rsshub 1.0.0-master.fe69819 → 1.0.0-master.febd623

package/lib/v2/wechat/tgchannel.js

@@ -0,0 +1,146 @@
+const got = require('@/utils/got');
+const cheerio = require('cheerio');
+const { finishArticleItem } = require('@/utils/wechat-mp');
+
+module.exports = async (ctx) => {
+    const id = ctx.params.id;
+    const mpName = ctx.params.mpName ?? '';
+    let searchQueryType = ctx.params.searchQueryType ?? '0';
+    if (searchQueryType !== '0' && searchQueryType !== '1' && searchQueryType !== '2') {
+        searchQueryType = '0';
+    }
+    searchQueryType = +searchQueryType; // 将字符串转换为数字
+
+    const channelUrl = `https://t.me/s/${id}`;
+    const searchQuery = mpName && searchQueryType ? (searchQueryType === 2 ? `?q=%23${mpName}` : `?q=${mpName}`) : '';
+    const { data } = await got.get(`${channelUrl}${searchQuery}`);
+    const $ = cheerio.load(data);
+    const list = $('.tgme_widget_message_wrap').slice(-20);
+
+    const out = await Promise.all(
+        list
+            .map(async (index, item) => {
+                item = $(item);
+
+                if (searchQuery) {
+                    // 删除关键字高亮 <mark class="highlight">
+                    const highlightMarks = item.find('mark.highlight').get();
+                    highlightMarks.forEach((mark) => {
+                        mark = $(mark);
+                        const markInnerHtml = mark.html();
+                        mark.replaceWith(markInnerHtml);
+                    });
+                    if (highlightMarks) {
+                        item = $(item.html()); // 删除关键字高亮后，相邻的裸文本节点不会被自动合并，重新生成 cheerio 对象以确保后续流程正常运行
+                    }
+                }
+
+                // [ div.tgme_widget_message_text 格式简略说明 ]
+                // 若频道只订阅一个公众号：
+                // 第 1 个元素: <a href="${用于 link priview 的预览图 url}"><i><b>🔗</b></i></a>
+                // 第 2 个元素: <a href="${文章 url}">${文章标题}</a>
+                // (余下是文章简介，一般是裸文本，这里用不到)
+                //
+                // 若频道订阅多于一个公众号：
+                // 第 1 个元素: <i><b>${emoji(标注消息来源于什么 slave，这里是表示微信的💬)}</b></i>
+                // 第 2 个元素: <i><b>${emoji(标注对话类型，这里是表示私聊的👤)</b></i>
+                // 裸文本: (半角空格)${公众号名}(半角冒号)
+                // 第 3 个元素: <br />
+                // 第 4 个元素: <a href="${用于 link priview 的预览图 url}"><i><b>🔗</b></i></a>
+                // 第 5 个元素: <a href="${文章 url}">${文章标题}</a>
+                // (余下是文章简介，一般是裸文本，这里用不到)
+                //
+                // 若启用 efb-patch-middleware 且频道订阅多于一个公众号：
+                // 第 1 个元素: <i><b>${emoji(标注消息来源于什么 slave，这里是表示微信的💬)}</b></i>
+                // 第 2 个元素: <i><b>${emoji(标注对话类型，这里是表示私聊的👤)</b></i>
+                // 第 3 个元素: <a href="${?q=%23url-encoded公众号名}">#${公众号名}</a>
+                // 裸文本: ${公众号名余下部分 (若 hashtag 不合法 (遇到空格、标点) 导致被截断才会有)}(半角冒号)
+                // 第 4 个元素: <br />
+                // 第 5 个元素: <a href="${用于 link priview 的预览图 url}"><i><b>🔗</b></i></a>
+                // 第 6 个元素: <a href="${文章 url}">${文章标题}</a>
+                // (余下是文章简介，一般是裸文本，这里用不到)
+
+                let author = '';
+                let titleElemIs3thA = false;
+
+                const brNode = item.find('.tgme_widget_message_text > br:nth-of-type(1)').get(0); // 获取第一个换行
+                const authorNode = brNode && brNode.prev; // brNode 不为 undefined 时获取它的前一个节点
+                const authorNodePrev = authorNode && authorNode.prev; // authorNode 不为 undefined 时获取它的前一个节点
+                if (authorNode && authorNode.type === 'text') {
