rsshub 1.0.0-master.f6cb490 → 1.0.0-master.f6f0273

package/lib/routes/fangchan/list.ts

@@ -0,0 +1,224 @@
+import { type Data, type DataItem, type Route, 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';
+
+import { type CheerioAPI, type Cheerio, type Element, load } from 'cheerio';
+import { type Context } from 'hono';
+import path from 'node:path';
+
+const __dirname = getCurrentPath(import.meta.url);
+
+export const handler = async (ctx: Context): Promise<Data> => {
+    const { id = 'datalist' } = ctx.req.param();
+    const limit: number = Number.parseInt(ctx.req.query('limit') ?? '30', 10);
+
+    const baseUrl: string = 'http://www.fangchan.com';
+    const apiBaseUrl: string = 'http://news.fangchan.com';
+    const targetUrl: string = new URL(id.endsWith('/') ? id : `${id}/`, baseUrl).href;
+    const apiUrl: string = new URL(`api/${id.endsWith('/') ? id.replace(/\/$/, '') : id}.json`, apiBaseUrl).href;
+
+    const targetResponse = await ofetch(targetUrl);
+    const $: CheerioAPI = load(targetResponse);
+    const language = $('html').attr('lang') ?? 'zh-CN';
+
+    const response = await ofetch(apiUrl, {
+        query: {
+            pagesize: limit,
+            page: 1,
+        },
+    });
+
+    let items: DataItem[] = [];
+
+    items = response.data.slice(0, limit).map((item): DataItem => {
+        const title: string = item.title;
+        const description: string = art(path.join(__dirname, 'templates/description.art'), {
+            intro: item.zhaiyao,
+        });
+        const pubDate: number | string = item.createtime;
+        const linkUrl: string | undefined = item.url;
+        const categories: string[] = [...new Set([item.topcolumn, item.subcolumn, ...(item.keyword?.split(/,/) ?? [])].filter(Boolean))];
+        const image: string | undefined = item.pic;
+        const updated: number | string = item.createtime;
+
+        const processedItem: DataItem = {
+            title,
+            description,
+            pubDate: pubDate ? parseDate(pubDate, 'X') : undefined,
+            link: linkUrl,
+            id: categories,
+            content: {
+                html: description,
+                text: item.zhaiyao ?? description,
+            },
+            image,
+            banner: image,
+            updated: updated ? parseDate(updated, 'X') : 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 $$: CheerioAPI = load(detailResponse);
+
+                    const title: string = $$('div.summary-text h').text();
+                    const description: string = (item.description ?? '') + ($$('div.top-info').html() ?? '') + ($$('div.summary-text-p').html() ?? '');
+                    const pubDateStr: string | undefined = $$('span.news-date')
+                        .text()
+                        .match(/\d{4}-\d{2}-\d{2}\s\d{2}:\d{2}:\d{2}/)?.[1];
+                    const idEls: Element[] = $$('a.news-column, div.label span').toArray();
+                    const categories: string[] = [...new Set([...(item.id as string[]), ...idEls.map((el) => $$(el).text()).filter(Boolean)].filter(Boolean))];
+                    const authors: DataItem['author'] = $$('span.news-date')
+                        .text()
+                        ?.split(/\d{4}-\d{2}-\d{2}/)?.[0]
+                        ?.trim()
+                        ?.split(/\s/)
+                        ?.map((author) => ({
+                            name: author,
+                        }));
+                    const upDatedStr: string | undefined = pubDateStr;
+
+                    let processedItem: DataItem = {
+                        title,
+                        description,
+                        pubDate: pubDateStr ? timezone(parseDate(pubDateStr), +8) : item.pubDate,
+                        id: categories,
+                        author: authors,
+                        content: {
+                            html: description,
+                            text: description,
+                        },
