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

package/lib/routes/finology/utils.ts

@@ -1,60 +1,65 @@
 import cache from '@/utils/cache';
-import got from '@/utils/got';
 import { load } from 'cheerio';
 import { parseDate } from '@/utils/parse-date';
 import timezone from '@/utils/timezone';
+import ofetch from '@/utils/ofetch';
+import { DataItem } from '@/types';
 
-const getItems = async (url: string, extra: { date: boolean; selector: string; topicName?: string }) => {
+const getItems = async (url: string, extra: { date: boolean; selector: string }) => {
     const mainUrl = 'https://insider.finology.in';
-    const { data: response } = await got(url);
+    const response = await ofetch(url);
     const $ = load(response);
     const listItems = $(extra.selector)
         .toArray()
         .map((item) => {
-            item = $(item);
-            const title = item.find('p.text-m-height').text();
-            const link = item.find('a').attr('href');
-            const pubDate = extra.date ? timezone(parseDate(item.find('div.text-light p').first().text()), 0) : '';
-            const itunes_item_image = item.find('img').attr('src');
-            const category = item.find('p.pt025').text();
+            const $item = $(item);
+            const title = $item.find('p.text-m-height').text();
+            const link = $item.find('a').attr('href');
+            const pubDate = extra.date ? timezone(parseDate($item.find('div.text-light p').first().text()), 0) : '';
+            const itunes_item_image = $item.find('img').attr('src');
+            const category = [$item.find('p.pt025').text()];
             return {
                 title,
                 link: `${mainUrl}${link}`,
                 pubDate,
                 itunes_item_image,
                 category,
-            };
+            } as DataItem;
         });
 
     const items = (
         await Promise.allSettled(
-            listItems.map((item) =>
-                cache.tryGet(item.link, async () => {
-                    const { data: response } = await got(item.link);
+            listItems.map((item) => {
+                if (item.link === undefined) {
+                    return item;
+                }
+                return cache.tryGet(item.link, async () => {
+                    const response = await ofetch(item.link || '');
                     const $ = load(response);
                     const div = $('div.w60.flex.flex-wrap-badge');
                     item.author = div.find('div a p').text();
-                    item.updated = div.find('p:contains("Updated on") span').text();
-                    item.description = $('div#main-wrapper div#insiderhead')
-                        .find('div.flex.flex-col.w100.align-center')
-                        .children('div.m-position-r')
-                        .remove()
-                        .end()
-                        .find('a[href="https://quest.finology.in/"]')
-                        .remove()
-                        .end()
-                        .find('div.blur-wall-wrap')
-                        .remove()
-                        .end()
-                        .html();
+                    item.updated = extra.date ? parseDate(div.find('p:contains("Updated on") span').text()) : '';
+                    item.description =
+                        $('div#main-wrapper div#insiderhead')
+                            .find('div.flex.flex-col.w100.align-center')
+                            .children('div.m-position-r')
+                            .remove()
+                            .end()
+                            .find('a[href="https://quest.finology.in/"]')
+                            .remove()
+                            .end()
+                            .find('div.blur-wall-wrap')
+                            .remove()
+                            .end()
+                            .html() ?? '';
                     return item;
-                })
-            )
+                });
+            })
         )
     ).map((v, index) => (v.status === 'fulfilled' ? v.value : { ...listItems[index], description: `Website did not load within Timeout Limits. <a href="${listItems[index].link}">Check with Website if the page is slow</a>` }));
-    extra.topicName = $('h1.font-heading.fs1875')?.text();
-
-    return items;
+    const topicName = $('h1.font-heading.fs1875')?.text();
+    const validItems: DataItem[] = items.filter((item): item is DataItem => item !== null && typeof item !== 'string');
+    return { items: validItems, topicName };
 };
 
 export { getItems };

