rsshub 1.0.0-master.f9ec483 → 1.0.0-master.fa04a11

package/lib/routes/papers/query.ts

@@ -0,0 +1,112 @@
+import { Route } from '@/types';
+import { getCurrentPath } from '@/utils/helpers';
+const __dirname = getCurrentPath(import.meta.url);
+
+import { parseDate } from '@/utils/parse-date';
+import { art } from '@/utils/render';
+import path from 'node:path';
+import parser from '@/utils/rss-parser';
+
+const pdfUrlGenerators = {
+    arxiv: (id: string) => `https://arxiv.org/pdf/${id}.pdf`,
+};
+
+export const handler = async (ctx) => {
+    const { keyword = 'query/Detection' } = ctx.req.param();
+    const limit = ctx.req.query('limit') ? Number.parseInt(ctx.req.query('limit'), 10) : 150;
+
+    const rootUrl = 'https://papers.cool';
+    const currentUrl = new URL(`arxiv/search?highlight=1&query=${keyword}&sort=0`, rootUrl).href;
+    const feedUrl = new URL(`arxiv/search/feed?query=${keyword}`, rootUrl).href;
+
+    const site = keyword.split(/\//)[0];
+    const apiKimiUrl = new URL(`${site}/kimi?paper=`, rootUrl).href;
+    const feed = await parser.parseURL(feedUrl);
+
+    const language = 'en';
+
+    const items = feed.items.slice(0, limit).map((item) => {
+        const title = item.title;
+        const guid = item.guid;
+
+        const id = item.link?.split(/\//).pop() ?? '';
+        const kimiUrl = new URL(id, apiKimiUrl).href;
+        const pdfUrl = Object.hasOwn(pdfUrlGenerators, site) ? pdfUrlGenerators[site](id) : undefined;
+
+        const authorString = item.author;
+        const description = art(path.join(__dirname, 'templates/description.art'), {
+            pdfUrl,
+            siteUrl: item.link,
+            kimiUrl,
+            authorString,
+            summary: item.summary,
+        });
+
+        return {
+            title,
+            description,
+            pubDate: parseDate(item.pubDate ?? ''),
+            link: item.link,
+            category: item.categories,
+            author: authorString,
+            doi: `${site}${id}`,
+            guid,
+            id: guid,
+            content: {
+                html: description,
+                text: item.content,
+            },
+            language,
+            enclosure_url: pdfUrl,
+            enclosure_type: 'application/pdf',
+            enclosure_title: title,
+        };
+    });
+
+    return {
+        title: feed.title,
+        description: feed.description,
+        link: currentUrl,
+        item: items,
+        allowEmpty: true,
+        image: feed.image?.url,
+        language: feed.language,
+    };
+};
+
+export const route: Route = {
+    path: '/query/:keyword{.+}?',
+    name: 'Topic',
+    url: 'papers.cool',
+    maintainers: ['Muyun99'],
+    handler,
+    example: '/papers/query/Detection',
+    parameters: { keyword: 'Keyword to search for papers, e.g., Detection, Segmentation, etc.' },
+    description: `::: tip
+  If you subscibe to [arXiv Paper queryed by Detection](https://papers.cool/arxiv/search?highlight=1&query=Detection), where the URL is \`https://papers.cool/arxiv/search?highlight=1&query=Detection\`, extract the part \`https://papers.cool/\` to the end, and use it as the parameter to fill in. Therefore, the route will be [\`/papers/query/Detection\`](https://rsshub.app/papers/query/Detection).
+:::
+
+  | Category                                              | id                  |
+  | ----------------------------------------------------- | ------------------- |
+  | arXiv Paper queryed by Detection                      | query/Detection     |
+  | arXiv Paper queryed by Segmentation                   | query/Segmentation  |
+  `,
+    categories: ['journal'],
+
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportRadar: true,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: true,
+    },
+    radar: [
+        {
+            title: 'arXiv Paper queryed by Keyword',
+            source: ['papers.cool/arxiv/search?highlight=1&query=*&sort=0'],
+            target: '/papers/query/:keyword',
+        },
+    ],
+};

