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

package/lib/routes/mpaypass/main.js

@@ -1,73 +0,0 @@
-const got = require('../../utils/got');
-const cheerio = require('cheerio');
-
-module.exports = async (ctx) => {
-    let title_url = '';
-    const { type = '' } = ctx.params;
-    if (type) {
-        title_url = `http://www.mpaypass.com.cn/${type}.html`;
-    } else {
-        title_url = 'http://www.mpaypass.com.cn';
-    }
-
-    const response = await got({
-        method: 'get',
-        url: title_url,
-    });
-
-    const data = response.data;
-
-    const $ = cheerio.load(data);
-
-    let title_cn = '';
-    if (type) {
-        title_cn = $(`a[href="http://www.mpaypass.com.cn/${type}.html"]`).text();
-    } else {
-        title_cn = '最新文章';
-    }
-    const list = $('.newslist')
-        .map(function () {
-            const info = {
-                title: $(this).find('#title').text(),
-                link: $(this).find('#pic a').attr('href'),
-                pic: $(this).find('#pic img').attr('src'),
-                time: $(this).find('#time').text(),
-            };
-            return info;
-        })
-        .get();
-
-    const out = await Promise.all(
-        list.map(async (info) => {
-            const title = info.title;
-            let date = info.time.toString();
-            date = date.substring(2, date.length);
-            const link = info.link;
-
-            const cache = await ctx.cache.get(link);
-            if (cache) {
-                return Promise.resolve(JSON.parse(cache));
-            }
-
-            const response = await got.get(link);
-            const $ = cheerio.load(response.data);
-            const newsbody = $('div.newsbody').html();
-
-            const single = {
-                title,
-                link,
-                pubDate: date,
-                description: newsbody,
-            };
-
-            ctx.cache.set(link, JSON.stringify(single));
-            return Promise.resolve(single);
-        })
-    );
-
-    ctx.state.data = {
-        title: `移动支付网-${title_cn}`,
-        link: title_url,
-        item: out,
-    };
-};

package/lib/routes/mpaypass/news.js

@@ -1,43 +0,0 @@
-const got = require('@/utils/got');
-const cheerio = require('cheerio');
-
-module.exports = async (ctx) => {
-    const link = `http://m.mpaypass.com.cn/`;
-    const listData = await got.get(link);
-    const $list = cheerio.load(listData.data);
-    ctx.state.data = {
-        title: `新闻 - 移动支付网`,
-        link,
-        item: await Promise.all(
-            $list('.newsbodylist')
-                .map(async (_, el) => {
-                    const $el = $list(el);
-                    const $a = $el.find('.newsbodylist-title a');
-                    const href = $a.attr('href');
-                    const title = $a.text();
-                    const date = $el.find('.newsbodylist-title span').text().split('|')[1];
-
-                    const key = href;
-                    let description;
-                    const value = await ctx.cache.get(key);
-
-                    if (value) {
-                        description = value;
-                    } else {
-                        const contentData = await got.get(href);
-                        const $content = cheerio.load(contentData.data);
-                        description = $content('.newsbody').html();
-                        ctx.cache.set(key, description);
-                    }
-
-                    return {
-                        title,
-                        description,
-                        link: href,
-                        pubDate: new Date(date).toUTCString(),
-                    };
-                })
-                .get()
-        ),
-    };
-};

package/lib/routes/natgeo/dailyphoto.js

@@ -1,27 +0,0 @@
-const got = require('@/utils/got');
-
-module.exports = async (ctx) => {
-    const today = new Date();
-    const year = today.getFullYear();
-    const month = today.getMonth() + 1;
-
-    const api = `https://www.nationalgeographic.com/content/photography/en_US/photo-of-the-day/_jcr_content/.gallery.${year}-${month}.json`;
-    const response = await got.get(api);
-    const items = response.data.items;
-
-    const out = items.slice(0, 10).map((item) => {
-        const info = {
-            title: item.image.title,
-            author: item.image.credit && item.image.credit.replace('Photograph by ', ''),
-            link: item.pageUrl,
-            description: `<img src="${item.image.uri}">` + item.image.caption,
-        };
-        return info;
-    });
-
-    ctx.state.data = {
-        title: 'Photo of the Day',
-        link: 'https://www.nationalgeographic.com/photography/photo-of-the-day/',
-        item: out,
-    };
-};