+                    // 只有这个节点是一个裸文本时它才可能是公众号名，开始找寻公众号名
+                    if (authorNodePrev && authorNodePrev.type === 'tag' && authorNodePrev.name === 'a' && authorNodePrev.attribs.href && authorNodePrev.attribs.href.startsWith('?q=%23')) {
+                        // authorNode 前一个节点是链接, 且是个 hashtag，表示启用了 efb-patch-middleware，这个节点是公众号名
+                        // 有两种可能：
+                        // 带 # 的完整公众号名 (efb-patch-middleware 启用，且 hashtag 完全合法)
+                        // 被截断的公众号名前半部分 (efb-patch-middleware 启用，但 hashtag 被空格或标点截断)
+                        // (若 efb-patch-middleware 未启用，或 hashtag 完全不合法，不会进入此流程)
+                        titleElemIs3thA = true;
+                        author += $(authorNodePrev).text();
+                    }
+
+                    const spaceIndex = authorNode.data.indexOf(' ');
+                    const colonIndex = authorNode.data.indexOf(':');
+                    if (authorNode.data.length > 1 && colonIndex !== -1 && (spaceIndex !== -1 || titleElemIs3thA)) {
+                        // 有三种可能：
+                        // 不带 # 的完整公众号名 (efb-patch-middleware 未启用)
+                        // 带 # 的完整公众号名 (efb-patch-middleware 启用，但 hashtag 完全不合法)
+                        // 被截断的公众号名后半部分 (efb-patch-middleware 启用，但 hashtag 被空格或标点截断，此时空格有意义)
+                        // (若 efb-patch-middleware 启用，且 hashtag 完全合法，不会进入此流程)
+                        const sliceStart = titleElemIs3thA ? 0 : spaceIndex + 1;
+                        author += authorNode.data.slice(sliceStart, colonIndex); // 提取作者
+                    }
+
+                    if (author.startsWith('#')) {
+                        author = author.slice(1); // 去掉开头的 #
+                    }
+                }
+
+                // 如果启用了 efb-patch-middleware 且 hashtag (部分)合法，第三个 a 元素会是文章链接，否则是第二个
+                const titleElemNth = titleElemIs3thA ? 3 : 2;
+                const titleElem = item.find(`.tgme_widget_message_text > a:nth-of-type(${titleElemNth})`);
+
+                if (titleElem.length === 0) {
+                    // 获取不到标题 a 元素，这可能是公众号发的服务消息，丢弃它
+                    return;
+                }
+
+                let title = titleElem.text();
+                const link = titleElem.attr('href');
+
+                if (mpName && author !== mpName) {
+                    // 指定了要筛选的公众号名，且该文章不是该公众号发的
+                    return; // 丢弃
+                } else if (!mpName && author) {
+                    // 没有指定要筛选的公众号名，且匹配到了作者
+                    title = author + ': ' + title; // 给标题里加上获取到的作者
+                }
+
+                const pubDate = new Date(item.find('.tgme_widget_message_date time').attr('datetime')).toUTCString();
+
+                const single = {
+                    title,
+                    pubDate,
+                    link,
+                    guid: link,
+                };
+
+                if (link !== undefined) {
+                    try {
+                        return await finishArticleItem(ctx, single);
+                    } catch (err) {
+                        single.description = item.find('.tgme_widget_message_text').html();
+                    }
+                }
+                return single;
+            })
+            .get()
+    );
+
+    out.reverse();
+    ctx.state.data = {
+        title: mpName ?? $('.tgme_channel_info_header_title').text(),
+        link: `https://t.me/s/${id}`,
+        item: out.filter((item) => item),
+        allowEmpty: !!mpName,
+    };
+};