+                        updated: upDatedStr ? timezone(parseDate(upDatedStr), +8) : item.updated,
+                        language,
+                    };
+
+                    const extraLinkEls: Element[] = $$('ul.xgxw-ul li a').toArray();
+                    const extraLinks = extraLinkEls
+                        .map((extraLinkEl) => {
+                            const $$extraLinkEl: Cheerio<Element> = $$(extraLinkEl);
+
+                            return {
+                                url: $$extraLinkEl.attr('href'),
+                                type: 'related',
+                                content_html: $$extraLinkEl.text(),
+                            };
+                        })
+                        .filter((_): _ is { url: string; type: string; content_html: string } => true);
+
+                    if (extraLinks) {
+                        processedItem = {
+                            ...processedItem,
+                            _extra: {
+                                links: extraLinks,
+                            },
+                        };
+                    }
+
+                    return {
+                        ...item,
+                        ...processedItem,
+                    };
+                });
+            })
+        )
+    ).filter((_): _ is DataItem => true);
+
+    const author: string = '中房网';
+
+    return {
+        title: `${author} - ${$('div.curmbs a').text()}`,
+        description: $('meta[name="description"]').attr('content'),
+        link: targetUrl,
+        item: items,
+        allowEmpty: true,
+        author,
+        language,
+    };
+};
+
+export const route: Route = {
+    path: '/list/:id?',
+    name: '列表',
+    url: 'www.fangchan.com',
+    maintainers: ['nczitzk'],
+    handler,
+    example: '/fangchan/list/datalist',
+    parameters: {
+        id: {
+            description: '分类，默认为 `datalist`，即数据研究，可在对应分类页 URL 中找到',
+            options: [
+                {
+                    label: '数据研究',
+                    value: 'datalist',
+                },
+                {
+                    label: '行业测评',
+                    value: 'industrylist',
+                },
+                {
+                    label: '政策法规',
+                    value: 'policylist',
+                },
+            ],
+        },
+    },
+    description: `:::tip
+若订阅 [列表](https://www.fangchan.com/)，网址为 \`https://www.fangchan.com/\`，请截取 \`https://www.fangchan.com/\` 到末尾 \`.html\` 的部分 \`datalist\` 作为 \`id\` 参数填入，此时目标路由为 [\`/fangchan/datalist\`](https://rsshub.app/fangchan/datalist)。
+:::
+
+| [数据研究](https://www.fangchan.com/datalist)         | [行业测评](https://www.fangchan.com/industrylist)             | [政策法规](https://www.fangchan.com/policylist)           |
+| ----------------------------------------------------- | ------------------------------------------------------------- | --------------------------------------------------------- |
+| [datalist](https://rsshub.app/fangchan/list/datalist) | [industrylist](https://rsshub.app/fangchan/list/industrylist) | [policylist](https://rsshub.app/fangchan/list/policylist) |
+`,
+    categories: ['new-media'],
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportRadar: true,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['www.fangchan.com/:id'],
+            target: (params) => {
+                const id: string = params.id;
+
+                return `/fangchan/list/${id ? `/${id}` : ''}`;
+            },
+        },
+        {
+            title: '数据研究',
+            source: ['www.fangchan.com/datalist'],
+            target: '/list/datalist',
+        },
+        {
+            title: '行业测评',
+            source: ['www.fangchan.com/industrylist'],
+            target: '/list/industrylist',
+        },
+        {
+            title: '政策法规',
+            source: ['www.fangchan.com/policylist'],
+            target: '/list/policylist',
+        },
+    ],
+    view: ViewType.Articles,
+};

