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

package/lib/routes/51read/article.ts

@@ -0,0 +1,82 @@
+import { load } from 'cheerio';
+import cache from '@/utils/cache';
+import ofetch from '@/utils/ofetch';
+import type { Route, DataItem } from '@/types';
+
+export const route: Route = {
+    path: '/article/:id',
+    name: '章节',
+    url: 'm.51read.org',
+    maintainers: ['lazwa34'],
+    example: '/51read/article/152685',
+    parameters: { id: '小说 id, 可在对应小说页 URL 中找到' },
+    categories: ['reading'],
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['m.51read.org/xiaoshuo/:id'],
+            target: '/article/:id',
+        },
+        {
+            source: ['51read.org/xiaoshuo/:id'],
+            target: '/article/:id',
+        },
+    ],
+    handler,
+};
+
+async function handler(ctx) {
+    const { id } = ctx.req.param();
+    const link = `https://m.51read.org/xiaoshuo/${id}`;
+    const $book = load(await ofetch(link));
+
+    const chapter = `https://m.51read.org/zhangjiemulu/${id}`;
+    const $chapter = load(await ofetch(chapter));
+
+    const pageLength = $chapter('.ml-page select')
+        .find('option')
+        .map((_, option) => option.attribs.value)
+        .toArray().length;
+
+    const item = await createItem(chapter, pageLength);
+
+    return {
+        title: $book('h1').text(),
+        description: $book('.bi-cot p').text(),
+        link,
+        item,
+        image: $book('.bi-img img').attr('src'),
+        author: $book('.bi-wt a').text(),
+        language: 'zh-cn',
+    };
+}
+
+const createItem = async (baseUrl: string, page: number) => {
+    const url = `${baseUrl}/${page}`;
+    const $latest = load(await ofetch(url));
+    const item = await Promise.all(
+        $latest('.kb-jp li>a')
+            .map((_, chapter) => buildItem(chapter.attribs.href))
+            .toArray()
+            .toReversed()
+    );
+    return item;
+};
+
+const buildItem = (url: string) =>
+    cache.tryGet(url, async () => {
+        const $ = load(await ofetch(url));
+
+        return {
+            title: $('h1').text(),
+            description: $('.kb-cot').html() || '',
+            link: url,
+        };
+    }) as Promise<DataItem>;

package/lib/routes/{thecatcity → 51read}/namespace.ts

@@ -1,6 +1,6 @@
 import type { Namespace } from '@/types';
 
 export const namespace: Namespace = {
-    name: '貓奴日常',
-    url: 'thecatcity.com',
+    name: '51Read',
+    url: 'm.51read.org',
 };

package/lib/routes/5eplay/utils.ts

@@ -13,10 +13,12 @@ const getAcwScV2ByArg1 = (arg1) => {
         }
         return res;
     };
-    const unsbox = function (str) {
+    const unsbox = function (str: string) {
         const code = [15, 35, 29, 24, 33, 16, 1, 38, 10, 9, 19, 31, 40, 27, 22, 23, 25, 13, 6, 11, 39, 18, 20, 8, 14, 21, 32, 26, 2, 30, 7, 4, 17, 5, 3, 28, 34, 37, 12, 36];
-        const res = [];
-        for (const [i, cur] of str.entries()) {
+        const res: string[] = [];
+        // eslint-disable-next-line unicorn/no-for-loop
+        for (let i = 0; i < str.length; i++) {
+            const cur = str[i];
             for (const [j, element] of code.entries()) {
                 if (element === i + 1) {
                     res[j] = cur;

