rsshub 1.0.0-master.f7cdf8b → 1.0.0-master.f7f8b7a

package/lib/v2/google/alerts.js

@@ -0,0 +1,33 @@
+const got = require('@/utils/got');
+const cheerio = require('cheerio');
+
+module.exports = async (ctx) => {
+    const { keyword } = ctx.params;
+
+    const { data: response, url: link } = await got('https://www.google.com/alerts/preview', {
+        searchParams: {
+            params: `[null,[null,null,null,[null,"${keyword}","com",[null,"en","US"],null,null,null,0,0],null,3,[[null,1,"user@example.com",[null,null,20],2,"en-US",null,null,null,null,null,"0",null,null,"AB2Xq4hcilCERh73EFWJVHXx-io2lhh1EhC8UD8"]]],0]`,
+        },
+    });
+
+    const $ = cheerio.load(response, null, false);
+
+    const items = $('li.result')
+        .toArray()
+        .map((item) => {
+            item = $(item);
+            const title = item.find('.result_title a');
+            return {
+                title: title.text(),
+                link: new URL(title.attr('href')).searchParams.get('url'),
+                author: item.find('.result_source').text(),
+                description: item.find('.snippet').html(),
+            };
+        });
+
+    ctx.state.data = {
+        title: `Google Alerts - ${keyword}`,
+        link,
+        item: items,
+    };
+};

package/lib/v2/google/maintainer.js

@@ -1,5 +1,6 @@
 module.exports = {
     '/album/:id': ['hoilc'],
+    '/alerts/:keyword': ['TonyRL'],
     '/citations/:id': ['KellyHwong'],
     '/doodles/:language?': ['xyqfer'],
     '/fonts/:sort?': ['Fatpandac'],

package/lib/v2/google/router.js

@@ -1,5 +1,6 @@
 module.exports = function (router) {
     router.get('/album/:id', require('./album'));
+    router.get('/alerts/:keyword', require('./alerts'));
     router.get('/citations/:id', require('./citations'));
     router.get('/doodles/:language?', require('./doodles'));
     router.get('/fonts/:sort?', require('./fonts'));

package/lib/v2/gov/maintainer.js

@@ -29,12 +29,16 @@ module.exports = {
     '/miit/zcwj': ['Yoge-Code'],
     '/miit/wjgs': ['Yoge-Code'],
     '/miit/zcjd': ['Yoge-Code'],
+    '/moa/zdscxx/:channel?/:source?': ['MisteryMonster', 'nczitzk'],
+    '/moa/:suburl': ['Origami404'],
     '/moe/:type': ['Crawler995'],
     '/moe/s78/:column': ['TonyRL'],
     '/mofcom/article/:suffix+': ['LogicJake'],
     '/moj/aac/news/:type?': ['TonyRL'],
+    '/mot/:category?': ['nczitzk'],
+    '/nea/sjzz/ghs': ['nczitzk'],
     '/news/:uid': ['EsuRt'],
-    '/nifdc/:path+': ['nczitzk'],
+    '/nifdc/:path?': ['nczitzk'],
     '/nmpa/:path+': ['TonyRL'],
     '/nopss/:path+': ['nczitzk'],
     '/npc/:caty': ['233yeee'],
@@ -46,12 +50,15 @@ module.exports = {
     '/pbc/tradeAnnouncement': ['nczitzk'],
     '/pbc/zcyj': ['Fatpandac'],
     '/samr/xgzlyhd/:category?/:department?': ['nczitzk'],
+    '/safe/bussiness/:site?': ['nczitzk'],
+    '/safe/complaint/:site?': ['nczitzk'],
     '/sasac/:path+': ['TonyRL'],
     '/stats/:path+': ['bigfei', 'nczitzk'],
     '/zhengce/govall/:advance?': ['ciaranchen'],
     '/zhengce/wenjian/:pcodeJiguan?': ['ciaranchen'],
     '/zhengce/zhengceku/:department': ['zxx-457'],
-    '/zhengce/zuixin': ['SettingDust'],
+    '/zhengce/zuixin': ['SettingDust', 'nczitzk'],
+    '/zhengce/:category?': ['nczitzk'],
     // province
     '/anhui/kjt/:path?': ['nczitzk'],
     '/beijing/bphc/:channel': ['bigfei'],