package/lib/routes/fangchan/namespace.ts

@@ -0,0 +1,9 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: '中房网',
+    url: 'fangchan.com',
+    categories: ['new-media'],
+    description: '',
+    lang: 'zh-CN',
+};

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

@@ -0,0 +1,7 @@
+{{ if intro }}
+  <blockquote>{{ intro }}</blockquote>
+{{ /if }}
+
+{{ if description }}
+  {{@ description }}
+{{ /if }}

package/lib/routes/foreignaffairs/namespace.ts

@@ -0,0 +1,7 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: 'Foreign Affairs',
+    url: 'www.foreignaffairs.com',
+    lang: 'en',
+};

package/lib/routes/foreignaffairs/rss.ts

@@ -0,0 +1,55 @@
+import { Route } from '@/types';
+import cache from '@/utils/cache';
+import got from '@/utils/got';
+import parser from '@/utils/rss-parser';
+import { load } from 'cheerio';
+
+export const route: Route = {
+    path: '/rss',
+    categories: ['traditional-media'],
+    example: '/foreignaffairs/rss',
+    parameters: {},
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    name: 'RSS',
+    maintainers: ['dzx-dzx'],
+    handler,
+};
+
+async function handler() {
+    const link = 'https://www.foreignaffairs.com/rss.xml';
+
+    const feed = await parser.parseURL(link);
+
+    const items = await Promise.all(
+        feed.items.map((item) =>
+            cache.tryGet(item.link, async () => {
+                const response = await got({
+                    method: 'get',
+                    url: item.link,
+                });
+
+                const $ = load(response.data);
+
+                $('.paywall').remove();
+                $('.loading-indicator').remove();
+                item.description = $('.article-dropcap').html();
+                item.author = item.creator;
+
+                return item;
+            })
+        )
+    );
+
+    return {
+        title: 'Foreign Affairs - RSS',
+        link,
+        item: items,
+    };
+}

package/lib/routes/forklog/index.ts

@@ -0,0 +1,72 @@
+import { Route } from '@/types';
+import { parseDate } from '@/utils/parse-date';
+import got from '@/utils/got';
+import timezone from '@/utils/timezone';
+
+export const route: Route = {
+    path: '/news',
+    categories: ['finance'],
+    example: '/forklog/news',
+    radar: [
+        {
+            source: ['forklog.com/news'],
+            target: '/news',
+        },
+    ],
+    name: 'Новости',
+    maintainers: ['raven428'],
+    handler,
+    url: 'forklog.com/news',
+};
+
+async function handler() {
+    const response = await got('https://forklog.com/wp-content/themes/forklogv2/ajax/getPosts.php', {
+        method: 'POST',
+        headers: { 'x-requested-with': 'XMLHttpRequest' },
+        form: { action: 'getPostsByCategory', postperpage: '333' },
+    });
+    const items = JSON.parse(response.body).map((post) => {
+        const link = post.link;
+        const title = (post.title || post.text?.post_title)?.trim();
+        const description = post.text?.post_content.trim();
+        const author = post.author_name.trim();
+        let pubDate;
+        if (post.text?.post_date_gmt) {
+            pubDate = timezone(parseDate(post.text.post_date_gmt), +1);
+        } else if (post.text?.post_date) {
+            pubDate = timezone(parseDate(post.text.post_date), +4);
+        } else if (post.date) {
+            pubDate = timezone(parseDate(post.date, 'DD.MM.YYYY HH:mm'), +4);
+        }
+        const imageSrc = post.image || post.image_mobile;
+        const views = post.views;
+        return {
+            link,
+            title,
+            author,
+            pubDate,
+            description,
+            category: ['news', 'crypto', 'finance'],
+            ...(imageSrc
+                ? {
+                      media: {
+                          thumbnail: {
+                              url: imageSrc,
+                              width: 250,
+                              height: 250,
+                          },
+                      },
+                  }
+                : {}),
+            extra: {
+                views,
+            },
+        };
+    });
+    return {
+        title: 'Forklog – Новости',
+        link: 'https://forklog.com/news',
+        description: 'Последние новости из мира блокчейна и криптовалют',
+        item: items,
+    };
+}

package/lib/routes/forklog/namespace.ts

@@ -0,0 +1,7 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: 'Forklog',
+    url: 'forklog.com',
+    lang: 'ru',
+};