package/lib/routes/69shu/article.ts

@@ -0,0 +1,96 @@
+import { load } from 'cheerio';
+import cache from '@/utils/cache';
+import ofetch from '@/utils/ofetch';
+import type { Route, DataItem } from '@/types';
+
+export const route: Route = {
+    path: '/article/:id',
+    name: '章节',
+    url: 'www.69shuba.pro',
+    maintainers: ['eternasuno'],
+    example: '/69shu/article/47117',
+    parameters: { id: '小说 id, 可在对应小说页 URL 中找到' },
+    categories: ['reading'],
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['www.69shuba.pro/book/:id.htm'],
+            target: '/article/:id',
+        },
+    ],
+    handler: async (ctx) => {
+        const { id } = ctx.req.param();
+        const link = `https://www.69shuba.pro/book/${id}.htm`;
+        const $ = load(await get(link));
+
+        const item = await Promise.all(
+            $('.qustime li>a')
+                .map((_, chapter) => createItem(chapter.attribs.href))
+                .toArray()
+        );
+
+        return {
+            title: $('h1>a').text(),
+            description: $('.navtxt>p:first-of-type').text(),
+            link,
+            item,
+            image: $('.bookimg2>img').attr('src'),
+            author: $('.booknav2>p:first-of-type>a').text(),
+            language: 'zh-cn',
+        };
+    },
+};
+
+const createItem = (url: string) =>
+    cache.tryGet(url, async () => {
+        const $ = load(await get(url));
+        const { articleid, chapterid, chaptername } = parseObject(/bookinfo\s?=\s?{[\S\s]+?}/, $('head>script:not([src])').text());
+        const decryptionMap = parseObject(/_\d+\s?=\s?{[\S\s]+?}/, $('.txtnav+script').text());
+
+        return {
+            title: chaptername,
+            description: decrypt($('.txtnav').html() || '', articleid, chapterid, decryptionMap),
+            link: url,
+        };
+    }) as Promise<DataItem>;
+
+const get = async (url: string, encoding = 'gbk') => new TextDecoder(encoding).decode(await ofetch(url, { responseType: 'arrayBuffer' }));
+
+const parseObject = (reg: RegExp, str: string): Record<string, string> => {
+    const obj = {};
+    const match = reg.exec(str);
+    if (match) {
+        for (const line of match[0].matchAll(/(\w+):\s?["']?([\S\s]+?)["']?[\n,}]/g)) {
+            obj[line[1]] = line[2];
+        }
+    }
+
+    return obj;
+};
+
+const decrypt = (txt: string, articleid: string, chapterid: string, decryptionMap: Record<string, string>) => {
+    if (!txt || txt.length < 10) {
+        return txt;
+    }
+
+    const lineMap = {};
+    const articleKey = Number(articleid) + 3_061_711;
+    const chapterKey = Number(chapterid) + 3_421_001;
+    for (const key of Object.keys(decryptionMap)) {
+        lineMap[(Number(key) ^ chapterKey) - articleKey] = (Number(decryptionMap[key]) ^ chapterKey) - articleKey;
+    }
+
+    return txt
+        .replaceAll(/\u2003|\n/g, '')
+        .split('<br><br>')
+        .flatMap((line, index, array) => (lineMap[index] ? array[lineMap[index]] : line).split('<br>'))
+        .slice(1, -2)
+        .join('<br><br>');
+};

package/lib/routes/{arknights → 69shu}/namespace.ts

@@ -1,6 +1,6 @@
 import type { Namespace } from '@/types';
 
 export const namespace: Namespace = {
-    name: '明日方舟',
-    url: 'ak.arknights.jp',
+    name: '69书吧',
+    url: '69shuba.pro',
 };

package/lib/routes/6v123/latest-movies.ts

@@ -28,7 +28,7 @@ export const route: Route = {
 };
 
 async function handler(ctx) {
-    const item = await processItems(ctx, baseURL);
+    const item = await processItems(ctx, baseURL, [/第*集/, /第*季/, /(ep)\d+/i, /(s)\d+/i, /更新/]);
 
     return {
         title: '6v电影-最新电影',

package/lib/routes/6v123/latest-tvseries.ts

@@ -28,7 +28,7 @@ export const route: Route = {
 };
 
 async function handler(ctx) {
-    const item = await processItems(ctx, baseURL);
+    const item = await processItems(ctx, baseURL, []);
 
     return {
         title: '6v电影-最新电影',

package/lib/routes/6v123/utils.ts

@@ -5,80 +5,82 @@ import { load } from 'cheerio';
 import timezone from '@/utils/timezone';
 import { parseDate } from '@/utils/parse-date';
 
-const utils = {
-    loadDetailPage: async function loadDetailPage(link) {
-        const response = await got.get(link, {
-            responseType: 'buffer',
-        });
-        response.data = iconv.decode(response.data, 'gb2312');
+export async function loadDetailPage(link) {
+    const response = await got.get(link, {
+        responseType: 'buffer',
+    });
+    response.data = iconv.decode(response.data, 'gb2312');
 
-        const $ = load(response.data);
+    const $ = load(response.data);
 
