rsshub 1.0.0-master.ff487f3 → 1.0.0-master.ff76aa7

package/lib/routes/geekpark/index.ts

@@ -0,0 +1,219 @@
+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';
+
+export const handler = async (ctx) => {
+    const { column } = ctx.req.param();
+    const limit = ctx.req.query('limit') ? Number.parseInt(ctx.req.query('limit'), 10) : 20;
+
+    const rootUrl = 'https://geekpark.net';
+    const apiRootUrl = 'https://mainssl.geekpark.net';
+    const currentUrl = new URL(column ? `column/${column}` : '', rootUrl).href;
+    const apiUrl = new URL(column ? `api/v1/columns/${column}` : 'api/v2', apiRootUrl).href;
+
+    const { data: response } = await got(apiUrl);
+
+    let items = (response.homepage_posts ?? response.column.posts).slice(0, limit).map((item) => {
+        item = item.post ?? item;
+
+        const title = item.title;
+        const image = item.cover_url;
+        const description = art(path.join(__dirname, 'templates/description.art'), {
+            image: image
+                ? [
+                      {
+                          src: image,
+                          alt: title,
+                      },
+                  ]
+                : undefined,
+            intro: item.abstract,
+        });
+        const guid = `geekpark-${item.id}`;
+
+        return {
+            title,
+            description,
+            pubDate: parseDate(item.published_timestamp, 'X'),
+            link: new URL(`api/v1/posts/${item.id}`, apiRootUrl).href,
+            category: [...new Set([...item.tags, item.column?.title])].filter(Boolean),
+            author: item.authors.map((a) => a.realname ?? a.nickname).join('/'),
+            guid,
+            id: guid,
+            content: {
+                html: description,
+                text: item.abstract,
+            },
+            image,
+            banner: image,
+        };
+    });
+
+    items = await Promise.all(
+        items.map((item) =>
+            cache.tryGet(item.link, async () => {
+                const { data: detailResponse } = await got(item.link);
+
+                const data = detailResponse.post;
+
+                const title = data.title;
+                const image = data.cover_url;
+                const description = art(path.join(__dirname, 'templates/description.art'), {
+                    image: image
+                        ? [
+                              {
+                                  src: image,
+                                  alt: title,
+                              },
+                          ]
+                        : undefined,
+                    intro: data.abstract,
+                    description: data.content,
+                });
+                const guid = `geekpark-${data.id}`;
+
+                item.title = title;
+                item.description = description;
+                item.pubDate = parseDate(data.published_timestamp, 'X');
+                item.link = new URL(`news/${data.id}`, rootUrl).href;
+                item.category = [...new Set([...data.tags, data.column?.title])].filter(Boolean);
+                item.author = data.authors.map((a) => a.realname ?? a.nickname).join('/');
+                item.guid = guid;
+                item.id = guid;
+                item.content = {
+                    html: description,
+                    text: data.content,
+                };
+                item.image = image;
+                item.banner = image;
+                item.updated = parseDate(data.updated_at);
+
+                return item;
+            })
+        )
+    );
+
+    const data = {
+        title: '',
+        description: '',
+        link: currentUrl,
+        item: items,
+        allowEmpty: true,
+        image: '',
+        author: '',
+    };
+
+    if (column) {
+        data.title = `${response.column.title} | 极客公园`;
+        data.description = response.column.description;
+        data.image = response.column.banner_url;
+    } else {
+        const { data: currentResponse } = await got(currentUrl);
+
+        const $ = load(currentResponse);
+
+        data.title = $('title').text();
+        data.description = $('meta[property="og:description"]').prop('content');
+        data.image = `https:${$('meta[name="og:image"]').prop('content')}`;
+        data.author = $('meta[property="og:site_name"]').prop('content');
+    }
+
+    return data;
+};
+
+export const route: Route = {
+    path: '/:column?',
+    name: '栏目',
+    url: 'geekpark.net',
+    maintainers: ['nczitzk'],
+    handler,
+    example: '/geekpark',
+    parameters: { column: '栏目 id，默认为空，即首页资讯，可在对应栏目页 URL 中找到' },
+    description: `:::tip
+  若订阅 [综合报道](https://www.geekpark.net/column/179)，网址为 \`https://www.geekpark.net/column/179\`。截取 \`https://www.geekpark.net/column/\` 到末尾的部分 \`179\` 作为参数填入，此时路由为 [\`/geekpark/179\`](https://rsshub.app/geekpark/179)。
+  :::
+  
+  | 栏目                                                         | ID                                     |
+  | ------------------------------------------------------------ | -------------------------------------- |
+  | [综合报道](https://www.geekpark.net/column/179)              | [179](https://rsshub.app/geekpark/179) |
+  | [AI新浪潮观察](https://www.geekpark.net/column/304)          | [304](https://rsshub.app/geekpark/304) |
+  | [新造车观察](https://www.geekpark.net/column/305)            | [305](https://rsshub.app/geekpark/305) |
+  | [财报解读](https://www.geekpark.net/column/271)              | [271](https://rsshub.app/geekpark/271) |
+  | [底稿对话CEO系列](https://www.geekpark.net/column/308)       | [308](https://rsshub.app/geekpark/308) |
+  | [Geek Insight 特稿系列](https://www.geekpark.net/column/306) | [306](https://rsshub.app/geekpark/306) |
+  | [心科技](https://www.geekpark.net/column/307)                | [307](https://rsshub.app/geekpark/307) |
+  | [行业资讯](https://www.geekpark.net/column/2)                | [2](https://rsshub.app/geekpark/2)     |
+  `,
+    categories: ['new-media'],
+
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportRadar: true,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['geekpark.net'],
+            target: '/',
+        },
+        {
+            source: ['geekpark.net/column/:column?'],
+            target: (params) => {
+                const column = params.column;
+
+                return column ? `/${column}` : '';
+            },
+        },
+        {
+            title: '综合报道',
+            source: ['www.geekpark.net/column/179'],
+            target: '/179',
+        },
+        {
+            title: 'AI新浪潮观察',
+            source: ['www.geekpark.net/column/304'],
+            target: '/304',
+        },
+        {
+            title: '新造车观察',
+            source: ['www.geekpark.net/column/305'],
+            target: '/305',
+        },
+        {
+            title: '财报解读',
+            source: ['www.geekpark.net/column/271'],
+            target: '/271',
+        },
+        {
+            title: '底稿对话CEO系列',
+            source: ['www.geekpark.net/column/308'],
+            target: '/308',
+        },
+        {
+            title: 'Geek Insight 特稿系列',
+            source: ['www.geekpark.net/column/306'],
+            target: '/306',
+        },
+        {
+            title: '心科技',
+            source: ['www.geekpark.net/column/307'],
+            target: '/307',
+        },
+        {
+            title: '行业资讯',
+            source: ['www.geekpark.net/column/2'],
+            target: '/2',
+        },
+    ],
+};