package/lib/routes/gcores/categories.ts

@@ -0,0 +1,129 @@
+import { type Data, type Route, ViewType } from '@/types';
+
+import { getCurrentPath } from '@/utils/helpers';
+import { type Context } from 'hono';
+
+import { baseUrl, processItems } from './util';
+
+export const __dirname = getCurrentPath(import.meta.url);
+
+let viewType: ViewType = ViewType.Articles;
+
+export const handler = async (ctx: Context): Promise<Data> => {
+    const { id, tab } = ctx.req.param();
+    const limit: number = Number.parseInt(ctx.req.query('limit') ?? '30', 10);
+
+    const targetUrl: string = new URL(`categories/${id}${tab ? `?tab=${tab}` : ''}`, baseUrl).href;
+    const apiUrl: string = new URL(`gapi/v1/categories/${id}/${tab ?? 'originals'}`, baseUrl).href;
+
+    const query = {
+        'page[limit]': limit,
+        sort: '-published-at',
+        include: 'category,user,media',
+        'filter[list-all]': 1,
+        'filter[is-news]': tab === 'news' ? 1 : 0,
+    };
+
+    if (tab === 'radios') {
+        viewType = ViewType.Audios;
+    } else if (tab === 'videos') {
+        viewType = ViewType.Videos;
+    }
+
+    return await processItems(limit, query, apiUrl, targetUrl);
+};
+
+export const route: Route = {
+    path: '/categories/:id/:tab?',
+    name: '分类',
+    url: 'www.gcores.com',
+    maintainers: ['MoguCloud', 'StevenRCE0', 'nczitzk'],
+    handler,
+    example: '/gcores/categories/1/articles',
+    parameters: {
+        id: {
+            description: '分类 ID，可在对应分类页 URL 中找到',
+        },
+        tab: {
+            description: '类型，默认为空，即全部，可在对应分类页 URL 中找到',
+            options: [
+                {
+                    label: '全部',
+                    value: '',
+                },
+                {
+                    label: '播客',
+                    value: 'radios',
+                },
+                {
+                    label: '文章',
+                    value: 'articles',
+                },
+                {
+                    label: '资讯',
+                    value: 'news',
+                },
+                {
+                    label: '视频',
+                    value: 'videos',
+                },
+            ],
+        },
+    },
+    description: `:::tip
+若订阅 [文章 - 文章](https://www.gcores.com/categories/1?tab=articles)，网址为 \`https://www.gcores.com/categories/1?tab=articles\`，请截取 \`https://www.gcores.com/categories/\` 到末尾的部分 \`1\` 作为 \`id\` 参数填入，截取 \`articles\` 作为 \`tab\` 参数填入，此时目标路由为 [\`/gcores/categories/1/articles\`](https://rsshub.app/gcores/categories/1/articles)。
+:::
+
+| 全部 | 播客   | 文章     | 资讯 | 视频   |
+| ---- | ------ | -------- | ---- | ------ |
+|      | radios | articles | news | videos |
+`,
+    categories: ['game'],
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportRadar: true,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['www.gcores.com/categories/:id'],
+            target: (params, url) => {
+                const urlObj: URL = new URL(url);
+                const id: string = params.id;
+                const tab: string | undefined = urlObj.searchParams.get('tab') ?? undefined;
+
+                return `/gcores/categories/${id}/${tab ? `/${tab}` : ''}`;
+            },
+        },
+        {
+            title: '全部',
+            source: ['www.gcores.com/categories/:id'],
+            target: '/gcores/categories/:id',
+        },
+        {
+            title: '播客',
+            source: ['www.gcores.com/categories/:id'],
+            target: '/categories/:id/radios',
+        },
+        {
+            title: '文章',
+            source: ['www.gcores.com/categories/:id'],
+            target: '/categories/:id/articles',
+        },
+        {
+            title: '资讯',
+            source: ['www.gcores.com/categories/:id'],
+            target: '/categories/:id/news',
+        },
+        {
+            title: '视频',
+            source: ['www.gcores.com/categories/:id'],
+            target: '/categories/:id/videos',
+        },
+    ],
+    view: viewType,
+};