package/lib/routes/flyert/forum.ts

@@ -0,0 +1,99 @@
+import { Route } from '@/types';
+
+import cache from '@/utils/cache';
+import got from '@/utils/got';
+import iconv from 'iconv-lite';
+import { load } from 'cheerio';
+import { rootUrl, parseArticleList, parsePostList, parseArticle, parsePost } from './util';
+
+export const handler = async (ctx) => {
+    const { params } = ctx.req.param();
+    const limit = ctx.req.query('limit') ? Number.parseInt(ctx.req.query('limit'), 10) : 5;
+
+    const decodedParams = params
+        ? decodeURIComponent(params)
+              .split(/&/)
+              .filter((p) => p.split(/=/).length === 2)
+              .join('&')
+        : undefined;
+
+    const currentUrl = new URL(`forum.php${decodedParams ? `?${decodedParams}` : ''}`, rootUrl).href;
+
+    const { data: response } = await got(currentUrl, {
+        responseType: 'buffer',
+    });
+
+    const $ = load(iconv.decode(response, 'gbk'));
+
+    const language = $('meta[http-equiv="Content-Language"]').prop('content');
+
+    let items = $('table#threadlisttableid').length === 0 ? parseArticleList($, limit) : parsePostList($, limit);
+
+    items = await Promise.all(
+        items.map((item) =>
+            cache.tryGet(item.link, async () => {
+                const { data: detailResponse } = await got(item.link, {
+                    responseType: 'buffer',
+                });
+
+                const $$ = load(iconv.decode(detailResponse, 'gbk').replaceAll(/<\/?ignore_js_op>/g, ''));
+
+                item = $$('div.firstpost').length === 0 ? parseArticle($$, item) : parsePost($$, item);
+
+                item.language = language;
+
+                return item;
+            })
+        )
+    );
+
+    const image = `https:${$('div.wp h2 a img').prop('src')}`;
+
+    return {
+        title: `飞客 - ${$('a.forum_name, li.a, li.cur, li.xw1, div.z > a.xw1')
+            .toArray()
+            .map((a) => $(a).text())
+            .join(' - ')}`,
+        description: $('meta[name="description"]').prop('content'),
+        link: currentUrl,
+        item: items,
+        allowEmpty: true,
+        image,
+        author: $('meta[name="application-name"]').prop('content'),
+    };
+};
+
+export const route: Route = {
+    path: '/forum/:params{.+}?',
+    name: '会员说',
+    url: 'www.flyert.com.cn',
+    maintainers: ['nczitzk'],
+    handler,
+    example: '/flyert/forum',
+    parameters: { params: '参数，默认为空，可在对应分类页 URL 中找到' },
+    description: `::: tip
+  若订阅 [酒店集团优惠](https://www.flyert.com.cn/forum.php?mod=forumdisplay&sum=all&fid=all&catid=322&filter=sortid&sortid=144&searchsort=1&youhui_type=19)，网址为 \`https://www.flyert.com.cn/forum.php?mod=forumdisplay&sum=all&fid=all&catid=322&filter=sortid&sortid=144&searchsort=1&youhui_type=19\`。截取 \`https://www.flyert.com.cn/forum.php?\` 到末尾的部分 \`mod=forumdisplay&sum=all&fid=all&catid=322&filter=sortid&sortid=144&searchsort=1&youhui_type=19\` **进行 UrlEncode 编码** 后作为参数填入，此时路由为 [\`/flyert/forum/mod%3Dforumdisplay%26sum%3Dall%26fid%3Dall%26catid%3D322%26filter%3Dsortid%26sortid%3D144%26searchsort%3D1%26youhui_type%3D226\`](https://rsshub.app/flyert/forum/mod%3Dforumdisplay%26sum%3Dall%26fid%3Dall%26catid%3D322%26filter%3Dsortid%26sortid%3D144%26searchsort%3D1%26youhui_type%3D226)。
+:::
+    `,
+    categories: ['bbs'],
+
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportRadar: true,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['www.flyert.com.cn/forum.php'],
+            target: (_, url) => {
+                const params = [...url.searchParams.entries()].map(([key, value]) => key + '=' + value).join('&');
+
+                return `/forum${params ? `/${encodeURIComponent(params)}` : ''}`;
+            },
+        },
+    ],
+};

package/lib/routes/flyert/namespace.ts

@@ -3,5 +3,6 @@ import type { Namespace } from '@/types';
 export const namespace: Namespace = {
     name: '飞客茶馆',
     url: 'flyert.com',
+    description: '',
     lang: 'zh-CN',
 };

package/lib/routes/flyert/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/flyert/util.ts

