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

package/lib/routes/imhcg/blog.ts

@@ -0,0 +1,47 @@
+import { Route, ViewType } from '@/types';
+import ofetch from '@/utils/ofetch';
+import { load } from 'cheerio';
+
+export const route: Route = {
+    path: '/',
+    categories: ['blog'],
+    view: ViewType.Notifications,
+    example: '/imhcg',
+    parameters: {},
+    radar: [
+        {
+            source: ['infos.imhcg.cn'],
+        },
+    ],
+    name: 'Engineering blogs',
+    maintainers: ['ZiHao256'],
+    handler,
+    url: 'infos.imhcg.cn',
+};
+
+async function handler() {
+    const response = await ofetch('https://infos.imhcg.cn/');
+    const $ = load(response);
+    const items = $('li')
+        .toArray()
+        .map((item) => {
+            const title = $(item).find('a.title').text();
+            const link = $(item).find('a.title').attr('href');
+            const author = $(item).find('p.author').text();
+            const time = $(item).find('p.time').text();
+            const description = $(item).find('p.text').text();
+            return {
+                title,
+                link,
+                author,
+                time,
+                description,
+            };
+        });
+
+    return {
+        title: `Engineering Blogs`,
+        link: 'https://infos.imhcg.cn/',
+        item: items,
+    };
+}

package/lib/routes/imhcg/namespace.ts

@@ -0,0 +1,7 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: 'imhcg的信息站',
+    url: 'infos.imhcg.cn',
+    description: '包含多种技术和新闻信息的网站',
+};

package/lib/routes/imop/namespace.ts

@@ -0,0 +1,10 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: 'imop',
+    url: 'imop.com',
+
+    zh: {
+        name: '千橡游戏',
+    },
+};

package/lib/routes/imop/tianshu.ts

@@ -0,0 +1,53 @@
+import { Route } from '@/types';
+import { load } from 'cheerio';
+import got from '@/utils/got';
+import iconv from 'iconv-lite';
+import cache from '@/utils/cache';
+
+const baseUrl = 'http://t.imop.com';
+
+export const route: Route = {
+    path: '/tianshu',
+    categories: ['game'],
+    example: '/imop/tianshu',
+    radar: [
+        {
+            source: ['t.imop.com'],
+            target: '/tianshu',
+        },
+    ],
+    name: '全部消息',
+    maintainers: ['zhkgo'],
+    handler,
+};
+
+async function handler() {
+    const { data: response } = await got(`${baseUrl}/list/0-1.htm`, { responseType: 'buffer' });
+    const $ = load(iconv.decode(response, 'gbk'));
+    const list = $('.right .right_top .right_bot .list2 .ul1 ul')
+        .toArray()
+        .map((item) => {
+            item = $(item);
+            const href: string = item.find('a').attr('href');
+            return {
+                title: item.find('a').text(),
+                link: href.startsWith('http') ? href : `${baseUrl}${href}`,
+            };
+        });
+    const items = await Promise.all(
+        list.map((item) =>
+            cache.tryGet(item.link, async () => {
+                const { data: response } = await got(item.link, { responseType: 'buffer' });
+                const $ = load(iconv.decode(response, 'gbk'));
+                item.description = $('.right .right_top .right_bot .articlebox').html();
+                return item;
+            })
+        )
+    );
+
+    return {
+        title: '天书最新消息',
+        link: `${baseUrl}/list/0-1.htm`,
+        item: items,
+    };
+}