package/lib/v2/wfu/jwc.js

@@ -0,0 +1,54 @@
+const got = require('@/utils/got');
+const cheerio = require('cheerio');
+
+// 参考 whu/news 武汉大学页面写成
+
+const baseUrl = 'https://jwc.wfu.edu.cn/3742/list.htm';
+const sizeTitle = '潍坊学院教务处新闻';
+
+module.exports = async (ctx) => {
+    const response = await got({
+        method: 'get',
+        url: baseUrl,
+        headers: {
+            Referer: 'https://jwc.wfu.edu.cn/',
+        },
+    });
+    const $ = cheerio.load(response.data);
+
+    // 获取当前页面的 list
+    const list = $('ul.wp_article_list>li');
+
+    const result = await Promise.all(
+        // 遍历每一篇文章
+        list
+            .map((item) => {
+                const $ = cheerio.load(list[item]); // 将列表项加载成 html
+                const $article_title = $('div.pr_fields>span.Article_Title>a');
+                const $item_url = 'https://jwc.wfu.edu.cn/' + $article_title.attr('href'); // 获取 每一项的url
+                const $title = $article_title.text(); // 获取每个的标题
+                const $description = $('div.pr_fields>span.Article_Title').html();
+
+                // 列表上提取到的信息
+                // 教务处通知为文件，直接提供下载链接
+                // 标题 链接
+                const single = {
+                    title: $title,
+                    link: $item_url,
+                    guid: $item_url,
+                    description: $description,
+                };
+
+                // 合并解析后的结果集作为该篇文章最终的输出结果
+                return single;
+            })
+            .get()
+    );
+
+    ctx.state.data = {
+        title: sizeTitle,
+        link: baseUrl,
+        description: '潍坊学院教务处通知（通知为文件需下载）',
+        item: result,
+    };
+};

package/lib/v2/wfu/maintainer.js

@@ -0,0 +1,4 @@
+module.exports = {
+    '/jwc': ['cccht'],
+    '/news/:type?': ['cccht'],
+};

package/lib/v2/wfu/news.js

@@ -0,0 +1,96 @@
+const got = require('@/utils/got');
+const cheerio = require('cheerio');
+const { parseDate } = require('@/utils/parse-date');
+const timezone = require('@/utils/timezone');
+
+// 参考 whu/news 武汉大学页面写成
+
+const baseUrl = 'https://www.wfu.edu.cn';
+const sizeTitle = '--潍坊学院新闻';
+
+const catrgoryMap = {
+    wyyw: ['/50/list.htm', '潍院要闻'],
+    zhxw: ['/52/list.htm', '综合新闻'],
+    xszh: ['/xszh/list.htm', '学术纵横'],
+};
+
+// 专门定义一个function用于加载文章内容
+async function load(link) {
+    let description = '';
+
+    let response;
+    // 如果不是 大学的站点, 直接返回简单的标题即可
+    // 判断 是否外站链接,如果是 则直接返回页面 不做单独的解析
+    const https_reg = new RegExp('https://www.wfu.edu.cn(.*)');
+    if (!https_reg.test(link)) {
+        return { description };
+    }
+    try {
+        // 异步请求文章
+        response = await got.get(link);
+    } catch (err) {
+        // 如果网络问题 直接出错
+        if (err.name && (err.name === 'HTTPError' || err.name === 'RequestError')) {
+            description = 'Page 404 Please Check!';
+        }
+        return { description };
+    }
+    // 加载文章内容
+    const $ = cheerio.load(response.data);
+
+    // 提取文章内容
+    description = $('div.wp_articlecontent').html();
+    // 返回解析的结果
+    return { description };
+}
+
+module.exports = async (ctx) => {
+    // 默认 潍院要闻 然后获取列表页面
+    const type = ctx.params.type ?? 'wyyw';
+    const listPageUrl = baseUrl + catrgoryMap[type][0];
+    const response = await got({
+        method: 'get',
+        url: listPageUrl,
+        headers: {
+            Referer: baseUrl,
+        },
+    });
+    const $ = cheerio.load(response.data);
+
+    // 获取当前页面的 list
+    const list = $('div[frag=窗口1]>ul>li');
+
+    const result = await Promise.all(
+        // 遍历每一篇文章
+        list
+            .map(async (item) => {
+                const $ = cheerio.load(list[item]); // 将列表项加载成 html
+                const $item_url = 'https://www.wfu.edu.cn' + $('a').attr('href'); // 获取 每一项的url
+                const $title = $('a>div.txt>h1').text(); // 获取每个的标题
+                const $pubdate = timezone(parseDate($('a>div.txt>span.date').text().split('：')[1]), +8); // 获取发布时间
+
+                // 列表上提取到的信息
+                // 标题 链接
+                const single = {
+                    title: $title,
+                    pubDate: $pubdate,
+                    link: $item_url,
+                    guid: $item_url,
+                };
+
+                // 对于列表的每一项, 单独获取 时间与详细内容
+                // eslint-disable-next-line no-return-await
+                const other = await ctx.cache.tryGet($item_url, async () => await load($item_url));
+                // 合并解析后的结果集作为该篇文章最终的输出结果
+                return { ...single, ...other };
+            })
+            .get()
+    );
+
+    ctx.state.data = {
+        title: catrgoryMap[type][1] + sizeTitle,
+        link: baseUrl,
+        description: catrgoryMap[type][1] + sizeTitle,
+        item: result,
+    };
+};