-        const detailInfo = {
-            title: $('title')
-                .text()
-                .replaceAll(/，免费下载，迅雷下载|，6v电影/g, ''),
-            description: $('meta[name="description"]').attr('content'),
-            enclosure_urls: $('table td')
-                .map((i, e) => ({
-                    title: $(e).text().replace('磁力：', ''),
-                    magnet: $(e).find('a').attr('href'),
-                }))
-                .toArray()
-                .filter((item) => item.magnet?.includes('magnet')),
-        };
-        return detailInfo;
-    },
-    processItems: async (ctx, baseURL) => {
-        const response = await got.get(baseURL, {
-            responseType: 'buffer',
-        });
-        response.data = iconv.decode(response.data, 'gb2312');
+    return {
+        title: $('title')
+            .text()
+            .replaceAll(/，免费下载，迅雷下载|，6v电影/g, ''),
+        description: $('meta[name="description"]').attr('content'),
+        enclosure_urls: $('table td')
+            .map((i, e) => ({
+                title: $(e).text().replace('磁力：', ''),
+                magnet: $(e).find('a').attr('href'),
+            }))
+            .toArray()
+            .filter((item) => item.magnet?.includes('magnet')),
+    };
+}
 
-        const $ = load(response.data);
-        const list = $('ul.list')[0].children;
+export async function processItems(ctx, baseURL, exclude) {
+    const response = await got.get(baseURL, {
+        responseType: 'buffer',
+    });
+    response.data = iconv.decode(response.data, 'gb2312');
 
-        const process = await Promise.all(
-            list.map((item) => {
-                const link = $(item).find('a');
-                const href = link.attr('href');
-                const pubDate = timezone(parseDate($(item).find('span').text().replaceAll(/[[\]]/g, ''), 'MM-DD'), +8);
+    const $ = load(response.data);
+    const list = $('ul.list')[0].children;
 
-                if (href === undefined) {
-                    return;
-                }
+    const process = await Promise.all(
+        list.map((item) => {
+            const link = $(item).find('a');
+            const href = link.attr('href');
+            const pubDate = timezone(parseDate($(item).find('span').text().replaceAll(/[[\]]/g, ''), 'MM-DD'), +8);
+            const text = link.text();
+
+            if (href === undefined) {
+                return;
+            }
 
-                const itemUrl = 'https://www.hao6v.cc' + link.attr('href');
+            if (exclude && exclude.some((e) => e.test(text))) {
+                // 过滤掉满足正则的标题条目
+                return;
+            }
 
-                return cache.tryGet(itemUrl, async () => {
-                    const detailInfo = await utils.loadDetailPage(itemUrl);
+            const itemUrl = 'https://www.hao6v.cc' + link.attr('href');
 
-                    if (detailInfo.enclosure_urls.length > 1) {
-                        return detailInfo.enclosure_urls.map((url) => ({
-                            enclosure_url: url.magnet,
-                            enclosure_type: 'application/x-bittorrent',
-                            title: `${link.text()} ( ${url.title} )`,
-                            description: detailInfo.description,
-                            pubDate,
-                            link: itemUrl,
-                            guid: `${itemUrl}#${url.title}`,
-                        }));
-                    }
+            return cache.tryGet(itemUrl, async () => {
+                const detailInfo = await loadDetailPage(itemUrl);
 
-                    return {
-                        enclosure_url: detailInfo.enclosure_urls.length === 0 ? '' : detailInfo.enclosure_urls[0].magnet,
+                if (detailInfo.enclosure_urls.length > 1) {
+                    return detailInfo.enclosure_urls.map((url) => ({
+                        enclosure_url: url.magnet,
                         enclosure_type: 'application/x-bittorrent',
-                        title: link.text(),
+                        title: `${link.text()} ( ${url.title} )`,
                         description: detailInfo.description,
                         pubDate,
                         link: itemUrl,
-                    };
-                });
-            })
-        );
+                        guid: `${itemUrl}#${url.title}`,
+                    }));
+                }
 
-        return process.filter((item) => item !== undefined).flat();
-    },
-};
+                return {
+                    enclosure_url: detailInfo.enclosure_urls.length === 0 ? '' : detailInfo.enclosure_urls[0].magnet,
+                    enclosure_type: 'application/x-bittorrent',
+                    title: link.text(),
+                    description: detailInfo.description,
+                    pubDate,
+                    link: itemUrl,
+                };
+            });
+        })
+    );
 