@@ -0,0 +1,188 @@
+import { getCurrentPath } from '@/utils/helpers';
+const __dirname = getCurrentPath(import.meta.url);
+
+import { CheerioAPI } from 'cheerio';
+import timezone from '@/utils/timezone';
+import { parseDate } from '@/utils/parse-date';
+import { art } from '@/utils/render';
+import path from 'node:path';
+
+const rootUrl = 'https://www.flyert.com.cn';
+
+/**
+ * Parses a list of articles based on a CheerioAPI object and a limit.
+ * @param $ The CheerioAPI object.
+ * @param limit The maximum number of articles to parse.
+ * @returns An array of parsed article objects.
+ */
+const parseArticleList = ($: CheerioAPI, limit: number) =>
+    $('div.comiis_wzli')
+        .slice(0, limit)
+        .toArray()
+        .map((item) => {
+            item = $(item);
+
+            const title = item.find('div.wzbt').text().trim();
+            const image = item.find('div.wzpic img').prop('src');
+            const description = art(path.join(__dirname, 'templates/description.art'), {
+                images: image
+                    ? [
+                          {
+                              src: image,
+                              alt: title,
+                          },
+                      ]
+                    : undefined,
+                description: item.find('div.wznr').html(),
+            });
+            const pubDate = item.find('div.subcat span.y').contents()?.eq(2)?.text().trim() ?? undefined;
+            const link = new URL(item.find('div.wzbt a').prop('href'), rootUrl).href;
+
+            return {
+                title,
+                description,
+                pubDate: pubDate ? parseDate(pubDate) : undefined,
+                link,
+                author: item.find('div.subcat span.y a').first().text(),
+                content: {
+                    html: description,
+                    text: item.find('div.wznr').text(),
+                },
+                image,
+                banner: image,
+            };
+        });
+
+/**
+ * Parses a list of posts based on a CheerioAPI object and a limit.
+ * @param $ The CheerioAPI object.
+ * @param limit The maximum number of posts to parse.
+ * @returns An array of parsed post objects.
+ */
+const parsePostList = ($: CheerioAPI, limit: number) =>
+    $('div.comiis_postlist')
+        .toArray()
+        .filter((item) => {
+            item = $(item);
+
+            return item
+                .find('span.comiis_common a[data-track]')
+                .toArray()
+                .some((a) => {
+                    a = $(a);
+
+                    const dataTrack = a.attr('data-track') || '';
+                    return dataTrack.endsWith('文章');
+                });
+        })
+        .slice(0, limit)
+        .map((item) => {
+            item = $(item);
+
+            const aEl = $(
+                item
+                    .find('span.comiis_common a[data-track]')
+                    .toArray()
+                    .find((a) => {
+                        a = $(a);
+
+                        const dataTrack = a.attr('data-track') || '';
+                        return dataTrack.endsWith('文章');
+                    })
+            );
+
+            const pubDate = item.find('span.author_b span').prop('title') || undefined;
+
+            return {
+                title: aEl.text().trim(),
+                pubDate: pubDate ? parseDate(pubDate) : undefined,
+                link: new URL(aEl.prop('href'), rootUrl).href,
+                author: item.find('a.author_t').text().trim(),
+            };
+        });
+
+/**
+ * Parses an article based on a CheerioAPI object and an item.
+ * @param $$ The CheerioAPI object.
+ * @param item The item to parse.
+ * @returns The parsed article object.
+ */
+const parseArticle = ($$: CheerioAPI, item) => {
+    const title = $$('h1.ph').text().trim();
+    const description = art(path.join(__dirname, 'templates/description.art'), {
+        intro: $$('div.s').text() || undefined,
+        description: $$('div#artMain').html(),
+    });
+    const pubDate =
+        $$('p.xg1')
+            .contents()
+            .first()
+            .text()
+            .trim()
+            ?.match(/(\d{4}-\d{1,2}-\d{1,2}\s\d{2}:\d{2})/)?.[1] ?? undefined;
+    const guid = `flyert-${item.link.split(/=/).pop()}`;
+
+    item.title = title;
+    item.description = description;
+    item.pubDate = pubDate ? timezone(parseDate(pubDate), +8) : item.pubDate;
+    item.author = $$('p.xg1 a').first().text();
+    item.guid = guid;
+    item.id = guid;
+    item.content = {
+        html: description,
+        text: $$('div#artMain').text(),
+    };
+
+    return item;
+};
+
+/**
+ * Parses a post based on a CheerioAPI object and an item.
+ * @param $$ The CheerioAPI object.
+ * @param item The item to parse.
+ * @returns The parsed post object.
+ */
+const parsePost = ($$: CheerioAPI, item) => {
+    $$('img.zoom').each((_, el) => {
+        el = $$(el);
+
+        el.replaceWith(
+            art(path.join(__dirname, 'templates/description.art'), {
+                images:
+                    el.prop('zoomfile') || el.prop('file')
+                        ? [
+                              {
+                                  src: el.prop('zoomfile') || el.prop('file'),
+                                  alt: el.prop('alt') || el.prop('title'),
+                              },
+                          ]
+                        : undefined,
+            })
+        );
+    });
+
+    $$('i.pstatus').remove();
+    $$('div.tip').remove();
+
+    const title = $$('span#thread_subject').text().trim();
+    const description = $$('div.post_message').first().html();
+    const pubDate = $$('span[title]').first().prop('title');
+
+    const tid = item.link.match(/tid=(\d+)/)?.[1] ?? undefined;
+    const guid = tid ? `flyert-${tid}` : undefined;
+
+    item.title = title;
+    item.description = description;
+    item.pubDate = pubDate ? timezone(parseDate(pubDate), +8) : item.pubDate;
+    item.author = $$('a.kmxi2').first().text();
+    item.guid = guid;
+    item.id = guid;
+    item.content = {
+        html: description,
+        text: $$('div.post_message').first().text(),
+    };
+
+    return item;
+};
+
+export { rootUrl, parseArticleList, parsePostList, parseArticle, parsePost };