package/lib/v2/gov/moa/zdscxx.js

@@ -0,0 +1,104 @@
+const got = require('@/utils/got');
+const cheerio = require('cheerio');
+const { parseDate } = require('@/utils/parse-date');
+
+module.exports = async (ctx) => {
+    const { category } = ctx.params;
+    const limit = ctx.query.limit ? parseInt(ctx.query.limit, 10) : 5;
+
+    const domain = 'moa.gov.cn';
+    const rootFrameUrl = `http://www.${domain}`;
+    const rootUrl = `http://zdscxx.${domain}:8080`;
+    const apiUrl = new URL('nyb/getMessages', rootUrl).href;
+    const apiDetailUrl = new URL('nyb/getMessagesById', rootUrl).href;
+    const currentUrl = new URL('nyb/pc/messageList.jsp', rootUrl).href;
+    const frameUrl = new URL('iframe/top_sj/', rootFrameUrl).href;
+
+    let filterForm = {};
+
+    if (category) {
+        const apiFilterUrl = new URL('nyb/getMessageFilters', rootUrl).href;
+
+        const { data: filterResponse } = await got.post(apiFilterUrl, {
+            form: {
+                type: '',
+                isLatestMessage: false,
+            },
+        });
+
+        const filters = filterResponse.result.reduce((filters, f) => {
+            filters[f.name] = f.data.map((d) => d.name);
+            return filters;
+        }, {});
+
+        filterForm = category.split(/\//).reduce((form, c) => {
+            Object.keys(filters)
+                .filter((key) => filters[key].includes(c))
+                .forEach((key) => {
+                    form[key] = c;
+                });
+            return form;
+        }, {});
+    }
+
+    const { data: response } = await got.post(apiUrl, {
+        form: {
+            page: 1,
+            rows: limit,
+            type: '',
+            isLatestMessage: false,
+            ...filterForm,
+        },
+    });
+
+    let items = response.result.table.slice(0, limit).map((item) => ({
+        title: item.title,
+        link: item.id,
+        guid: `moa-zdscxx-${item.id}`,
+        pubDate: parseDate(item.date),
+    }));
+
+    items = await Promise.all(
+        items.map((item) =>
+            ctx.cache.tryGet(item.guid, async () => {
+                const { data: detailResponse } = await got.post(apiDetailUrl, {
+                    form: {
+                        id: item.link,
+                    },
+                });
+
+                const data = detailResponse.result;
+
+                item.title = data.title;
+                item.link = new URL(`nyb/pc/messageView.jsp?id=${item.link}`, rootUrl).href;
+                item.description = data.content;
+                item.author = data.source;
+                item.pubDate = parseDate(data.date);
+
+                return item;
+            })
+        )
+    );
+
+    const { data: frameResponse } = await got(frameUrl);
+
+    const $ = cheerio.load(frameResponse);
+
+    const title = $('title').text();
+    const description = '数据';
+    const icon = new URL('favicon.ico', rootUrl).href;
+
+    ctx.state.data = {
+        item: items,
+        title: `${title} - ${description} - ${category}`,
+        link: currentUrl,
+        description,
+        language: 'zh',
+        image: $('h1.logo a img').prop('src'),
+        icon,
+        logo: icon,
+        subtitle: category,
+        author: title,
+        allowEmpty: true,
+    };
+};

