fix(route): fix pianyuan, add pianyuan/search (#9721)

* fix route pianyuan, add route pianyuan/search

* update doc

* changes for reviews

* Update lib/routes/pianyuan/utils.js

Co-authored-by: Rongrong <Rongronggg9@outlook.com>

* changes for reviews

* refactor: migrate to v2

Co-authored-by: Rongrong <Rongronggg9@outlook.com>

assets/radar-rules.js

@@ -220,7 +220,6 @@
     'tw.manhuagui.com': { _name: '漫画柜台湾', www: [{ title: '漫画更新', docs: 'https://docs.rsshub.app/anime.html#kan-man-hua-tai-wan', source: '/comic/:id/', target: '/twmanhuagui/comic/:id' }] },
     'copymanga.com': { _name: '拷贝漫画', www: [{ title: '漫画更新', docs: 'https://docs.rsshub.app/anime.html#kao-bei-man-hua', source: '/comic/:id/', target: '/manhuagui/comic/:id/5' }] },
     'pgyer.com': { _name: '蒲公英应用分发', www: [{ title: 'app更新', docs: 'https://docs.rsshub.app/program-update.html#pu-gong-ying-ying-yong-fen-fa', source: '/:app', target: '/pgyer/:app' }] },
-    'pianyuan.la': { _name: '片源网', '.': [{ title: '电影和剧集', docs: 'https://docs.rsshub.app/multimedia.html#pian-yuan', source: '/' }] },
     'baidu.com': {
         _name: '贴吧',
         tieba: [

docs/install/README.md

@@ -664,6 +664,10 @@ RSSHub 支持使用访问密钥 / 码，白名单和黑名单三种方式进行
     -   `NHENTAI_USERNAME`: nhentai 用户名或邮箱
     -   `NHENTAI_PASSWORD`: nhentai 密码
 
+-   pianyuan 全部路由： [注册地址](https://pianyuan.org)
+
+    -   `PIANYUAN_COOKIE`: 对应 cookie 中的 `py_loginauth`, 例: PIANYUAN_COOKIE='py_loginauth=xxxxxxxxxx'
+
 -   pixiv 全部路由：[注册地址](https://accounts.pixiv.net/signup)
 
     -   `PIXIV_REFRESHTOKEN`: Pixiv Refresh Token, 请参考 [此文](https://gist.github.com/ZipFile/c9ebedb224406f4f11845ab700124362) 获取，或自行对客户端抓包获取

docs/multimedia.md

@@ -1262,7 +1262,17 @@ JavDB 有多个备用域名，本路由默认使用永久域名 <https://javdb.c
 
 ### 最新资源
 
-<Route author="greatcodeeer" example="/pianyuan" path="/pianyuan" radar="1" rssbud="1"/>
+<Route author="greatcodeeer jerry1119" example="/pianyuan/index" path="/pianyuan/index/:media?" :paramsDesc="['类别，见下表，默认为首页']" radar="1" rssbud="1" selfhost="1"/>
+
+| 电影 | 剧集 |
+| -- | -- |
+| mv | tv |
+
+### 搜索
+
+<Route author="jerry1119" example="/pianyuan/indexers/pianyuan/results/search/api?t=test&q=长津湖" path="/pianyuan/indexers/pianyuan/results/search/" selfhost="1"/>
+
+搜索路由模仿 jackett 的搜索 api, 以提供给 nastools 使用，填写在 nastools 配置 indexer 中
 
 ## 飘花电影网
 

lib/config.js

@@ -198,6 +198,9 @@ const calculateValue = () => {
             username: envs.NHENTAI_USERNAME,
             password: envs.NHENTAI_PASSWORD,
         },
+        pianyuan: {
+            cookie: envs.PIANYUAN_COOKIE,
+        },
         pixiv: {
             refreshToken: envs.PIXIV_REFRESHTOKEN,
             bypassCdn: envs.PIXIV_BYPASS_CDN !== '0' && envs.PIXIV_BYPASS_CDN !== 'false',

lib/radar-rules.js

@@ -466,16 +466,6 @@ module.exports = {
             },
         ],
     },
-    'pianyuan.la': {
-        _name: '片源网',
-        '.': [
-            {
-                title: '电影和剧集',
-                docs: 'https://docs.rsshub.app/multimedia.html#pian-yuan',
-                source: '/',
-            },
-        ],
-    },
     'baidu.com': {
         _name: '贴吧',
         tieba: [

lib/router.js

@@ -2271,8 +2271,9 @@ router.get('/chocolatey/software/:name?', lazyloadRouteHandler('./routes/chocola
 // Nyaa
 router.get('/nyaa/search/:query?', lazyloadRouteHandler('./routes/nyaa/search'));
 