package/lib/routes/follow/profile.ts

@@ -1,7 +1,7 @@
 import { ViewType, type Data, type Route } from '@/types';
 import type { Context } from 'hono';
 import ofetch from '@/utils/ofetch';
-import type { FollowResponse, InboxSubscription, ListSubscription, Profile, Subscription } from './types';
+import type { FeedSubscription, FollowResponse, InboxSubscription, ListSubscription, Profile, Subscription } from './types';
 import { parse } from 'tldts';
 
 export const route: Route = {
@@ -19,7 +19,7 @@ export const route: Route = {
         },
     ],
     handler,
-    maintainers: ['KarasuShin', 'DIYgod'],
+    maintainers: ['KarasuShin', 'DIYgod', 'DFobain'],
     features: {
         supportRadar: true,
     },
@@ -30,6 +30,8 @@ const isList = (subscription: Subscription): subscription is ListSubscription =>
 
 const isInbox = (subscription: Subscription): subscription is InboxSubscription => 'inboxId' in subscription;
 
+const isFeed = (subscription: Subscription): subscription is FeedSubscription => 'feeds' in subscription;
+
 async function handler(ctx: Context): Promise<Data> {
     const handleOrId = ctx.req.param('uid');
     const host = 'https://api.follow.is';
@@ -47,7 +49,7 @@ async function handler(ctx: Context): Promise<Data> {
 