package/lib/v2/wfu/radar.js

@@ -0,0 +1,21 @@
+module.exports = {
+    'wfu.edu.cn': {
+        _name: '潍坊学院',
+        jwc: [
+            {
+                title: '教务处通知',
+                docs: 'https://docs.rsshub.app/university.html#wei-fang-xue-yuan',
+                source: '/',
+                target: '/wfu/jwc',
+            },
+        ],
+        news: [
+            {
+                title: '新闻',
+                docs: 'https://docs.rsshub.app/university.html#wei-fang-xue-yuan',
+                source: '/',
+                target: '/wfu/news',
+            },
+        ],
+    },
+};

package/lib/v2/wfu/router.js

@@ -0,0 +1,4 @@
+module.exports = (router) => {
+    router.get('/jwc', require('./jwc'));
+    router.get('/news/:type?', require('./news'));
+};

package/lib/v2/whitehouse/maintainer.js

@@ -1,3 +1,4 @@
 module.exports = {
     '/briefing-room/:category?': ['nczitzk'],
+    '/ostp': ['LyleLee'],
 };

package/lib/v2/whitehouse/ostp.js

@@ -0,0 +1,50 @@
+const got = require('@/utils/got');
+const cheerio = require('cheerio');
+const { parseDate } = require('@/utils/parse-date');
+
+module.exports = async (ctx) => {
+    const rootUrl = 'https://www.whitehouse.gov';
+    const currentUrl = `${rootUrl}/ostp/news-updates`;
+    const response = await got({
+        method: 'get',
+        url: currentUrl,
+    });
+
+    const $ = cheerio.load(response.data);
+
+    const list = $('.news-item__title')
+        .slice(0, 10)
+        .map((_, item) => {
+            item = $(item);
+            return {
+                title: item.text(),
+                link: item.attr('href'),
+            };
+        })
+        .get();
+
+    const items = await Promise.all(
+        list.map((item) =>
+            ctx.cache.tryGet(item.link, async () => {
+                const detailResponse = await got({
+                    method: 'get',
+                    url: item.link,
+                });
+                const content = cheerio.load(detailResponse.data);
+
+                item.description = content('.body-content').html();
+                item.pubDate = parseDate(content('time.published').attr('datetime'));
+                item.author = content('span.tax-links.cat-links > a').text();
+
+                return item;
+            })
+        )
+    );
+
+    ctx.state.data = {
+        title: 'Whitehouse OSTP',
+        link: currentUrl,
+        description: 'Whitehouse Office of Science and Technology Policy',
+        item: items,
+    };
+};

package/lib/v2/whitehouse/radar.js

@@ -8,6 +8,12 @@ module.exports = {
                 source: ['/briefing-room/:category', '/'],
                 target: '/whitehouse/briefing-room/:category',
             },
+            {
+                title: '科技政策办公室',
+                docs: 'https://docs.rsshub.app/government.html#mei-guo-bai-gong-ban-gong-ting',
+                source: ['/ostp', '/'],
+                target: '/whitehouse/ostp',
+            },
         ],
     },
 };