package/lib/routes/geekpark/namespace.ts

@@ -0,0 +1,8 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: '极客公园',
+    url: 'geekpark.net',
+    categories: ['new-media'],
+    description: '',
+};

package/lib/routes/geekpark/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/gisreportsonline/index.ts

@@ -0,0 +1,60 @@
+import { Route } from '@/types';
+
+import { load } from 'cheerio';
+import { parseDate } from '@/utils/parse-date';
+import cache from '@/utils/cache';
+import ofetch from '@/utils/ofetch';
+
+export const route: Route = {
+    path: '/:path{.*}',
+    categories: ['new-media'],
+    example: '/gis/c/security-challenges/',
+    parameters: { path: '包含"Reports"页面下的路径' },
+    name: '报告',
+    maintainers: ['dzx-dzx'],
+    radar: [
+        {
+            source: ['www.gisreportsonline.com'],
+        },
+    ],
+    handler,
+};
+
+async function handler(ctx) {
+    const rootUrl = 'https://www.gisreportsonline.com';
+    const currentUrl = `${rootUrl}/${ctx.req.param('path')}`;
+    const response = await ofetch(currentUrl);
+
+    const $ = load(response);
+
+    const list = $('article h3 a')
+        .toArray()
+        .map((e) => ({ link: $(e).attr('href'), title: $(e).text() }));
+
+    const items = await Promise.all(
+        list.map((item) =>
+            cache.tryGet(item.link, async () => {
+                const content = load(await ofetch(item.link));
+                const ldjson = JSON.parse(content('script.rank-math-schema-pro').text())['@graph'].find((e) => e['@type'] === 'NewsArticle');
+
+                item.pubDate = parseDate(ldjson.datePublished);
+                item.updated = parseDate(ldjson.dateModified);
+                item.author = [ldjson.author];
+                item.category = ldjson.keywords.split(',');
+                item.language = ldjson.inLanguage;
+
+                item.description = content('header.entry-header ~ :not(#pos-conclusion ~ *)')
+                    .toArray()
+                    .map((e) => content(e).prop('outerHTML'))
+                    .join('');
+
+                return item;
+            })
+        )
+    );
+    return {
+        title: $('title').text(),
+        link: currentUrl,
+        item: items,
+    };
+}

package/lib/routes/gisreportsonline/namespace.ts

@@ -0,0 +1,6 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: 'GIS Reports',
+    url: 'www.gisreportsonline.com',
+};

package/lib/routes/github/activity.ts

@@ -2,6 +2,7 @@ import { Route, ViewType } from '@/types';
 import ofetch from '@/utils/ofetch';
 import { parseDate } from '@/utils/parse-date';
 import Parser from 'rss-parser';
+import sanitizeHtml from 'sanitize-html';
 
 const parser = new Parser();
 