package/lib/routes/informedainews/docs.ts

@@ -0,0 +1,78 @@
+import { Route } from '@/types';
+import ofetch from '@/utils/ofetch'; // 统一使用的请求库
+import { load } from 'cheerio'; // 类似 jQuery 的 API HTML 解析器
+import { parseDate } from '@/utils/parse-date';
+import cache from '@/utils/cache';
+
+export const route: Route = {
+    path: '/zh-Hans/docs/:type',
+    categories: ['new-media'],
+    example: '/informedainews/zh-Hans/docs/world-news-daily',
+    parameters: { type: 'world-news-daily|tech-enthusiast-weekly|ai-enthusiast-daily' },
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['informedainews.com', 'informedainews.com/zh-Hans/docs/:type', 'informedainews.com/docs/:type'],
+            target: '/zh-Hans/docs/:type',
+        },
+    ],
+    name: '知闻AI',
+    maintainers: ['guicaiyue'],
+    handler,
+};
+
+async function handler(ctx) {
+    const { type } = ctx.req.param();
+    const response = await ofetch(`https://informedainews.com/zh-Hans/docs/${type}`);
+    const $ = load(response);
+    const list = $('li.theme-doc-sidebar-item-category ul li')
+        .toArray()
+        .map((item) => {
+            item = $(item);
+            const a = item.find('a').first();
+            const text = a.text();
+            // 找到第一个'('字符的位置
+            const start = text.indexOf('(');
+            // 找到第一个')'字符的位置
+            const end = text.indexOf(')');
+            // 从第一个'('到第一个')'之间的子字符串就是日期
+            const date = text.substring(start + 1, end);
+            return {
+                title: text,
+                link: `https://informedainews.com${a.attr('href')}`,
+                pubDate: parseDate(date),
+                author: 'AI',
+            };
+        });
+
+    const items = await Promise.all(
+        list.map((item) =>
+            cache.tryGet(item.link, async () => {
+                const response = await ofetch(item.link);
+                const $ = load(response);
+
+                // 选择类名为“comment-body”的第一个元素
+                item.description = $('.theme-doc-markdown.markdown').first().html();
+
+                // 上面每个列表项的每个属性都在此重用，
+                // 并增加了一个新属性“description”
+                return item;
+            })
+        )
+    );
+    return {
+        // 源标题
+        title: `${type} docs`,
+        // 源链接
+        link: `https://informedainews.com/zh-Hans/docs/${type}`,
+        // 源文章
+        item: items,
+    };
+}

package/lib/routes/informedainews/namespace.ts

@@ -0,0 +1,18 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: 'Informed AI News',
+    url: 'informedainews.com',
+    description: `
+:::tip
+informed AI RSS feeds:
+
+-   World News Daily: 'https://rsshub.app/informedainews/zh-Hans/docs/world-news-daily'
+-   Tech Enthusiast Weekly: 'https://rsshub.app/informedainews/zh-Hans/docs/tech-enthusiast-weekly'
+-   AI Enthusiast Weekly: 'https://rsshub.app/informedainews/zh-Hans/docs/ai-enthusiast-daily'
+:::`,
+
+    zh: {
+        name: '知闻AI',
+    },
+};

package/lib/routes/infzm/hot.ts

@@ -0,0 +1,39 @@
+import type { Data, DataItem, Route } from '@/types';
+import type { ContentsResponse } from './types';
+import got from '@/utils/got';
+import { fetchArticles } from './utils';
+
+export const route: Route = {
+    path: '/hot',
+    parameters: {},
+    categories: ['traditional-media'],
+    example: '/infzm/hot',
+    radar: [
+        {
+            source: ['infzm.com/'],
+        },
+    ],
+    name: '热门文章',
+    maintainers: ['KarasuShin', 'ranpox', 'xyqfer'],
+    handler,
+};
+
+async function handler(): Promise<Data> {
+    const link = 'https://www.infzm.com/';
+    const { data } = await got<ContentsResponse>({
+        method: 'get',
+        url: `https://www.infzm.com/hot_contents`,
+        headers: {
+            Referer: link,
+        },
+    });
+
+    const resultItem = await fetchArticles(data.data.hot_contents);
+
+    return {
+        title: `南方周末-热门文章`,
+        link,
+        image: 'https://www.infzm.com/favicon.ico',
+        item: resultItem as DataItem[],
+    };
+}