     return {
         title: `${profile.data.name}'s subscriptions`,
-        item: (<Exclude<Subscription, InboxSubscription>[]>subscriptions.data.filter((i) => !isInbox(i))).map((subscription) => {
+        item: (<Exclude<Subscription, InboxSubscription>[]>subscriptions.data.filter((i) => !isInbox(i) && !(isFeed(i) && !!i.feeds.errorAt))).map((subscription) => {
             if (isList(subscription)) {
                 return {
                     title: subscription.lists.title,
@@ -64,7 +66,7 @@ async function handler(ctx: Context): Promise<Data> {
                 category: subscription.category ? [subscription.category] : undefined,
             };
         }),
-        link: `https://app.follow.is/share/user/${handleOrId}`,
+        link: `https://app.follow.is/share/users/${handleOrId}`,
         image: profile.data.image,
     };
 }

package/lib/routes/foodtalks/index.ts

@@ -0,0 +1,75 @@
+import { Route } from '@/types';
+import ofetch from '@/utils/ofetch';
+import cache from '@/utils/cache';
+import { namespace } from './namespace';
+import logger from '@/utils/logger';
+
+export const route: Route = {
+    path: '/',
+    categories: namespace.categories,
+    example: '/foodtalks',
+    radar: [
+        {
+            source: ['www.foodtalks.cn'],
+        },
+    ],
+    name: 'FoodTalks global food information network',
+    maintainers: ['Geraldxm'],
+    handler,
+    url: 'www.foodtalks.cn',
+};
+
+function processItems(list: any[], fullTextApi: string) {
+    return Promise.all(
+        list.map((item) =>
+            cache.tryGet(item.link, async () => {
+                try {
+                    const response = await ofetch(fullTextApi.replace('{id}', item.id), {
+                        headers: {
+                            referrer: 'https://www.foodtalks.cn/',
+                            method: 'GET',
+                        },
+                    });
+                    item.description = response.data.content;
+                    return item;
+                } catch (error) {
+                    logger.error(`Error fetching full text for ${item.link}:`, error);
+                    return item;
+                }
+            })
+        )
+    );
+}
+
+async function handler(ctx) {
+    const limit = ctx.req.query('limit') || 15;
+    const url = `https://api-we.foodtalks.cn/news/news/page?current=1&size=${limit}&isLatest=1&language=ZH`;
+    const response = await ofetch(url, {
+        headers: {
+            referrer: 'https://www.foodtalks.cn/',
+            method: 'GET',
+        },
+    });
+    const records = response.data.records;
+
+    const list = records.map((item) => ({
+        title: item.title,
+        pubDate: new Date(item.publishTime),
+        link: `https://www.foodtalks.cn/news/${item.id}`,
+        category: item.parentTagCode === 'category' ? item.tagCode : item.parentTagCode,
+        author: item.author === null ? item.sourceName : item.author,
+        id: item.id,
+        image: item.coverImg,
+    }));
+
+    const fullTextApi = 'https://api-we.foodtalks.cn/news/news/{id}?language=ZH';
+    const items = await processItems(list, fullTextApi);
+
+    return {
+        title: namespace.name,
+        description: namespace.description,
+        link: 'https://' + namespace.url,
+        item: items,
+        image: 'https://www.foodtalks.cn/static/img/news-site-logo.7aaa5463.svg',
+    };
+}

package/lib/routes/foodtalks/namespace.ts

@@ -0,0 +1,9 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: 'FoodTalks全球食品资讯网',
+    url: 'www.foodtalks.cn',
+    categories: ['new-media'],
+    lang: 'zh-CN',
+    description: 'FoodTalks全球食品资讯网是一个提供食品饮料行业新闻、资讯、分析和商业资源的领先在线平台。它涵盖行业趋势、市场动态、产品创新、投融资信息以及企业新闻，连接行业内的专业人士、企业和消费者。',
+};

package/lib/routes/foresightnews/article.ts

@@ -3,7 +3,7 @@ import { rootUrl, apiRootUrl, processItems, icon, image } from './util';
 
 export const route: Route = {
     path: '/article',
-    categories: ['new-media'],
+    categories: ['new-media', 'popular'],
     example: '/foresightnews/article',
     parameters: {},
     features: {