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

@@ -10,6 +10,10 @@
   <a href="{{ kimiUrl }}">[Kimi]</a>
 {{ /if }}
 
+{{ if authorString }}
+  <p><b>Authors:</b> {{ authorString }}</p>
+{{ /if }}
+
 {{ if summary }}
   <p>{{ summary }}</p>
 {{ /if }}

package/lib/routes/parliament.uk/namespace.ts

@@ -3,5 +3,7 @@ import type { Namespace } from '@/types';
 export const namespace: Namespace = {
     name: 'UK Parliament',
     url: 'parliament.uk',
+    categories: ['government'],
+    description: 'The UK Parliament has two Houses that work on behalf of UK citizens to check and challenge the work of Government, make and shape effective laws, and debate/make decisions on the big issues of the day.',
     lang: 'en',
 };

package/lib/routes/parliament.uk/petitions.ts

@@ -0,0 +1,191 @@
+import path from 'node:path';
+
+import { type Context } from 'hono';
+import { load, type CheerioAPI } from 'cheerio';
+
+import { type DataItem, type Route, type Data, ViewType } from '@/types';
+import { getCurrentPath } from '@/utils/helpers';
+import { parseDate } from '@/utils/parse-date';
+import { art } from '@/utils/render';
+import ofetch from '@/utils/ofetch';
+
+const __dirname = getCurrentPath(import.meta.url);
+
+export const handler = async (ctx: Context): Promise<Data> => {
+    const { state = 'all' } = ctx.req.param();
+    const limit: number = Number.parseInt(ctx.req.query('limit') ?? '50', 10);
+
+    const rootUrl: string = 'https://petition.parliament.uk';
+    const targetUrl: string = new URL(`petitions?state=${state}`, rootUrl).href;
+    const jsonUrl: string = new URL('petitions.json', rootUrl).href;
+
+    const response = await ofetch(targetUrl);
+    const $: CheerioAPI = load(response);
+    const language: string = $('html').prop('lang') ?? 'en';
+
+    const jsonResponse = await ofetch(jsonUrl, {
+        query: {
+            page: 1,
+            state,
+        },
+    });
+
+    const items = jsonResponse.data.slice(0, limit).map((item): DataItem => {
+        const attributes = item.attributes;
+
+        const title = attributes.action;
+        const description = art(path.join(__dirname, 'templates/description.art'), {
+            intro: attributes.background,
+            description: attributes.additional_details,
+        });
+        const guid = `parliament.uk-petition-${item.id}`;
+
+        const author: DataItem['author'] = attributes.creator_name;
+
+        const extraLinks = attributes.departments?.map((link) => ({
+            url: link.url,
+            type: 'related',
+            content_html: link.name,
+        }));
+
+        return {
+            title,
+            description,
+            pubDate: parseDate(attributes.created_at),
+            link: new URL(`petitions/${item.id}`, rootUrl).href,
+            category: [...new Set([...(attributes.topics ?? []), ...(attributes.departments?.map((d) => d.name) ?? [])])].filter(Boolean),
+            author,
+            guid,
+            id: guid,
+            content: {
+                html: description,
+                text: attributes.background,
+            },
+            updated: parseDate(attributes.updated_at),
+            language,
+            _extra: {
+                links: extraLinks?.length ? extraLinks : undefined,
+            },
+        };
+    });
+
+    const feedImage = $('meta[property="og:image"]').prop('content');
+
+    return {
+        title: $('h1.page-title').text(),
+        description: $('meta[property="twitter:description"]').prop('content'),
+        link: targetUrl,
+        item: items,
+        allowEmpty: true,
+        image: feedImage,
+        author: $('meta[name="msapplication-tooltip"]').prop('content'),
+        language,
+        id: $('meta[property="og:url"]').prop('content'),
+    };
+};
+
+export const route: Route = {
+    path: '/petitions/:state?',
+    name: 'Petitions',
+    url: 'petition.parliament.uk',
+    maintainers: ['nczitzk'],
+    handler,
+    example: '/parliament.uk/petitions/all',
+    parameters: {
+        state: 'State, `all` by default, see below',
+    },
+    description: `::: tip
+If you subscribe to [Recent petitions](https://petition.parliament.uk/petitions?state=recent)，where the URL is \`https://petition.parliament.uk/petitions?state=recent\`, use the value of \`state\` as the parameter to fill in. Therefore, the route will be [\`/parliament.uk/petitions/recent\`](https://rsshub.app/parliament.uk/petitions/recent).
+:::
+
+<details>
+  <summary>More states</summary>
+
+| Name                            | ID                |
+| ------------------------------- | ----------------- |
+| All petitions                   | all               |
+| Open petitions                  | open              |
+| Recent petitions                | recent            |
+| Closed petitions                | closed            |
+| Rejected petitions              | rejected          |
+| Awaiting government response    | awaiting_response |
+| Government responses            | with_response     |
+| Awaiting a debate in Parliament | awaiting_debate   |
+| Debated in Parliament           | debated           |
+| Not debated in Parliament       | not_debated       |
+
+</details>
+    `,
+    categories: ['government'],
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportRadar: true,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['petition.parliament.uk/petitions'],
+            target: (_, url) => {
+                const urlObj = new URL(url);
+                const state = urlObj.searchParams.get('state');
+
+                return `/parliament.uk/petitions${state ? `/${state}` : ''}`;
+            },
+        },
+        {
+            title: 'All petitions',
+            source: ['petition.parliament.uk/petitions'],
+            target: '/petitions/all',
+        },
+        {
+            title: 'Open petitions',
+            source: ['petition.parliament.uk/petitions'],
+            target: '/petitions/open',
+        },
+        {
+            title: 'Recent petitions',
+            source: ['petition.parliament.uk/petitions'],
+            target: '/petitions/recent',
+        },
+        {
+            title: 'Closed petitions',
+            source: ['petition.parliament.uk/petitions'],
+            target: '/petitions/closed',
+        },
+        {
+            title: 'Rejected petitions',
+            source: ['petition.parliament.uk/petitions'],
+            target: '/petitions/rejected',
+        },
+        {
+            title: 'Awaiting government response',
+            source: ['petition.parliament.uk/petitions'],
+            target: '/petitions/awaiting_response',
+        },
+        {
+            title: 'Government responses',
+            source: ['petition.parliament.uk/petitions'],
+            target: '/petitions/with_response',
+        },
+        {
+            title: 'Awaiting a debate in Parliament',
+            source: ['petition.parliament.uk/petitions'],
+            target: '/petitions/awaiting_debate',
+        },
+        {
+            title: 'Debated in Parliament',
+            source: ['petition.parliament.uk/petitions'],
+            target: '/petitions/debated',
+        },
+        {
+            title: 'Not debated in Parliament',
+            source: ['petition.parliament.uk/petitions'],
+            target: '/petitions/not_debated',
+        },
+    ],
+    view: ViewType.Articles,
+};