package/lib/v2/whitehouse/router.js

@@ -1,3 +1,4 @@
 module.exports = (router) => {
     router.get('/briefing-room/:category?', require('./briefing-room'));
+    router.get('/ostp', require('./ostp'));
 };

package/lib/v2/who/maintainer.js

@@ -0,0 +1,5 @@
+module.exports = {
+    '/news/:language?': ['nczitzk'],
+    '/news-room/:category?/:language?': ['LogicJake', 'nczitzk'],
+    '/speeches/:language?': ['nczitzk'],
+};

package/lib/v2/who/news-room.js

@@ -0,0 +1,76 @@
+const got = require('@/utils/got');
+const cheerio = require('cheerio');
+const { parseDate } = require('@/utils/parse-date');
+
+module.exports = async (ctx) => {
+    const category = ctx.params.category ?? 'feature-stories';
+    const language = ctx.params.language ?? '';
+
+    const rootUrl = 'https://www.who.int';
+    const currentUrl = `${rootUrl}/${language ? `${language}/` : ''}news-room/${category}`;
+
+    const response = await got({
+        method: 'get',
+        url: currentUrl,
+    });
+
+    const $ = cheerio.load(response.data);
+
+    let list = $('.list-view--item a');
+
+    if (list.length === 0) {
+        const response = await got({
+            method: 'get',
+            url: `${rootUrl}/api/hubs/${category.replace(/-/g, '')}?sf_culture=zh&$orderby=PublicationDateAndTime%20desc&$select=Title,PublicationDateAndTime,ItemDefaultUrl&$top=30`,
+        });
+
+        list = response.data.value.map((item) => ({
+            title: item.Title,
+            link: `${currentUrl}/detail/${item.ItemDefaultUrl}`,
+            pubDate: parseDate(item.PublicationDateAndTime),
+        }));
+    } else {
+        list = list
+            .map((_, item) => {
+                item = $(item);
+                const link = item.attr('href');
+
+                return {
+                    link: `${link.indexOf('http') === 0 ? '' : rootUrl}${item.attr('href')}`,
+                };
+            })
+            .get();
+    }
+
+    const items = await Promise.all(
+        list.map(
+            async (item) =>
+                await ctx.cache.tryGet(item.link, async () => {
+                    const detailResponse = await got({
+                        method: 'get',
+                        url: item.link,
+                    });
+
+                    const matches = detailResponse.data.match(/"headline":"(.*)","description":"(.*)","datePublished":"(.*)","image"/);
+
+                    if (matches) {
+                        item.title = matches[1];
+                        item.description = matches[2];
+                        item.pubDate = parseDate(matches[3]);
+                    } else {
+                        const content = cheerio.load(detailResponse.data);
+
+                        item.description = content('.sf-content-block').html();
+                    }
+
+                    return item;
+                })
+        )
+    );
+
+    ctx.state.data = {
+        title: `${$('meta[property="og:title"]').attr('content')} - WHO`,
+        link: currentUrl,
+        item: items,
+    };
+};

package/lib/v2/who/news.js

@@ -0,0 +1,43 @@
+const got = require('@/utils/got');
+const { parseDate } = require('@/utils/parse-date');
+
+module.exports = async (ctx) => {
+    const language = ctx.params.language ?? 'en';
+
+    const rootUrl = 'https://www.who.int';
+    const currentUrl = `${rootUrl}/${language === 'en' ? '' : `${language}/`}news`;
+    const apiUrl = `${rootUrl}/api/news/newsitems?sf_culture=${language}&$orderby=PublicationDateAndTime%20desc&$select=Title,PublicationDateAndTime,ItemDefaultUrl`;
+
+    const response = await got({
+        method: 'get',
+        url: apiUrl,
+    });
+
+    const list = response.data.value.map((item) => ({
+        title: item.Title,
+        link: `${currentUrl}/item/${item.ItemDefaultUrl}`,
+        pubDate: parseDate(item.PublicationDateAndTime),
+    }));
+
+    const items = await Promise.all(
+        list.map(
+            async (item) =>
+                await ctx.cache.tryGet(item.link, async () => {
+                    const detailResponse = await got({
+                        method: 'get',
+                        url: item.link,
+                    });
+
+                    item.description = detailResponse.data.match(/"description":"(.*)","datePublished"/)[1];
+
+                    return item;
+                })
+        )
+    );
+
+    ctx.state.data = {
+        title: 'News - WHO',
+        link: currentUrl,
+        item: items,
+    };
+};