-// 片源网
-router.get('/pianyuan/:media?', lazyloadRouteHandler('./routes/pianyuan/app'));
+// 片源网 migrated to v2
+// router.get('/pianyuan/index/:media?', lazyloadRouteHandler('./routes/pianyuan/app'));
+// router.get('/pianyuan/indexers/pianyuan/results/search/api', lazyloadRouteHandler('./routes/pianyuan/search'));
 
 // 巴哈姆特
 router.get('/bahamut/creation/:author/:category?', lazyloadRouteHandler('./routes/bahamut/creation'));

lib/routes/pianyuan/app.js

@@ -1,49 +0,0 @@
-const got = require('@/utils/got');
-const cheerio = require('cheerio');
-
-module.exports = async (ctx) => {
-    const media = ctx.params.media || -1;
-    const link_base = 'http://pianyuan.tv/';
-    let description = '电影和剧集';
-    let link = link_base;
-    if (media !== -1) {
-        link = link_base + `?cat=${media}`;
-        if (media === 'mv') {
-            description = '电影';
-        } else if (media === 'tv') {
-            description = '剧集';
-        } else {
-            link = link_base;
-        }
-    }
-
-    const response = await got.get(link);
-    const data = response.data;
-    const $ = cheerio.load(data);
-
-    const items = [];
-    $('#main-container > div > div.col-md-10 > table > tbody > tr').each((i, item) => {
-        const link = $(item).find('td.dt.prel.nobr > a').attr('href');
-        const text = $(item).find('td.dt.prel.nobr > a').text();
-        const description = $(item)
-            .find('td.dt.prel.nobr')
-            .text()
-            .replace(/^\s+|\s+$/g, '');
-        const size = $(item).find('td:nth-child(2)').text();
-
-        const description_simple = description.substr(0, description.indexOf('主演')).replace(text, '');
-
-        items.push({
-            title: `[${size}] ${description_simple}`,
-            description,
-            link: link_base + link,
-        });
-    });
-
-    ctx.state.data = {
-        title: `片源网`,
-        description,
-        link: link_base,
-        item: items,
-    };
-};

lib/v2/pianyuan/app.js

@@ -0,0 +1,34 @@
+const cheerio = require('cheerio');
+const utils = require('./utils');
+
+module.exports = async (ctx) => {
+    const media = ctx.params.media ?? -1;
+    const link_base = 'https://pianyuan.org/';
+    let description = '电影和剧集';
+    let link = link_base;
+    if (media !== -1) {
+        link = link_base + `?cat=${media}`;
+        if (media === 'mv') {
+            description = '电影';
+        } else if (media === 'tv') {
+            description = '剧集';
+        } else {
+            link = link_base;
+        }
+    }
+
+    const response = await utils.request(link, ctx.cache);
+    const $ = cheerio.load(response.data);
+    const detailLinks = $('#main-container > div > div.col-md-10 > table > tbody > tr')
+        .get()
+        .map((tr) => $(tr).find('td.dt.prel.nobr > a').attr('href'));
+    detailLinks.shift();
+    const items = await utils.ProcessFeed(detailLinks, ctx.cache);
+
+    ctx.state.data = {
+        title: '片源网',
+        description,
+        link: link_base,
+        item: items,
+    };
+};

lib/v2/pianyuan/maintainer.js

@@ -0,0 +1,4 @@
+module.exports = {
+    '/index/:media?': ['greatcodeeer', 'jerry1119'],
+    '/indexers/pianyuan/results/search/api': ['jerry1119'],
+};

lib/v2/pianyuan/radar.js

@@ -0,0 +1,13 @@
+module.exports = {
+    'pianyuan.org': {
+        _name: '片源网',
+        '.': [
+            {
+                title: '电影和剧集',
+                docs: 'https://docs.rsshub.app/multimedia.html#pian-yuan',
+                source: '/',
+                target: '/pianyuan/index',
+            },
+        ],
+    },
+};

lib/v2/pianyuan/router.js

@@ -0,0 +1,4 @@
+module.exports = (router) => {
+    router.get('/index/:media?', require('./app'));
+    router.get('/indexers/pianyuan/results/search/api', require('./search'));
+};

