

package/lib/routes/alistapart/index.ts

@@ -3,16 +3,18 @@ import { getData, getList } from './utils';
 
 export const route: Route = {
     path: '/',
+    categories: ['programming'],
     radar: [
         {
             source: ['alistapart.com/articles/'],
-            target: '',
+            target: '/',
         },
     ],
-    name: 'Unknown',
+    name: 'Home Feed',
     maintainers: ['Rjnishant530'],
     handler,
     url: 'alistapart.com/articles/',
+    example: '/alistapart',
 };
 
 async function handler() {

package/lib/routes/alistapart/topic.ts

@@ -17,6 +17,7 @@ export const route: Route = {
     radar: [
         {
             source: ['alistapart.com/blog/topic/:topic'],
+            target: '/:topic',
         },
     ],
     name: 'Topics',

package/lib/routes/ally/rail.ts

@@ -27,9 +27,9 @@ export const route: Route = {
     maintainers: ['Rongronggg9'],
     handler,
     url: 'rail.ally.net.cn/',
-    description: `:::tip
+    description: `::: tip
   默认抓取前 20 条，可通过 \`?limit=\` 改变。
-  :::`,
+:::`,
 };
 
 async function handler(ctx) {