@@ -44,7 +45,7 @@ export const route: Route = {
             item: feed.items.map((item) => ({
                 title: item.title ?? '',
                 link: item.link,
-                description: item.content?.replace(/href="(.+?)"/g, `href="https://github.com$1"`),
+                description: sanitizeHtml(item.content?.replace(/href="\/(.+?)"/g, `href="https://github.com/$1"`) ?? '', { allowedTags: [...sanitizeHtml.defaults.allowedTags, 'img'] }),
                 pubDate: item.pubDate ? parseDate(item.pubDate) : undefined,
                 author: item.author,
                 guid: item.id,

package/lib/routes/github/advisor.ts

@@ -0,0 +1,97 @@
+import { Route } from '@/types';
+import got from '@/utils/got';
+import { load } from 'cheerio';
+import { parseDate } from '@/utils/parse-date';
+import ofetch from '@/utils/ofetch';
+import cache from '@/utils/cache';
+
+export const route: Route = {
+    path: '/advisor/data/:type?/:category?',
+    categories: ['programming'],
+    example: '/github/advisor/data/reviewed/composer',
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['github.com/advisories', 'github.com'],
+        },
+    ],
+    name: 'Github Advisory Database RSS',
+    maintainers: ['sd0ric4'],
+    handler,
+    description: `
+| Type | Description | Explanation |
+| --- | --- | --- |
+| reviewed | Reviewed | 已审核 |
+| unreviewed | Unreviewed | 未审核 |
+
+| Category | Description | Explanation |
+| --- | --- | --- |
+| composer | Composer | PHP 依赖管理工具 |
+| go | Go | Go 语言包管理工具 |
+| maven | Maven | Java 项目管理工具 |
+| npm | NPM | Node.js 包管理工具 |
+| nuget | NuGet | .NET 包管理工具 |
+| pip | Pip | Python 包管理工具 |
+| pub | Pub | Dart 包管理工具 |
+| rubygems | RubyGems | Ruby 包管理工具 |
+| rust | Rust | Rust 包管理工具 |
+| erlang | Erlang | Erlang 包管理工具 |
+| actions | Actions | GitHub Actions |
+| swift | Swift | Swift 包管理工具 |`,
+};
+
+async function handler(ctx) {
+    const { category, type } = ctx.req.param();
+
+    const apiRootUrl = 'https://github.com/advisories';
+    const apiUrl = `${apiRootUrl}?query=type%3A${type}+ecosystem%3A${category}`;
+    const currentUrl = `https://github.com/advisories`;
+
+    const response = await got({
+        method: 'get',
+        url: apiUrl,
+    });
+    const $ = load(response.data);
+
+    const list = $('div.Box-row')
+        .toArray()
+        .map((item) => {
+            item = $(item);
+            const a = item.find('a.Link--primary');
+            const b = item.find('relative-time').attr('datetime');
+            const title = a.text() || 'No title';
+            const link = a.attr('href') || '#';
+            const pubDate = parseDate(b || '');
+
+            return {
+                title,
+                link: `https://github.com${link}`,
+                pubDate,
+                description: '',
+            };
+        });
+    const items = await Promise.all(
+        list.map((item) =>
+            cache.tryGet(item.link, async () => {
+                const response = await ofetch(item.link);
+                const $ = load(response);
+
+                item.description = $('.comment-body').first().html() || '';
+
+                return item;
+            })
+        )
+    );
+    return {
+        title: `GitHub Advisory Database RSS - ${category} - ${type}`,
+        link: currentUrl,
+        item: items,
+    };
+}

package/lib/routes/github/comments.ts

@@ -1,5 +1,5 @@
 import { Route } from '@/types';
-import got from '@/utils/got';
+import ofetch from '@/utils/ofetch';
 import { parseDate } from '@/utils/parse-date';
 import MarkdownIt from 'markdown-it';
 const md = MarkdownIt({
@@ -59,16 +59,16 @@ async function handler(ctx) {
 }
 
 async function allIssues(ctx, user, repo, limit, headers) {
-    const response = await got(`${apiUrl}/repos/${user}/${repo}/issues/comments`, {
+    const response = await ofetch.raw(`${apiUrl}/repos/${user}/${repo}/issues/comments`, {
         headers,
-        searchParams: {
+        query: {
             sort: 'updated',
             direction: 'desc',
             per_page: limit,
         },
     });
 