package/lib/routes/infzm/index.ts

@@ -1,10 +1,7 @@
 import type { Data, DataItem, Route } from '@/types';
 import type { ContentsResponse } from './types';
-import { config } from '@/config';
 import got from '@/utils/got';
-import { load } from 'cheerio';
-import timezone from '@/utils/timezone';
-import cache from '@/utils/cache';
+import { fetchArticles } from './utils';
 
 export const route: Route = {
     path: '/:id',
@@ -27,7 +24,7 @@ export const route: Route = {
     | 1    | 2    | 3    | 4    | 7    | 8    | 6    | 5    | 131  |`,
 };
 
-const baseUrl = 'https://www.infzm.com/contents';
+export const baseUrl = 'https://www.infzm.com/contents';
 
 async function handler(ctx): Promise<Data> {
     const id = ctx.req.param('id');
@@ -40,31 +37,7 @@ async function handler(ctx): Promise<Data> {
         },
     });
 
-    const resultItem = await Promise.all(
-        data.data.contents.map(({ id, subject, author, publish_time }) => {
-            const link = `${baseUrl}/${id}`;
-
-            return cache.tryGet(link, async () => {
-                const cookie = config.infzm.cookie;
-                const response = await got.get<string>({
-                    method: 'get',
-                    url: link,
-                    headers: {
-                        Referer: link,
-                        Cookie: cookie || `passport_session=${Math.floor(Math.random() * 100)};`,
-                    },
-                });
-                const $ = load(response.data);
-                return {
-                    title: subject,
-                    description: $('div.nfzm-content__content').html() ?? '',
-                    pubDate: timezone(publish_time, +8).toUTCString(),
-                    link,
-                    author,
-                };
-            });
-        })
-    );
+    const resultItem = await fetchArticles(data.data.contents);
 
     return {
         title: `南方周末-${data.data.current_term.title}`,

package/lib/routes/infzm/utils.ts

@@ -0,0 +1,34 @@
+import { config } from '@/config';
+import cache from '@/utils/cache';
+import got from '@/utils/got';
+import timezone from '@/utils/timezone';
+import { load } from 'cheerio';
+import { baseUrl } from '.';
+
+export async function fetchArticles(data) {
+    return await Promise.all(
+        data.map(({ id, subject, author, publish_time }) => {
+            const link = `${baseUrl}/${id}`;
+
+            return cache.tryGet(link, async () => {
+                const cookie = config.infzm.cookie;
+                const response = await got.get<string>({
+                    method: 'get',
+                    url: link,
+                    headers: {
+                        Referer: link,
+                        Cookie: cookie || `passport_session=${Math.floor(Math.random() * 100)};`,
+                    },
+                });
+                const $ = load(response.data);
+                return {
+                    title: subject,
+                    description: $('div.nfzm-content__content').html() ?? '',
+                    pubDate: timezone(publish_time, +8).toUTCString(),
+                    link,
+                    author,
+                };
+            });
+        })
+    );
+}

package/lib/routes/inspirehep/author.ts

@@ -0,0 +1,46 @@
+import { Route } from '@/types';
+import ofetch from '@/utils/ofetch';
+import { AuthorResponse, LiteratureResponse } from './types';
+import cache from '@/utils/cache';
+
+import { baseUrl, parseLiterature } from './utils';
+
+export const route: Route = {
+    path: '/authors/:id',
+    example: '/inspirehep/authors/1696909',
+    parameters: { id: 'Author ID' },
+    name: 'Author Search',
+    maintainers: ['TonyRL'],
+    radar: [
+        {
+            source: ['inspirehep.net/authors/:id'],
+        },
+    ],
+    handler,
+};
+
+export const getAuthorById = (id: string) => cache.tryGet(`inspirehep:author:${id}`, () => ofetch<AuthorResponse>(`${baseUrl}/api/authors/${id}`));
+
+async function handler(ctx) {
+    const id = ctx.req.param('id');
+    const limit = ctx.req.query('limit') ? Number.parseInt(ctx.req.query('limit')) : 25;
+
+    const authorInfo = (await getAuthorById(id)) as AuthorResponse;
+    const response = await ofetch<LiteratureResponse>(`${baseUrl}/api/literature`, {
+        query: {
+            sort: 'mostrecent',
+            size: limit,
+            page: 1,
+            search_type: 'hep-author-publication',
+            author: authorInfo.metadata.facet_author_name,
+        },
+    });
+
+    const items = parseLiterature(response.hits.hits);
+
+    return {
+        title: `${authorInfo.metadata.name.preferred_name} - INSPIRE`,
+        link: `${baseUrl}/authors/${id}`,
+        item: items,
+    };
+}