package/lib/routes/natgeo/natgeo.js

@@ -1,70 +0,0 @@
-const cheerio = require('cheerio');
-const got = require('@/utils/got');
-
-// https://www.natgeomedia.com//article/
-
-const MonthMap = {
-    JAN: 0,
-    FEB: 1,
-    MAR: 2,
-    APR: 3,
-    MAY: 4,
-    JUN: 5,
-    JUL: 6,
-    AUG: 7,
-    SEP: 8,
-    OCT: 9,
-    NOV: 10,
-    DEC: 11,
-};
-
-async function load(link) {
-    const { data } = await got.get(link);
-    const $ = cheerio.load(data);
-    const dtStr = $('.content-title-area')
-        .find('h6')
-        .first()
-        .text()
-        .split(/[\s.]+/);
-    const dt = new Date();
-    dt.setMonth(MonthMap[dtStr[0].toUpperCase()]);
-    dt.setDate(dtStr[1]);
-    let description = $('article').first().html() + $('article').eq(1).html();
-    if (/photo/.test(link)) {
-        description = $('#content-album').html() + description;
-    }
-    return {
-        title: $('title').text(),
-        pubDate: dt.toUTCString(),
-        description,
-    };
-}
-
-module.exports = async (ctx) => {
-    const type = ctx.params.type || '';
-    const url = `https://www.natgeomedia.com/${ctx.params.cat}/${type}`;
-    const res = await got.get(url);
-    const $ = cheerio.load(res.data);
-
-    const urlList = Array.prototype.map.call($('.article-link-w100').find('.read-btn'), (i) => $(i).find('a[href]').first().attr('href'));
-
-    const count = [];
-    for (let i = 0; i < Math.min(urlList.length, 10); i++) {
-        count.push(i);
-    }
-    const out = await Promise.all(
-        count.map(async (i) => {
-            const link = urlList[i];
-            const single = {
-                link,
-            };
-            const other = await ctx.cache.tryGet(link, () => load(link));
-            return Object.assign({}, single, other);
-        })
-    );
-    ctx.state.data = {
-        title: $('title').text(),
-        link: url,
-        item: out,
-    };
-};