package/lib/routes/parliament.uk/templates/description.art

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

package/lib/routes/patreon/feed.ts

@@ -0,0 +1,126 @@
+import { Route } from '@/types';
+import { CreatorData, MediaRelation, PostData } from './types';
+
+import cache from '@/utils/cache';
+import ofetch from '@/utils/ofetch';
+import * as cheerio from 'cheerio';
+import { parseDate } from '@/utils/parse-date';
+import path from 'node:path';
+import { getCurrentPath } from '@/utils/helpers';
+import { art } from '@/utils/render';
+import { config } from '@/config';
+
+const __dirname = getCurrentPath(import.meta.url);
+
+export const route: Route = {
+    path: '/:creator',
+    categories: ['new-media'],
+    example: '/patreon/straightupsisters',
+    parameters: { creator: 'Patreon creator id, can be found in the url' },
+    features: {
+        requireConfig: [
+            {
+                name: 'PATREON_SESSION_ID',
+                optional: true,
+                description: 'The value of the session_id cookie after logging in to Patreon, required to access paid posts',
+            },
+        ],
+    },
+    radar: [
+        {
+            source: ['patreon.com/:creator'],
+        },
+    ],
+    name: 'Home',
+    maintainers: ['TonyRL'],
+    handler,
+};
+
+async function handler(ctx) {
+    const { creator } = ctx.req.param();
+
+    const baseUrl = 'https://www.patreon.com';
+    const link = `${baseUrl}/${creator}`;
+
+    const creatorData = (await cache.tryGet(`patreon:creator:${creator}`, async () => {
+        const response = await ofetch(link);
+
+        const $ = cheerio.load(response);
+        const nextData = JSON.parse($('#__NEXT_DATA__').text());
+        const bootstrapEnvelope = nextData.props.pageProps.bootstrapEnvelope;
+
+        return {
+            meta: bootstrapEnvelope.meta,
+            id: bootstrapEnvelope.pageBootstrap.campaign.data.id,
+            attributes: bootstrapEnvelope.pageBootstrap.campaign.data.attributes,
+        };
+    })) as CreatorData;
+
+    if (!creatorData.id) {
+        throw new Error('Creator not found');
+    }
+
+    let headers = {};
+    if (config.patreon?.sessionId) {
+        headers = {
+            Cookie: `session_id=${config.patreon.sessionId}`,
+        };
+    }
+
+    const posts = await ofetch<PostData>('https://www.patreon.com/api/posts', {
+        headers,
+        query: {
+            include:
+                'campaign,access_rules,access_rules.tier.null,attachments_media,audio,audio_preview.null,drop,images,media,native_video_insights,poll.choices,poll.current_user_responses.user,poll.current_user_responses.choice,poll.current_user_responses.poll,user,user_defined_tags,ti_checks,video.null,content_unlock_options.product_variant.null',
+            'fields[campaign]': 'currency,show_audio_post_download_links,avatar_photo_url,avatar_photo_image_urls,earnings_visibility,is_nsfw,is_monthly,name,url',
+            'fields[post]':
+                'change_visibility_at,comment_count,commenter_count,content,created_at,current_user_can_comment,current_user_can_delete,current_user_can_report,current_user_can_view,current_user_comment_disallowed_reason,current_user_has_liked,embed,image,insights_last_updated_at,is_paid,like_count,meta_image_url,min_cents_pledged_to_view,monetization_ineligibility_reason,post_file,post_metadata,published_at,patreon_url,post_type,pledge_url,preview_asset_type,thumbnail,thumbnail_url,teaser_text,title,upgrade_url,url,was_posted_by_campaign_owner,has_ti_violation,moderation_status,post_level_suspension_removal_date,pls_one_liners_by_category,video,video_preview,view_count,content_unlock_options,is_new_to_current_user,watch_state',
+            'fields[post_tag]': 'tag_type,value',
+            'fields[user]': 'image_url,full_name,url',
+            'fields[access_rule]': 'access_rule_type,amount_cents',
+            'fields[media]': 'id,image_urls,display,download_url,metadata,file_name',
+            'fields[native_video_insights]': 'average_view_duration,average_view_pct,has_preview,id,last_updated_at,num_views,preview_views,video_duration',
+            'fields[content-unlock-option]': 'content_unlock_type',
+            'fields[product-variant]': 'price_cents,currency_code,checkout_url,is_hidden,published_at_datetime,content_type,orders_count,access_metadata',
+            'filter[campaign_id]': creatorData.id,
+            'filter[contains_exclusive_posts]': true,
+            'filter[is_draft]': false,
+            sort: '-published_at',
+            'json-api-use-default-includes': false,
+            'json-api-version': '1.0',
+        },
+    });
+
+    const items = posts.data.map(({ attributes, relationships }) => {
+        for (const [key, value] of Object.entries(relationships)) {
+            if (value.data) {
+                relationships[key] = Array.isArray(value.data) ? value.data.map((item) => posts.included.find((i) => i.id === item.id)) : posts.included.find((i) => i.id === value.data.id);
+            }
+        }
+        if (attributes.video_preview) {
+            relationships.video_preview = posts.included.find((i) => Number.parseInt(i.id) === attributes.video_preview.media_id) as unknown as MediaRelation;
+        }
+
+        return {
+            title: attributes.title,
+            description: art(path.join(__dirname, 'templates/description.art'), {
+                attributes,
+                relationships,
+                included: posts.included,
+            }),
+            link: attributes.url,
+            pubDate: parseDate(attributes.published_at),
+            image: attributes.thumbnail?.url ?? attributes.image.url,
+            category: relationships.user_defined_tags?.map((tag) => tag.attributes.value),
+        };
+    });
+
+    return {
+        title: creatorData.meta.title,
+        description: creatorData.meta.desc,
+        link,
+        image: creatorData.attributes.avatar_photo_url,
+        item: items,
+        allowEmpty: true,
+    };
+}