-export default utils;
+    return process.filter((item) => item !== undefined).flat();
+}

package/lib/routes/81/81rc/index.ts

@@ -1,41 +1,35 @@
 import { Route } from '@/types';
-import { getSubPath } from '@/utils/common-utils';
+
 import cache from '@/utils/cache';
 import got from '@/utils/got';
 import { load } from 'cheerio';
 import timezone from '@/utils/timezone';
 import { parseDate } from '@/utils/parse-date';
 
-export const route: Route = {
-    path: '/81rc/*',
-    name: 'Unknown',
-    maintainers: [],
-    handler,
-};
-
-async function handler(ctx) {
-    const thePath = getSubPath(ctx).replace(/^\/81rc/, '');
+export const handler = async (ctx) => {
+    const { category = 'sy/gzdt_210283' } = ctx.req.param();
     const limit = ctx.req.query('limit') ? Number.parseInt(ctx.req.query('limit'), 10) : 30;
 
     const rootUrl = 'https://81rc.81.cn';
-
-    // The default is http://81rc.81.cn/sy/gzdt_210283.
-    const currentUrl = new URL(thePath || '/sy/gzdt_210283', rootUrl).href;
+    const currentUrl = new URL(category?.endsWith('/') ? `${category}/` : category, rootUrl).href;
 
     const { data: response } = await got(currentUrl);
 
     const $ = load(response);
 
-    let items = $('div.left-news ul li a')
+    const language = $('html').prop('lang');
+
+    let items = $('div.left-news ul li')
         .slice(0, limit)
         .toArray()
         .map((item) => {
             item = $(item);
 
             return {
-                title: item.text(),
-                link: new URL(item.prop('href'), rootUrl).href,
-                pubDate: timezone(parseDate(item.parent().find('span').text()), +8),
+                title: item.find('a').text(),
+                pubDate: timezone(parseDate(item.find('span').text()), +8),
+                link: item.find('a').prop('href'),
+                language,
             };
         });
 
@@ -44,29 +38,71 @@ async function handler(ctx) {
             cache.tryGet(item.link, async () => {
                 const { data: detailResponse } = await got(item.link);
 
-                const content = load(detailResponse);
+                const $$ = load(detailResponse);
 
-                item.description = content('.txt').html();
-                item.author = content('meta[name="reporter"]').prop('content') || content('meta[name="author"]').prop('content');
+                const description = $$('div.txt').html();
+
+                item.title = $$('h2').text();
+                item.description = description;
+                item.pubDate = timezone(parseDate($$('div.time span').last().text()), +8);
+                item.author = $$('div.time span').first().text();
+                item.content = {
+                    html: description,
+                    text: $$('div.txt').text(),
+                };
+                item.language = language;
 
                 return item;
             })
         )
     );
 
-    const icon = $('link[rel="icon"]').prop('href');
+    const title = $('title').text();
+    const image = new URL('template/tenant207/t582/new.jpg', rootUrl).href;
 
     return {
-        item: items,
-        title: `军队人才网 - ${$('div.left-word')
-            .find('a')
-            .toArray()
-            .map((a) => $(a).text())
-            .filter((a) => a !== '首页')
-            .join(' - ')}`,
+        title,
+        description: $('div.time').contents().first().text(),
         link: currentUrl,
-        language: 'zh-cn',
-        icon,
-        logo: icon,
+        item: items,
+        allowEmpty: true,
+        image,
+        author: title.split(/-/).pop()?.trim(),
+        language,
     };
-}
+};
+
+export const route: Route = {
+    path: '/81rc/:category{.+}?',
+    name: '中国人民解放军专业技术人才网',
+    url: '81rc.81.cn',
+    maintainers: ['nczitzk'],
+    handler,
+    example: '/81/81rc/sy/gzdt_210283',
+    parameters: { category: '分类，默认为 `sy/gzdt_210283`，即工作动态，可在对应分类页 URL 中找到' },
+    description: `:::tip
+  若订阅 [工作动态](https://81rc.81.cn/sy/gzdt_210283)，网址为 \`https://81rc.81.cn/sy/gzdt_210283\`。截取 \`https://81rc.81.cn/\` 到末尾的部分 \`sy/gzdt_210283\` 作为参数填入，此时路由为 [\`/81/81rc/sy/gzdt_210283\`](https://rsshub.app/81/81rc/sy/gzdt_210283)。
+  :::
+  `,
+    categories: ['government'],
+
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportRadar: true,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['81rc.81.cn/:category'],
+            target: (params) => {
+                const category = params.category;
+
+                return `/81/81rc/${category ? `/${category}` : ''}`;
+            },
+        },
+    ],
+};