package/lib/v2/who/radar.js

@@ -0,0 +1,25 @@
+module.exports = {
+    'who.int': {
+        _name: '世界卫生组织 WHO',
+        '.': [
+            {
+                title: '新闻稿',
+                docs: 'https://docs.rsshub.app/government.html#shi-jie-wei-sheng-zu-zhi-who',
+                source: '/news',
+                target: '/who/news',
+            },
+            {
+                title: '媒体中心',
+                docs: 'https://docs.rsshub.app/government.html#shi-jie-wei-sheng-zu-zhi-who',
+                source: '/news-room/:type',
+                target: '/who/news-room/:type',
+            },
+            {
+                title: '总干事的讲话',
+                docs: 'https://docs.rsshub.app/government.html#shi-jie-wei-sheng-zu-zhi-who',
+                source: '/director-general/speeches',
+                target: '/who/speeches',
+            },
+        ],
+    },
+};

package/lib/v2/who/router.js

@@ -0,0 +1,5 @@
+module.exports = (router) => {
+    router.get('/news/:language?', require('./news'));
+    router.get('/news-room/:category?/:language?', require('./news-room'));
+    router.get('/speeches/:language?', require('./speeches'));
+};

package/lib/v2/wikinews/index.js

@@ -0,0 +1,43 @@
+const got = require('@/utils/got');
+const { parseString } = require('xml2js');
+const cheerio = require('cheerio');
+const currentURL = 'https://zh.wikinews.org/wiki/Special:%E6%96%B0%E9%97%BB%E8%AE%A2%E9%98%85';
+const { parseDate } = require('@/utils/parse-date');
+
+module.exports = async (ctx) => {
+    const resp = await got(currentURL);
+    const {
+        urlset: { url: urls },
+    } = await new Promise((resolve, reject) => {
+        parseString(resp.data, (err, result) => {
+            if (err) {
+                reject(err);
+                return;
+            }
+            resolve(result);
+        });
+    });
+
+    ctx.state.data = {
+        title: '最新新闻 - 维基新闻',
+        link: currentURL,
+        item: await Promise.all(
+            urls.map(async (url) => {
+                const loc = url.loc[0];
+                const news = url['news:news'][0];
+                const description = await ctx.cache.tryGet(loc, async () => {
+                    const resp = await got(loc);
+                    const $ = cheerio.load(resp.data);
+                    return $('#bodyContent').html();
+                });
+                return {
+                    title: news['news:title'][0],
+                    pubDate: parseDate(news['news:publication_date'][0]),
+                    category: news['news:keywords'][0].split(',').map((item) => item.trim()),
+                    link: loc,
+                    description,
+                };
+            })
+        ),
+    };
+};

package/lib/v2/wikinews/maintainer.js

@@ -0,0 +1,3 @@
+module.exports = {
+    '/latest': ['KotoriK'],
+};

package/lib/v2/wikinews/radar.js

@@ -0,0 +1,13 @@
+module.exports = {
+    'wikinews.org': {
+        _name: '维基新闻',
+        zh: [
+            {
+                title: '最新新闻',
+                docs: 'https://docs.rsshub.app/new-media.html#wei-ji-xin-wen',
+                source: ['/wiki/Special:新闻订阅'],
+                target: '/wikinews/latest',
+            },
+        ],
+    },
+};

package/lib/v2/wikinews/router.js

@@ -0,0 +1,4 @@
+const routerIndex = require('./index');
+module.exports = function (router) {
+    router.get('/latest', routerIndex);
+};

package/lib/v2/wp-china/maintainer.js

@@ -0,0 +1,3 @@
+module.exports = {
+    '/news/:category?': ['nczitzk'],
+};