package/lib/v2/gov/mot/index.js

@@ -0,0 +1,66 @@
+const got = require('@/utils/got');
+const cheerio = require('cheerio');
+const timezone = require('@/utils/timezone');
+const { parseDate } = require('@/utils/parse-date');
+
+module.exports = async (ctx) => {
+    const { category = 'tongjishuju/gonglu' } = ctx.params;
+    const limit = ctx.query.limit ? parseInt(ctx.query.limit, 10) : 30;
+
+    const rootUrl = 'https://www.mot.gov.cn';
+    const currentUrl = new URL(`${category}/`, rootUrl).href;
+
+    const { data: response } = await got(currentUrl);
+
+    const $ = cheerio.load(response);
+
+    let items = $('div.tab-pane a[title]')
+        .slice(0, limit)
+        .toArray()
+        .map((item) => {
+            item = $(item);
+
+            const link = item.prop('href');
+
+            return {
+                title: item.prop('title'),
+                link: link.startsWith('http') ? link : new URL(item.prop('href'), currentUrl).href,
+                pubDate: parseDate(item.find('span.badge').text()),
+            };
+        });
+
+    items = await Promise.all(
+        items.map((item) =>
+            ctx.cache.tryGet(item.link, async () => {
+                if (/\.gov\.cn/.test(item.link) && item.link.endsWith('.html')) {
+                    const { data: detailResponse } = await got(item.link);
+
+                    const content = cheerio.load(detailResponse);
+
+                    item.title = content('meta[name="ArticleTitle"]').prop('content') || content('h1#ti').text();
+                    item.description = content('div.TRS_UEDITOR').html();
+                    item.author = [...new Set([content('meta[name="Author"]').prop('content'), content('meta[name="ContentSource"]').prop('content')])].filter((a) => a);
+                    item.category = [
+                        ...new Set([content('meta[name="ColumnName"]').prop('content'), content('meta[name="ColumnType"]').prop('content'), ...(content('meta[name="Keywords"]').prop('content')?.split(/,|;/) ?? [])]),
+                    ].filter((c) => c);
+                    item.pubDate = timezone(parseDate(content('meta[name="PubDate"]').prop('content')), +8);
+                }
+
+                return item;
+            })
+        )
+    );
+
+    const image = new URL($('a.navbar-brand img').prop('src'), rootUrl).href;
+
+    ctx.state.data = {
+        item: items,
+        title: $('title').text(),
+        link: currentUrl,
+        description: $('meta[name="ColumnDescription"]').prop('content'),
+        language: $('html').prop('lang'),
+        image,
+        subtitle: $('meta[name="ColumnName"]').prop('content'),
+        author: $('meta[name="SiteName"]').prop('content'),
+    };
+};

package/lib/v2/gov/nea/ghs.js

@@ -0,0 +1,58 @@
+const got = require('@/utils/got');
+const cheerio = require('cheerio');
+const timezone = require('@/utils/timezone');
+const { parseDate } = require('@/utils/parse-date');
+
+module.exports = async (ctx) => {
+    const limit = ctx.query.limit ? parseInt(ctx.query.limit, 10) : 35;
+
+    const rootUrl = 'https://www.nea.gov.cn';
+    const currentUrl = new URL('sjzz/ghs/', rootUrl).href;
+
+    const { data: response } = await got(currentUrl);
+
+    const $ = cheerio.load(response);
+
+    let items = $('div.right_box ul li')
+        .slice(0, limit)
+        .toArray()
+        .map((item) => {
+            item = $(item);
+
+            const a = item.find('a');
+
+            return {
+                title: a.text(),
+                link: a.prop('href'),
+                pubDate: parseDate(item.find('span.date-tex').text()),
+            };
+        });
+
+    items = await Promise.all(
+        items.map((item) =>
+            ctx.cache.tryGet(item.link, async () => {
+                const { data: detailResponse } = await got(item.link);
+
+                const content = cheerio.load(detailResponse);
+
+                item.title = content('meta[name="ArticleTitle"]').prop('content');
+                item.description = content('td.detail').html() || content('div.article-content td').html();
+                item.author = content('meta[name="ContentSource"]').prop('content');
+                item.category = content('meta[name="keywords"]').prop('content').split(/,/);
+                item.pubDate = timezone(parseDate(content('meta[name="PubDate"]').prop('content')), +8);
+
+                return item;
+            })
+        )
+    );
+
+    ctx.state.data = {
+        item: items,
+        title: $('title').text(),
+        link: currentUrl,
+        description: $('meta[name="ColumnDescription"]').prop('content'),
+        language: 'zh',
+        subtitle: $('meta[name="ColumnType"]').prop('content'),
+        author: $('meta[name="ColumnKeywords"]').prop('content'),
+    };
+};

package/lib/v2/gov/nifdc/index.js

@@ -4,58 +4,55 @@ const timezone = require('@/utils/timezone');
 const { parseDate } = require('@/utils/parse-date');
 
 module.exports = async (ctx) => {
-    const params = ctx.path === '/nifdc' ? '/nifdc/bshff/ylqxbzhgl/qxggtzh' : ctx.path;
+    const { path = 'bshff/ylqxbzhgl/qxggtzh' } = ctx.params;
+    const limit = ctx.query.limit ? parseInt(ctx.query.limit, 10) : 30;
 
     const rootUrl = 'https://www.nifdc.org.cn';
-    const currentUrl = `${rootUrl}${params}/index.html`;
+    const currentUrl = new URL(`nifdc/${path}/`, rootUrl).href;
 