-    const timeline = response.data;
+    const timeline = response._data;
 
     const items = timeline.map((item) => {
         const actor = item.actor?.login ?? item.user?.login ?? 'ghost';
@@ -86,14 +86,13 @@ async function allIssues(ctx, user, repo, limit, headers) {
         };
     });
 
-    // response headers is broken due to #14922
-    // const rateLimit = {
-    //     limit: Number.parseInt(response.headers['x-ratelimit-limit']),
-    //     remaining: Number.parseInt(response.headers['x-ratelimit-remaining']),
-    //     reset: parseDate(Number.parseInt(response.headers['x-ratelimit-reset']) * 1000),
-    //     resoure: response.headers['x-ratelimit-resource'],
-    //     used: Number.parseInt(response.headers['x-ratelimit-used']),
-    // };
+    const rateLimit = {
+        limit: Number.parseInt(response.headers.get('x-ratelimit-limit')),
+        remaining: Number.parseInt(response.headers.get('x-ratelimit-remaining')),
+        reset: parseDate(Number.parseInt(response.headers.get('x-ratelimit-reset')) * 1000),
+        resoure: response.headers.get('x-ratelimit-resource'),
+        used: Number.parseInt(response.headers.get('x-ratelimit-used')),
+    };
 
     const ret = {
         title: `${user}/${repo}: Issue & Pull request comments`,
@@ -103,35 +102,38 @@ async function allIssues(ctx, user, repo, limit, headers) {
 
     ctx.set('json', {
         ...ret,
-        // rateLimit,
+        rateLimit,
     });
     return ret;
 }
 
 async function singleIssue(ctx, user, repo, number, limit, headers) {
-    const response = await got(`${apiUrl}/repos/${user}/${repo}/issues/${number}`, {
+    const response = await ofetch.raw(`${apiUrl}/repos/${user}/${repo}/issues/${number}`, {
         headers,
     });
-    const issue = response.data;
+    const issue = response._data;
     const type = issue.pull_request ? 'pull' : 'issue';
 
-    const timelineResponse = await got(issue.timeline_url, {
+    let timelineResponse = await ofetch.raw(issue.timeline_url, {
         headers,
-        searchParams: {
+        query: {
             per_page: limit,
         },
     });
-    const timeline = timelineResponse.data;
-
-    const items = [
-        {
+    const items = [];
+    const lastUrl = timelineResponse.headers.get('link')?.match(/<(\S+?)>; rel="last"/)?.[1];
+    if (lastUrl) {
+        timelineResponse = await ofetch.raw(lastUrl, { headers });
+    } else {
+        items.push({
             title: `${issue.user.login} created ${user}/${repo}: ${typeDict[type].title} #${issue.number}`,
             description: issue.body ? md.render(issue.body) : null,
             author: issue.user.login,
             pubDate: parseDate(issue.created_at),
             link: `${issue.html_url}#issue-${issue.id}`,
-        },
-    ];
+        });
+    }
+    const timeline = timelineResponse._data;
 
     for (const item of timeline) {
         const actor = item.actor?.login ?? item.user?.login ?? 'ghost';
@@ -194,13 +196,13 @@ async function singleIssue(ctx, user, repo, number, limit, headers) {
 
     ctx.set('json', {
         ...ret,
-        // rateLimit: {
-        //     limit: Number.parseInt(response.headers['x-ratelimit-limit']),
-        //     remaining: Number.parseInt(response.headers['x-ratelimit-remaining']),
-        //     reset: parseDate(Number.parseInt(response.headers['x-ratelimit-reset']) * 1000),
-        //     resoure: response.headers['x-ratelimit-resource'],
-        //     used: Number.parseInt(response.headers['x-ratelimit-used']),
-        // },
+        rateLimit: {
+            limit: Number.parseInt(response.headers.get('x-ratelimit-limit')),
+            remaining: Number.parseInt(response.headers.get('x-ratelimit-remaining')),
+            reset: parseDate(Number.parseInt(response.headers.get('x-ratelimit-reset')) * 1000),
+            resoure: response.headers.get('x-ratelimit-resource'),
+            used: Number.parseInt(response.headers.get('x-ratelimit-used')),
+        },
     });
     return ret;
 }