package/lib/routes/patreon/namespace.ts

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

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

@@ -0,0 +1,39 @@
+{{ if attributes.post_type === 'image_file' }}
+    {{ each attributes.post_metadata.image_order mediaIdStr }}
+        {{ set img = included.find((i) => i.id === mediaIdStr) }}
+        {{ if img }}
+            <img src="{{ img.attributes.image_urls.original }}" alt="{{ img.attributes.file_name }}"><br>
+        {{ /if }}
+    {{ /each }}
+
+{{ else if attributes.post_type === 'video_external_file' }}
+    {{ if attributes.video_preview }}
+    <video controls preload="metadata" poster="{{ attributes.image.url }}">
+        <source src="{{ relationships.video_preview.attributes.download_url }}" type="video/mp4">
+    </video><br>
+    {{ /if }}
+
+{{ else if attributes.post_type === 'audio_file' || attributes.post_type === 'podcast' }}
+    <img src="{{ attributes.thumbnail.url }}"><br>
+    {{ set url = relationships.audio.attributes.download_url || relationships.audio_preview.attributes.download_url }}
+    <audio controls preload="metadata">
+        <source src="{{ url }}" type="audio/mpeg">
+    </audio><br>
+
+{{ else if attributes.post_type === 'video_embed' || attributes.post_type === 'link' }}
+    <img src="{{ attributes.image.url }}"><br>
+
+{{ else }}
+Post type: "{{ attributes.post_type }}" is not supported. <br>
+
+{{ /if }}
+
+{{ if attributes.content || attributes.teaser_text }}
+    {{@ attributes.content || attributes.teaser_text }}
+{{ /if }}
+
+{{ if relationships.attachments_media }}
+    {{ each relationships.attachments_media media }}
+        <a href="{{ media.attributes.download_url }}">{{ media.attributes.file_name }}</a><br>
+    {{ /each }}
+{{ /if }}