-    const response = await got({
-        method: 'get',
-        url: currentUrl,
-    });
+    const { data: response } = await got(currentUrl);
 
-    const $ = cheerio.load(response.data);
+    const $ = cheerio.load(response);
 
-    let items = $('.list ul li a')
-        .slice(0, ctx.query.limit ? parseInt(ctx.query.limit) : 20)
+    let items = $('div.list ul li')
+        .slice(0, limit)
         .toArray()
         .map((item) => {
             item = $(item);
 
-            const link = item.attr('href');
+            const a = item.find('a');
+            const link = a.prop('href');
 
             return {
-                title: item.text(),
-                link: /^http/.test(link) ? link : new URL(link, currentUrl).href,
-                pubDate: parseDate(
-                    item
-                        .next()
-                        .text()
-                        .match(/\((.*)\)/)
-                ),
+                title: a.prop('title') || a.text(),
+                link: link.startsWith('http') ? link : new URL(link, currentUrl).href,
+                pubDate: parseDate(item.find('span').text().replace(/\(|\)/g, '')),
             };
         });
 
     items = await Promise.all(
         items.map((item) =>
             ctx.cache.tryGet(item.link, async () => {
-                if (/^https:\/\/www\.nmpa\.gov\.cn\//.test(item.link)) {
-                    const { data: html } = await got(item.link);
+                try {
+                    const { data: detailResponse } = await got(item.link);
 
-                    const content = cheerio.load(html);
+                    const content = cheerio.load(detailResponse);
 
-                    item.description = content('.text').html();
-                    item.pubDate = timezone(parseDate($('meta[name="PubDate"]').attr('content')), +8);
-                } else {
-                    const detailResponse = await got({
-                        method: 'get',
-                        url: item.link,
-                    });
+                    item.title = content('.title').text();
+                    item.description = content('div.text').append(content('div.fujian')).html();
+                    item.author = content('meta[name="ContentSource"]').prop('content');
+                    item.category = [
+                        ...new Set([content('meta[name="ColumnName"]').prop('content'), content('meta[name="ColumnType"]').prop('content'), ...(content('meta[name="ColumnKeywords"]').prop('content').split(/,|;/) ?? [])]),
+                    ].filter((c) => c);
+                    item.pubDate = timezone(parseDate(content('meta[name="PubDate"]').prop('content')), +8);
+                    item.enclosure_url = content('a.fujianClass').first().prop('href');
 
-                    const content = cheerio.load(detailResponse.data);
-
-                    item.description = content('.text').append(content('.fujian')).html();
-                    item.pubDate = timezone(parseDate(content('meta[name="PubDate"]').attr('content')), +8);
+                    if (item.enclosure_url) {
+                        item.enclosure_url = new URL(item.enclosure_url, rootUrl).href;
+                        item.enclosure_type = `application/${item.enclosure_url.split(/\./).pop()}`;
+                    }
+                } catch (e) {
+                    // no-empty
                 }
 
                 return item;
@@ -63,9 +60,19 @@ module.exports = async (ctx) => {
         )
     );
 
+    const image = new URL($('div.logo img').prop('src'), currentUrl).href;
+    const icon = new URL($('link[rel="shortcut icon"]').prop('href'), currentUrl).href;
+
     ctx.state.data = {
+        item: items,
         title: $('title').text().replace(/----/, ' - '),
         link: currentUrl,
-        item: items,
+        description: $('meta[name="ColumnDescription"]').prop('content'),
+        language: 'zh',
+        image,
+        icon,
+        logo: icon,
+        subtitle: $('meta[ name="ColumnName"]').prop('content'),
+        author: $('meta[name="SiteName"]').prop('content'),
     };
 };