package/lib/routes/81/namespace.ts

@@ -2,5 +2,7 @@ import type { Namespace } from '@/types';
 
 export const namespace: Namespace = {
     name: '中国军网',
-    url: '81rc.81.cn',
+    url: '81.cn',
+    categories: ['government'],
+    description: '',
 };

package/lib/routes/95mm/utils.ts

@@ -45,7 +45,7 @@ const ProcessItems = async (ctx, title, currentUrl) => {
                 const images = detailResponse.data.match(/src": '(.*?)',"width/g);
 
                 item.description = art(path.join(__dirname, 'templates/description.art'), {
-                    images: images.map((i) => i.split("'")[1].replaceAll('\\/', '/')),
+                    images: images.map((i) => i.split("'")[1].replaceAll(String.raw`\/`, '/')),
                 });
 
                 return item;

package/lib/routes/abc/index.ts

@@ -82,8 +82,8 @@ async function handler(ctx) {
             }),
             author: i.newsBylineProps?.authors?.map((a) => a.name).join('/') ?? undefined,
             guid: `abc-${i.id}`,
-            pubDate: parseDate(i.timestamp.dates.firstPublished),
-            updated: i.timestamp.dates.lastUpdated ? parseDate(i.timestamp.dates.lastUpdated) : undefined,
+            pubDate: parseDate(i.dates.firstPublished),
+            updated: i.dates.lastUpdated ? parseDate(i.dates.lastUpdated) : undefined,
         };
 
         if (i.mediaIndicator) {
@@ -126,7 +126,7 @@ async function handler(ctx) {
                     item.title = content('meta[property="og:title"]').prop('content');
                     item.description = '';
 
-                    const enclosurePattern = '"(?:MIME|content)?Type":"([\\w]+/[\\w]+)".*?"(?:fileS|s)?ize":(\\d+),.*?"url":"([\\w-.:/?]+)"';
+                    const enclosurePattern = String.raw`"(?:MIME|content)?Type":"([\w]+/[\w]+)".*?"(?:fileS|s)?ize":(\d+),.*?"url":"([\w-.:/?]+)"`;
 
                     const enclosureMatches = detailResponse.match(new RegExp(enclosurePattern, 'g'));
 

package/lib/routes/academia/namespace.ts

@@ -0,0 +1,6 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: 'Academia',
+    url: 'www.academia.edu',
+};

package/lib/routes/academia/topics.ts

@@ -0,0 +1,49 @@
+import { Route } from '@/types';
+import ofetch from '@/utils/ofetch';
+import { load } from 'cheerio';
+
+export const route: Route = {
+    path: '/topic/:interest',
+    example: '/academia/topic/Urban_History',
+    parameters: { interest: 'interest' },
+    radar: [
+        {
+            source: ['academia.edu/Documents/in/:interest'],
+            target: '/topic/:interest',
+        },
+    ],
+    name: 'interest',
+    maintainers: ['K33k0'],
+    categories: ['journal'],
+    handler,
+    url: 'academia.edu',
+};
+
+async function handler(ctx) {
+    const interest = ctx.req.param('interest');
+    const response = await ofetch(`https://www.academia.edu/Documents/in/${interest}/MostRecent`);
+    const $ = load(response);
+    const list = $('.works > .u-borderBottom1')
+        .toArray()
+        .map((item) => {
+            const tagsElem = $(item).find('li.InlineList-item.u-positionRelative > span > script').text().replaceAll('}{', '},{');
+            let categories = [];
+            if (tagsElem !== null) {
+                const categoriesJSON = JSON.parse(`[${tagsElem}]`);
+                categories = categoriesJSON.map((category) => category.name);
+            }
+
+            return {
+                title: $(item).find('.header .title').text(),
+                link: $(item).find('.header .title > a').attr('href'),
+                author: $(item).find('span[itemprop=author] > a').text(),
+                description: $(item).find('.complete').text(),
+                category: categories,
+            };
+        });
+    return {
+        title: `academia.edu | ${interest} documents`,
+        link: `https://academia.edu/Documents/in/${interest}/MostRecent`,
+        item: list,
+    };
+}