feat: 增加财新网首页新闻、中国政府网滚动新闻、中国政府网新闻要闻 (#2533)

* 增加财新网首页新闻、中国政府网滚动新闻、中国政府网新闻要闻

* 增加财新网首页新闻、中国政府网滚动新闻、中国政府网新闻要闻的文档说明

* 整理格式

* 增加国务院信息

* 调整格式

* Remove User-Agent

docs/government.md

@@ -20,6 +20,18 @@ pageClass: routes
 
 <Route author="ciaranchen" example="/gov/zhengce/wenjian" path="/gov/zhengce/wenjian/:pcodeJiguan?" :paramsDesc="['文种分类。 国令; 国发; 国函; 国发明电; 国办发; 国办函; 国办发明电; 其他']" />
 
+### 滚动新闻
+
+<Route author="EsuRt" example="/gov/xinwen/gundong" path="/gov/xinwen/gundong"/>
+
+### 新闻要闻
+
+<Route author="EsuRt" example="/gov/xinwen/yaowen" path="/gov/xinwen/yaowen"/>
+
+### 国务院信息
+
+<Route author="EsuRt" example="/gov/statecouncil/news" path="/gov/statecouncil/news"/>
+
 ### 江苏省人民政府
 
 <Route author="ocleo1" example="/gov/province/jiangsu/important-news" path="/gov/province/jiangsu/:category" :paramsDesc="['分类名']">

docs/traditional-media.md

@@ -120,6 +120,10 @@ Category 列表:
 
 </Route>
 
+### 首页新闻
+
+<Route author="EsuRt"  example="/caixin/article" path="/caixin/article"/>
+
 ## 东方网
 
 ### 上海新闻

lib/router.js

@@ -328,6 +328,8 @@ router.get('/cctv/:category', require('./routes/cctv/category'));
 router.get('/caixin/blog/:column', require('./routes/caixin/blog'));
 // 财新
 router.get('/caixin/:column/:category', require('./routes/caixin/category'));
+//财新首页
+router.get('/caixin/article', require('./routes/caixin/article'));
 
 // 草榴社区
 router.get('/t66y/post/:tid', require('./routes/t66y/post'));
@@ -1006,6 +1008,9 @@ router.get('/gov/zhengce/zuixin', require('./routes/gov/zhengce/zuixin'));
 router.get('/gov/zhengce/wenjian/:pcodeJiguan?', require('./routes/gov/zhengce/wenjian'));
 router.get('/gov/province/:name/:category', require('./routes/gov/province'));
 router.get('/gov/city/:name/:category', require('./routes/gov/city'));
+router.get('/gov/xinwen/gundong', require('./routes/gov/xinwen/gundong'));
+router.get('/gov/xinwen/yaowen', require('./routes/gov/xinwen/yaowen'));
+router.get('/gov/statecouncil/news', require('./routes/gov/statecouncil/news'));
 
 // 中华人民共和国生态环境部
 router.get('/gov/mee/gs', require('./routes/gov/mee/gs'));

lib/routes/caixin/article.js

@@ -0,0 +1,27 @@
+const got = require('@/utils/got');
+
+module.exports = async (ctx) => {
+    const response = await got({
+        method: 'get',
+        url: 'http://mapiv5.caixin.com//m/api/getWapIndexListByPage?page=1&callback=jQuery213030389065931348935_1560140003113&_=1560140003179',
+        headers: {
+            Referer: `http://mapiv5.caixin.com/`,
+            Host: 'mapiv5.caixin.com',
+        },
+    });
+
+    const reg = /(.*jQuery.*\()([\s\S]*)(\))/;
+    const datatmp = response.data.replace(reg, '$2');
+    const data = JSON.parse(datatmp).data.list;
+
+    ctx.state.data = {
+        title: `财新网 - 首页`,
+        link: `http://www.caixin.com/`,
+        description: '财新网 - 首页',
+        item: data.map((item) => ({
+            title: item.title,
+            description: item.summary,
+            link: item.web_url,
+        })),
+    };
+};

lib/routes/gov/statecouncil/news.js

@@ -0,0 +1,55 @@
+const got = require('@/utils/got');
+const cheerio = require('cheerio');
+
+module.exports = async (ctx) => {
+    const link = `http://www.gov.cn/pushinfo/v150203/`;
+    const listData = await got.get(link);
+    const $list = cheerio.load(listData.data);
+
+    ctx.state.data = {
+        title: '中国政府网 - 国务院信息',
+        link,
+        item: await Promise.all(
+            $list('.news_box .list li:not(.line)')
+                .slice(1, 12)
+                .map(async (_, el) => {
+                    const $el = $list(el);
+                    const $a = $el.find('h4 a');
+                    const href = $a.attr('href');
+                    const key = `gov_statecouncil: ${href}`;
+                    let description;
+                    let dataEncode;
+                    let dataDecode;
+                    let urlSplit;
+                    const value = await ctx.cache.get(key);
+
+                    if (value) {
+                        description = value;
+                    } else {
+                        const contentUrl = href.startsWith('/') ? `http://www.gov.cn${href}` : href;
+                        const contentData = await got.get(contentUrl);
+                        const $content = cheerio.load(contentData.data);
+                        const regImg = /(img src=")(.*)(".*)/g;
+                        const regUrl = /(http.*\/)(content.*)/;
+                        if (contentData.data.indexOf('UCAP-CONTENT') !== -1) {
+                            dataEncode = $content('#UCAP-CONTENT').html();
+                        } else {
+                            dataEncode = $content('body').html();
+                        }
+                        dataDecode = unescape(dataEncode.replace(/&#x/g, '%u').replace(/;/g, ''));
+                        urlSplit = contentUrl.replace(regUrl, '$1');
+                        description = dataDecode.replace(regImg, '$1' + urlSplit + '$2' + '$3');
+                        ctx.cache.set(key, description);
+                    }
+
+                    return {
+                        title: $a.text(),
+                        description,
+                        link: $a.attr('href'),
+                        pubDate: new Date($el.find('.date').text()).toUTCString(),
+                    };
+                })
+                .get()
+        ),
+    };
+};