package/lib/routes/inspirehep/literature.ts

@@ -0,0 +1,42 @@
+import { Route } from '@/types';
+import ofetch from '@/utils/ofetch';
+import { LiteratureResponse } from './types';
+
+import { baseUrl, parseLiterature } from './utils';
+
+export const route: Route = {
+    path: '/literature/:q',
+    example: '/inspirehep/literature/Physics',
+    parameters: { q: 'Search keyword' },
+    name: 'Literature Search',
+    maintainers: ['TonyRL'],
+    radar: [
+        {
+            source: ['inspirehep.net/literature'],
+            target: (_params, url) => `/inspirehep/literature/${new URL(url).searchParams.get('q')}`,
+        },
+    ],
+    handler,
+};
+
+async function handler(ctx) {
+    const q = ctx.req.param('q');
+    const limit = ctx.req.query('limit') ? Number.parseInt(ctx.req.query('limit')) : 25;
+
+    const response = await ofetch<LiteratureResponse>(`${baseUrl}/api/literature`, {
+        query: {
+            sort: 'mostrecent',
+            size: limit,
+            page: 1,
+            q,
+        },
+    });
+
+    const items = parseLiterature(response.hits.hits);
+
+    return {
+        title: 'Literature Search - INSPIRE',
+        link: `${baseUrl}/literature?sort=mostrecent&size=${limit}&page=1&q=${q}`,
+        item: items,
+    };
+}

package/lib/routes/inspirehep/namespace.ts

@@ -0,0 +1,7 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: 'INSPIRE',
+    url: 'inspirehep.net',
+    categories: ['journal'],
+};