package/lib/routes/foresightnews/column.ts

@@ -3,7 +3,7 @@ import { rootUrl, apiRootUrl, processItems, icon, image } from './util';
 
 export const route: Route = {
     path: '/column/:id',
-    categories: ['new-media'],
+    categories: ['new-media', 'popular'],
     example: '/foresightnews/column/1',
     parameters: { id: '专栏 id, 可在对应专栏页 URL 中找到' },
     features: {

package/lib/routes/foresightnews/index.ts

@@ -3,13 +3,15 @@ import { rootUrl, apiRootUrl, processItems, icon, image } from './util';
 
 export const route: Route = {
     path: '/',
+    categories: ['new-media', 'popular'],
+    example: '/foresightnews',
     radar: [
         {
             source: ['foresightnews.pro/'],
             target: '',
         },
     ],
-    name: 'Unknown',
+    name: '精选资讯',
     maintainers: ['nczitzk'],
     handler,
     url: 'foresightnews.pro/',

package/lib/routes/foresightnews/news.ts

@@ -3,7 +3,7 @@ import { rootUrl, apiRootUrl, processItems, icon, image } from './util';
 
 export const route: Route = {
     path: '/news',
-    categories: ['new-media'],
+    categories: ['new-media', 'popular'],
     example: '/foresightnews/news',
     parameters: {},
     features: {

package/lib/routes/freebuf/index.ts

@@ -23,9 +23,9 @@ export const route: Route = {
     name: '文章',
     maintainers: ['trganda'],
     handler,
-    description: `:::tip
+    description: `::: tip
   Freebuf 的文章页面带有反爬虫机制，所以目前无法获取文章的完整内容。
-  :::`,
+:::`,
 };
 
 async function handler(ctx) {

package/lib/routes/freecomputerbooks/index.ts

@@ -8,7 +8,6 @@ import path from 'node:path';
 
 import got from '@/utils/got';
 import { art } from '@/utils/render';
-import { parseDate } from '@/utils/parse-date';
 
 const baseURL = 'https://freecomputerbooks.com/';
 
@@ -89,15 +88,6 @@ function buildPostItem(listItem, categoryTitle, cache) {
             : categoryTitle,
     };
 
-    const pubDateText = postInfo.find('span:last').text().replace(/^on /, '');
-    if (pubDateText) {
-        // Pretty much the same situation: Only a "Selected New Books" page has
-        // explicit publication dates for posts; even on each post's details
-        // page, there seems to be only the publication date for the book, but
-        // the post's creation date is still missing.
-        postItem.pubDate = parseDate(pubDateText);
-    }
-
     return cache.tryGet(postItem.link, () => insertDescriptionInto(postItem));
 }
 

package/lib/routes/ft/myft.ts

@@ -20,10 +20,10 @@ export const route: Route = {
     name: 'myFT personal RSS',
     maintainers: ['HenryQW'],
     handler,
-    description: `:::tip
+    description: `::: tip
   -   Visit ft.com -> myFT -> Contact Preferences to enable personal RSS feed, see [help.ft.com](https://help.ft.com/faq/email-alerts-and-contact-preferences/what-is-myft-rss-feed/)
   -   Obtain the key from the personal RSS address, it looks like \`12345678-abcd-4036-82db-vdv20db024b8\`
-  :::`,
+:::`,
 };
 
 async function handler(ctx) {

package/lib/routes/ftchinese/channel.ts

@@ -17,9 +17,9 @@ export const route: Route = {
     name: 'FT 中文网',
     maintainers: ['HenryQW', 'xyqfer'],
     handler,
-    description: `:::tip
+    description: `::: tip
   -   不支持付费文章。
-  :::
+:::
 
   通过提取文章全文，以提供比官方源更佳的阅读体验。
 

package/lib/routes/ftm/index.ts

@@ -7,7 +7,7 @@ import ofetch from '@/utils/ofetch';
 
 export const route: Route = {
     path: '/',
-    categories: ['new-media'],
+    categories: ['new-media', 'popular'],
     example: '/ftm',
     parameters: {},
     name: '文章',