package/lib/routes/nature/cover.js

@@ -1,90 +0,0 @@
-// The content is generateed by undocumentated API of nature journals
-// This router has **just** been tested in:
-// nature:           Nature
-// nbt:              Nature Biotechnology
-// neuro:            Nature Neuroscience
-// ng:               Nature Genetics
-// ni:               Nature Immunology
-// nmeth:            Nature Method
-// nchem:            Nature Chemistry
-// nmat:             Nature Materials
-// natmachintell:    Nature Machine Intelligence
-// ncb:              Nature Cell Biology
-// nplants:          Nature Plants
-// natastron:        Nature Astronomy
-// nphys             Nature Physics
-
-const got = require('@/utils/got');
-
-module.exports = async (ctx) => {
-    const baseURL = 'https://www.nature.com';
-    const journalMap = new Map([
-        ['nature', { id: '41586', name: 'Nature' }],
-        ['nbt', { id: '41587', name: 'Nature Biotechnology' }],
-        ['neuro', { id: '41593', name: 'Nature Neuroscience' }],
-        ['ng', { id: '41588', name: 'Nature Genetics' }],
-        ['ni', { id: '41590', name: 'Nature Immunology' }],
-        ['nmeth', { id: '41592', name: 'Nature Methods' }],
-        ['nchem', { id: '41590', name: 'Nature Chemistry' }],
-        ['nmat', { id: '41563', name: 'Nature Material' }],
-        ['natmachintell', { id: '42256', name: 'Nature Machine Intelligence' }],
-        ['ncb', { id: '41556', name: 'Nature Cell Biology' }],
-        ['nplants', { id: '41477', name: 'Nature Plants' }],
-        ['natastron', { id: '41550', name: 'Nature Astronomy' }],
-        ['nphys', { id: '41567', name: 'Nature Physics' }],
-    ]);
-    const journals = [...journalMap.keys()];
-    const out = await Promise.all(
-        journals.map(async (journal) => {
-            // get the lastest volumn and issue id
-            const pageURL = `${baseURL}/${journal}/current-issue`;
-            const cookieData = await got
-                .extend({
-                    prefixUrl: 'https://idp.nature.com/authorize',
-                    followRedirect: false,
-                })
-                .get(`?response_type=cookie&client_id=grover&redirect_uri=${encodeURI(pageURL)}`)
-                .then((response) => response.headers['set-cookie'].join(' '));
-            const issueURL = await got
-                .extend({
-                    prefixUrl: pageURL,
-                    headers: {
-                        cookie: cookieData,
-                    },
-                    followRedirect: false,
-                })
-                .get('')
-                .then((response) => response.headers.location);
-            const capturingRegex = /volumes\/(?<volumes>\d+)\/issues\/(?<issues>\d+)/;
-            const { volumes, issues } = issueURL.match(capturingRegex).groups;
-
-            const address = `${baseURL}${issueURL}`;
-            const cache = await ctx.cache.get(address);
-            if (cache) {
-                return Promise.resolve(JSON.parse(cache));
-            }
-            const imgSize = 600;
-
-            const id = journalMap.get(journal).id;
-            const imageURL = `https://media.springernature.com/w${imgSize}/springer-static/cover-hires/journal/${id}/${volumes}/${issues}?as=webp`;
-            const contents = `<div align="center"><img src="${imageURL}" alt="Volume ${volumes} Issue ${issues}"></div>`;
-
-            const single = {
-                title: `${journalMap.get(journal).name} | Volume ${volumes} Issue ${issues}`,
-                author: '@yech1990',
-                description: contents,
-                link: address,
-                guid: address,
-                pubDate: new Date().toUTCString(),
-            };
-            ctx.cache.set(address, JSON.stringify(single));
-            return Promise.resolve(single);
-        })
-    );
-    ctx.state.data = {
-        title: 'Nature Covers Story',
-        description: 'Find out the cover story of some Nature journals.',
-        link: baseURL,
-        item: out,
-    };
-};

package/lib/routes/nature/highlight.js

@@ -1,57 +0,0 @@
-const cheerio = require('cheerio');
-const got = require('@/utils/got');
-
-module.exports = async (ctx) => {
-    const base = `https://www.nature.com`;
-    const url = `${base}/nature/articles?type=research-highlight`;
-
-    const res = await got.get(url);
-    const $ = cheerio.load(res.data);
-    const list = $('.border-bottom-1.pb20').get();
-
-    const out = await Promise.all(
-        list.slice(0, 2).map(async (item) => {
-            const $ = cheerio.load(item);
-            const title = $('h3 > a').text();
-            const partial = $('h3 > a').attr('href');
-            const address = `${base}${partial}`;
-            const time = $('time').text();
-            let author;
-            if ($('.js-list-authors-3 li').length > 3) {
-                author = $('.js-list-authors-3 li').slice(0, 1).text() + ' et al.';
-            } else {
-                author = $('.js-list-authors-3 li').text();
-            }
-            const cache = await ctx.cache.get(address);
-            if (cache) {
-                return Promise.resolve(JSON.parse(cache));
-            }
-            const res = await got.get(address);
-            const capture = cheerio.load(res.data);
-            let figure = capture('figure .figure--bleed').html();
-            if (figure === null) {
-                figure = '';
-            }
-            let contents = capture('.article-item--open .article-item__body').html();
-            if (contents === null) {
-                contents = '';
-            }
-            const single = {
-                title,
-                author,
-                description: figure + contents,
-                link: address,
-                guid: address,
-                pubDate: new Date(time).toUTCString(),
-            };
-            ctx.cache.set(address, JSON.stringify(single));
-            return Promise.resolve(single);
-        })
-    );
-    ctx.state.data = {
-        title: `Nature | Research Highlight`,
-        description: `Nature, a nature research journal`,
-        link: url,
-        item: out,
-    };
-};