lib/v2/pianyuan/search.js

@@ -0,0 +1,45 @@
+const cheerio = require('cheerio');
+const utils = require('./utils');
+
+module.exports = async (ctx) => {
+    const link_base = 'https://pianyuan.org/';
+    const description = '搜索';
+    // 适配jackett 搜索api, eg: https://rsshub.app/pianyuan/indexers/pianyuan/results/search/api?t=test&q=halo
+    const searchKey = ctx.originalUrl.split('&q=')[1];
+    const link = link_base + `search?q=${searchKey}`;
+
+    const response = await utils.request(link, ctx.cache);
+    const $ = cheerio.load(response.data);
+    // 只获取第一页的搜索结果
+    const searchLinks = $('.nomt > a')
+        .get()
+        .map((a) => $(a).attr('href'));
+    if (searchLinks.length === 0) {
+        throw 'pianyuan 搜索失败';
+    }
+
+    const detailLinks = [];
+
+    await Promise.all(
+        searchLinks.map(async (e) => {
+            const link = new URL(e, link_base);
+            const single = await ctx.cache.tryGet(link, async () => {
+                const res = await utils.request(link, ctx.cache);
+                const content = cheerio.load(res.data);
+                content('.ico.ico_bt')
+                    .get()
+                    .map((a) => detailLinks.push($(a).attr('href')));
+            });
+            return single;
+        })
+    );
+
+    const items = await utils.ProcessFeed(detailLinks, ctx.cache);
+
+    ctx.state.data = {
+        title: '片源网',
+        description,
+        link: link_base,
+        item: items,
+    };
+};

lib/v2/pianyuan/utils.js

@@ -0,0 +1,88 @@
+const cheerio = require('cheerio');
+const got = require('@/utils/got');
+const config = require('@/config').value;
+const security_key = 'pianyuan-security_session_verify';
+const PHPSESSID_key = 'pianyuan-PHPSESSID';
+const loginauth_key = 'pianyuan-py_loginauth';
+
+const ProcessFeed = async (list, cache) => {
+    const link_base = 'https://pianyuan.org';
+
+    const items = await Promise.all(
+        list.map(async (e) => {
+            const link = new URL(e, link_base);
+            const single = await cache.tryGet(link, async () => {
+                const response = await request(link, cache);
+                const content = cheerio.load(response.data);
+                const magnet = content('.btn-primary').attr('href');
+                const torrent_name = content('body > div.jumbotron.masthead > div > div > div.col-sm-10.col-md-10.col-lg-10.text-left > h1').text();
+                const name = content('body > div.jumbotron.masthead > div > div > div.col-sm-10.col-md-10.col-lg-10.text-left > h2 > a').text();
+                const size = content('#main-container > div > div.col-sm-10.col-md-8.col-lg-8 > div > ul > li:nth-child(2)').text();
+                let length;
+                if (size.includes('MB')) {
+                    length = size.replace('MB', '') * 1024;
+                } else if (size.includes('GB')) {
+                    length = size.replace('GB', '') * 1024 * 1024;
+                }
+                // const description ='';
+
+                return {
+                    title: `${torrent_name} [${name}] [${size}]`,
+                    size: length,
+                    enclosure_url: magnet,
+                    enclosure_type: 'application/x-bittorrent',
+                    enclosure_length: length,
+                };
+            });
+            return single;
+        })
+    );
+
+    return items;
+};
+
+async function getCookie(cache) {
+    const security_session_verify = await cache.get(security_key);
+    const PHPSESSID = await cache.get(PHPSESSID_key);
+    let py_loginauth = await cache.get(loginauth_key);
+    if (!py_loginauth) {
+        if (!config.pianyuan || !config.pianyuan.cookie) {
+            throw 'pianyuan is disabled due to the lack of <a href="https://docs.rsshub.app/install/#pei-zhi-bu-fen-rss-mo-kuai-pei-zhi">relevant config</a>';
+        }
+        py_loginauth = config.pianyuan.cookie;
+    }
+    return `${py_loginauth};${security_session_verify};${PHPSESSID};`;
+}
+
+async function request(link, cache) {
+    const cookie = await getCookie(cache);
+    const response = await got({
+        method: 'get',
+        url: link,
+        headers: {
+            Cookie: cookie,
+        },
+    });
+    // set cookie
+    const set_cookie = response.headers['set-cookie'];
+    if (set_cookie) {
+        for (const e of set_cookie) {
+            if (e.indexOf('security_session_verify') === 0) {
+                cache.set(security_key, e.split(';')[0]);
+            } else if (e.indexOf('PHPSESSID') === 0) {
+                cache.set(PHPSESSID_key, e.split(';')[0]);
+            } else if (e.indexOf('py_loginauth') === 0) {
+                cache.set(loginauth_key, e.split(';')[0]);
+            }
+        }
+    }
+    if (response.data.includes('会员登录后才能访问')) {
+        throw 'pianyuan Cookie已失效';
+    }
+    return response;
+}
+
+module.exports = {
+    ProcessFeed,
+    request,
+};