feat(route): add 飞客会员说 (DIYgod#17441)

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)}` : ''}`;
+            },
+        },
+    ],
+};

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',
 };

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 }}

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 };