lib/routes/gov/xinwen/gundong.js

@@ -0,0 +1,55 @@
+const got = require('@/utils/got');
+const cheerio = require('cheerio');
+
+module.exports = async (ctx) => {
+    const link = `http://www.gov.cn/xinwen/gundong.htm`;
+    const listData = await got.get(link);
+    const $list = cheerio.load(listData.data);
+
+    ctx.state.data = {
+        title: '中国政府网 - 滚动新闻',
+        link,
+        item: await Promise.all(
+            $list('.news_box .list li:not(.line)')
+                .slice(1, 12)
+                .map(async (_, el) => {
+                    const $el = $list(el);
+                    const $a = $el.find('h4 a');
+                    const href = $a.attr('href');
+                    const key = `gov_gundong: ${href}`;
+                    let description;
+                    let dataEncode;
+                    let dataDecode;
+                    let urlSplit;
+                    const value = await ctx.cache.get(key);
+
+                    if (value) {
+                        description = value;
+                    } else {
+                        const contentUrl = href.startsWith('/') ? `http://www.gov.cn${href}` : href;
+                        const contentData = await got.get(contentUrl);
+                        const $content = cheerio.load(contentData.data);
+                        const regImg = /(img src=")(.*)(".*)/g;
+                        const regUrl = /(http.*\/)(content.*)/;
+                        if (contentData.data.indexOf('UCAP-CONTENT') !== -1) {
+                            dataEncode = $content('#UCAP-CONTENT').html();
+                        } else {
+                            dataEncode = $content('body').html();
+                        }
+                        dataDecode = unescape(dataEncode.replace(/&#x/g, '%u').replace(/;/g, ''));
+                        urlSplit = contentUrl.replace(regUrl, '$1');
+                        description = dataDecode.replace(regImg, '$1' + urlSplit + '$2' + '$3');
+                        ctx.cache.set(key, description);
+                    }
+
+                    return {
+                        title: $a.text(),
+                        description,
+                        link: $a.attr('href'),
+                        pubDate: new Date($el.find('.date').text()).toUTCString(),
+                    };
+                })
+                .get()
+        ),
+    };
+};

lib/routes/gov/xinwen/yaowen.js

@@ -0,0 +1,55 @@
+const got = require('@/utils/got');
+const cheerio = require('cheerio');
+
+module.exports = async (ctx) => {
+    const link = `http://www.gov.cn/xinwen/yaowen.htm`;
+    const listData = await got.get(link);
+    const $list = cheerio.load(listData.data);
+
+    ctx.state.data = {
+        title: '中国政府网 - 要闻',
+        link,
+        item: await Promise.all(
+            $list('.news_box .list li:not(.line)')
+                .slice(1, 12)
+                .map(async (_, el) => {
+                    const $el = $list(el);
+                    const $a = $el.find('h4 a');
+                    const href = $a.attr('href');
+                    const key = `gov_yaowen: ${href}`;
+                    let description;
+                    let dataEncode;
+                    let dataDecode;
+                    let urlSplit;
+                    const value = await ctx.cache.get(key);
+
+                    if (value) {
+                        description = value;
+                    } else {
+                        const contentUrl = href.startsWith('/') ? `http://www.gov.cn${href}` : href;
+                        const contentData = await got.get(contentUrl);
+                        const $content = cheerio.load(contentData.data);
+                        const regImg = /(img src=")(.*)(".*)/g;
+                        const regUrl = /(http.*\/)(content.*)/;
+                        if (contentData.data.indexOf('UCAP-CONTENT') !== -1) {
+                            dataEncode = $content('#UCAP-CONTENT').html();
+                        } else {
+                            dataEncode = $content('body').html();
+                        }
+                        dataDecode = unescape(dataEncode.replace(/&#x/g, '%u').replace(/;/g, ''));
+                        urlSplit = contentUrl.replace(regUrl, '$1');
+                        description = dataDecode.replace(regImg, '$1' + urlSplit + '$2' + '$3');
+                        ctx.cache.set(key, description);
+                    }
+
+                    return {
+                        title: $a.text(),
+                        description,
+                        link: $a.attr('href'),
+                        pubDate: new Date($el.find('.date').text()).toUTCString(),
+                    };
+                })
+                .get()
+        ),
+    };
+};