package/lib/routes/gcores/collections.ts

@@ -0,0 +1,129 @@
+import { type Data, type Route, ViewType } from '@/types';
+
+import { getCurrentPath } from '@/utils/helpers';
+import { type Context } from 'hono';
+
+import { baseUrl, processItems } from './util';
+
+export const __dirname = getCurrentPath(import.meta.url);
+
+let viewType: ViewType = ViewType.Articles;
+
+export const handler = async (ctx: Context): Promise<Data> => {
+    const { id, tab } = ctx.req.param();
+    const limit: number = Number.parseInt(ctx.req.query('limit') ?? '30', 10);
+
+    const targetUrl: string = new URL(`collections/${id}${tab ? `?tab=${tab}` : ''}`, baseUrl).href;
+    const apiUrl: string = new URL(`gapi/v1/collections/${id}/${tab ?? 'originals'}`, baseUrl).href;
+
+    const query = {
+        'page[limit]': limit,
+        sort: '-published-at',
+        include: 'category,user,media',
+        'filter[list-all]': 1,
+        'filter[is-news]': tab === 'news' ? 1 : 0,
+    };
+
+    if (tab === 'radios') {
+        viewType = ViewType.Audios;
+    } else if (tab === 'videos') {
+        viewType = ViewType.Videos;
+    }
+
+    return await processItems(limit, query, apiUrl, targetUrl);
+};
+
+export const route: Route = {
+    path: '/collections/:id/:tab?',
+    name: '专题',
+    url: 'www.gcores.com',
+    maintainers: ['kudryavka1013', 'nczitzk'],
+    handler,
+    example: '/gcores/collections/64/articles',
+    parameters: {
+        id: {
+            description: '专题 ID，可在对应专题页 URL 中找到',
+        },
+        tab: {
+            description: '类型，默认为空，即全部，可在对应专题页 URL 中找到',
+            options: [
+                {
+                    label: '全部',
+                    value: '',
+                },
+                {
+                    label: '播客',
+                    value: 'radios',
+                },
+                {
+                    label: '文章',
+                    value: 'articles',
+                },
+                {
+                    label: '资讯',
+                    value: 'news',
+                },
+                {
+                    label: '视频',
+                    value: 'videos',
+                },
+            ],
+        },
+    },
+    description: `:::tip
+若订阅 [文章 - 文章](https://www.gcores.com/collections/64?tab=articles)，网址为 \`https://www.gcores.com/collections/64?tab=articles\`，请截取 \`https://www.gcores.com/collections/\` 到末尾的部分 \`64\` 作为 \`id\` 参数填入，截取 \`articles\` 作为 \`tab\` 参数填入，此时目标路由为 [\`/gcores/collections/64/articles\`](https://rsshub.app/gcores/collections/64/articles)。
+:::
+
+| 全部 | 播客   | 文章     | 资讯 | 视频   |
+| ---- | ------ | -------- | ---- | ------ |
+|      | radios | articles | news | videos |
+`,
+    categories: ['game'],
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportRadar: true,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['www.gcores.com/collections/:id'],
+            target: (params, url) => {
+                const urlObj: URL = new URL(url);
+                const id: string = params.id;
+                const tab: string | undefined = urlObj.searchParams.get('tab') ?? undefined;
+
+                return `/gcores/collections/${id}/${tab ? `/${tab}` : ''}`;
+            },
+        },
+        {
+            title: '全部',
+            source: ['www.gcores.com/collections/:id'],
+            target: '/collections/:id',
+        },
+        {
+            title: '播客',
+            source: ['www.gcores.com/collections/:id'],
+            target: '/collections/:id/radios',
+        },
+        {
+            title: '文章',
+            source: ['www.gcores.com/collections/:id'],
+            target: '/collections/:id/articles',
+        },
+        {
+            title: '资讯',
+            source: ['www.gcores.com/collections/:id'],
+            target: '/collections/:id/news',
+        },
+        {
+            title: '视频',
+            source: ['www.gcores.com/collections/:id'],
+            target: '/collections/:id/videos',
+        },
+    ],
+    view: viewType,
+};