package/lib/routes/inspirehep/types.ts

@@ -0,0 +1,210 @@
+interface Links {
+    self?: string;
+    next?: string;
+    bibtex: string;
+    'latex-eu': string;
+    'latex-us': string;
+    json: string;
+    cv: string;
+    citations: string;
+}
+
+interface Metadata {
+    number_of_authors: number;
+    date: string;
+    publication_info: {
+        year: number;
+        artid?: string;
+        journal_volume?: string;
+        journal_title?: string;
+        journal_issue?: string;
+    }[];
+    citation_count: number;
+    is_collection_hidden: boolean;
+    authors: {
+        uuid: string;
+        record: {
+            $ref: string;
+        };
+        full_name: string;
+        first_name: string;
+        ids: {
+            schema: string;
+            value: string;
+        }[];
+        last_name: string;
+        recid: number;
+        affiliations: {
+            value: string;
+            record: {
+                $ref: string;
+            };
+            curated_relation?: boolean;
+        }[];
+        raw_affiliations: {
+            value: string;
+        }[];
+        curated_relation?: boolean;
+    }[];
+    citation_count_without_self_citations: number;
+    titles: {
+        title: string;
+        source: string;
+    }[];
+    texkeys: string[];
+    imprints: {
+        date: string;
+        publisher?: string;
+    }[];
+    abstracts: {
+        value: string;
+        source: string;
+    }[];
+    document_type: string[];
+    control_number: number;
+    inspire_categories: {
+        term: string;
+        source?: string;
+    }[];
+    number_of_pages?: number;
+    keywords?: {
+        value: string;
+        source?: string;
+        schema?: string;
+    }[];
+    thesis_info?: {
+        institutions: {
+            name: string;
+            record: {
+                $ref: string;
+            };
+            curated_relation?: boolean;
+        }[];
+        degree_type: string;
+        date: string;
+    };
+    license?: {
+        url: string;
+        license: string;
+        imposing?: string;
+    }[];
+    persistent_identifiers?: {
+        value: string;
+        schema: string;
+        source: string;
+    }[];
+    supervisors?: {
+        uuid: string;
+        record: {
+            $ref: string;
+        };
+        full_name: string;
+        inspire_roles: string[];
+    }[];
+    isbns?: {
+        value: string;
+        medium?: string;
+    }[];
+    urls?: {
+        value: string;
+        description?: string;
+    }[];
+    dois?: {
+        value: string;
+    }[];
+    number_of_references?: number;
+    external_system_identifiers?: {
+        url_name: string;
+        url_link: string;
+    }[];
+    report_numbers?: {
+        value: string;
+    }[];
+    accelerator_experiments?: {
+        name: string;
+        record: {
+            $ref: string;
+        };
+    }[];
+    documents?: {
+        source: string;
+        key: string;
+        url: string;
+        fulltext: boolean;
+        hidden: boolean;
+        filename: string;
+    }[];
+    citation_pdf_urls?: string[];
+    fulltext_links?: {
+        description: string;
+        value: string;
+    }[];
+}
+
+interface Literature {
+    created: string;
+    metadata: Metadata;
+    links: Links;
+    updated: string;
+    id: string;
+}
+
+export interface AuthorResponse {
+    id: string;
+    uuid: string;
+    revision_id: number;
+    updated: string;
+    links: {
+        json: string;
+    };
+    metadata: {
+        can_edit: boolean;
+        orcid: string;
+        bai: string;
+        facet_author_name: string;
+        should_display_positions: boolean;
+        positions: {
+            institution: string;
+            current: boolean;
+            display_date: string;
+            record: {
+                $ref: string;
+            };
+        }[];
+        project_membership: {
+            name: string;
+            record: {
+                $ref: string;
+            };
+            current: boolean;
+            curated_relation: boolean;
+        }[];
+        ids: {
+            value: string;
+            schema: string;
+        }[];
+        name: {
+            value: string;
+            preferred_name: string;
+        };
+        stub: boolean;
+        status: string;
+        deleted: boolean;
+        control_number: number;
+        legacy_version: string;
+        legacy_creation_date: string;
+    };
+    created: string;
+}
+
+export interface LiteratureResponse {
+    hits: {
+        hits: Literature[];
+        total: number;
+    };
+    links: Links;
+    sort_options: {
+        value: string;
+        title: string;
+    }[];
+}

package/lib/routes/inspirehep/utils.ts

@@ -0,0 +1,15 @@
+import { LiteratureResponse } from './types';
+import { parseDate } from '@/utils/parse-date';
+
+export const baseUrl = 'https://inspirehep.net';
+
+export const parseLiterature = (hits: LiteratureResponse['hits']['hits']) =>
+    hits.map((item) => ({
+        title: item.metadata.titles.map((t) => t.title).join(' '),
+        link: `${baseUrl}/literature/${item.id}`,
+        description: item.metadata.abstracts?.map((a) => `<span>${a.value}</span>`).join('<br>'),
+        pubDate: parseDate(item.created),
+        updated: parseDate(item.updated),
+        category: item.metadata.keywords?.map((k) => k.value),
+        author: item.metadata.authors.map((a) => `${a.first_name} ${a.last_name}${a.affiliations ? ` (${a.affiliations.map((aff) => aff.value).join(', ')})` : ''}`).join(', '),
+    }));