package/lib/routes/nature/news-and-comment.js

@@ -1,78 +0,0 @@
-// example usage: `/nature/news-and-comment/ng`
-// The journals from NPG are run by different group of people,
-// and the website of may not be consitent for all the journals
-//
-// This router has **just** been tested in:
-// nbt:              Nature Biotechnology
-// neuro:            Nature Neuroscience
-// ng:               Nature Genetics
-// ni:               Nature Immunology
-// nmeth:            Nature Method
-// nchem:            Nature Chemistry
-// nmat:             Nature Materials
-// natmachintell:    Nature Machine Intelligence
-
-const cheerio = require('cheerio');
-const got = require('@/utils/got');
-
-module.exports = async (ctx) => {
-    const baseURL = `https://www.nature.com`;
-
-    const journal = ctx.params.journal;
-    const pageURL = `${baseURL}/${journal}/news-and-comment`;
-
-    const pageResponse = await got.get(pageURL);
-    const pageCapture = cheerio.load(pageResponse.data);
-
-    const pageDescription = pageCapture('meta[name="description"]').attr('content') || `Nature, a nature research journal`;
-    const pageTitleName = pageCapture('meta[name="WT.cg_n"]').attr('content') || `Nature (${journal})`;
-    const pageTitleSub = pageCapture('meta[name="WT.cg_s"]').attr('content') || 'News & Comment';
-
-    const list = pageCapture('.border-bottom-1.pb20').get();
-
-    const items = list.map((el) => {
-        const $ = cheerio.load(el);
-        const title = $('h3 > a').text();
-        const partial = $('h3 > a').attr('href');
-        const address = `${baseURL}${partial}`;
-        const brief = $('.hide-overflow.inline').text();
-        const time = $('time').text();
-        const author = $('.js-list-authors-3 li').text();
-        const articleType = $('p > span').attr('data-class');
-        const headerContents = `
-                <div>
-                  <p style="color: #666">
-                    <span>${articleType}</span>
-                    <span>| </span>
-                    <span>${author}</span>
-                  </p>
-                </div>
-                `;
-        let briefContents = '';
-        if (brief !== '') {
-            briefContents = `
-                <div>
-                  <h2 align="left">Brief</h2>
-                  <p>${brief}</p>
-                </div>
-                `;
-        }
-        const contents = headerContents + briefContents;
-
-        return {
-            title,
-            author,
-            description: contents,
-            link: address,
-            guid: address,
-            pubDate: new Date(time).toUTCString(),
-        };
-    });
-
-    ctx.state.data = {
-        title: `${pageTitleName} | ${pageTitleSub}`,
-        description: pageDescription,
-        link: pageURL,
-        item: items,
-    };
-};

package/lib/routes/nature/news.js

@@ -1,51 +0,0 @@
-const cheerio = require('cheerio');
-const got = require('@/utils/got');
-
-module.exports = async (ctx) => {
-    const base = `https://www.nature.com`;
-    const url = `${base}/nature/articles?type=news`;
-
-    const res = await got.get(url);
-    const $ = cheerio.load(res.data);
-    const list = $('.border-bottom-1.pb20').get();
-
-    const out = await Promise.all(
-        list.map(async (item) => {
-            const $ = cheerio.load(item);
-            const title = $('h3 > a').text();
-            const partial = $('h3 > a').attr('href');
-            const address = `${base}${partial}`;
-            const time = $('time').text();
-            let author;
-            if ($('.js-list-authors-3 li').length > 3) {
-                author = $('.js-list-authors-3 li').slice(0, 1).text() + ' et al.';
-            } else {
-                author = $('.js-list-authors-3 li').text();
-            }
-            const cache = await ctx.cache.get(address);
-            if (cache) {
-                return Promise.resolve(JSON.parse(cache));
-            }
-            const res = await got.get(address);
-            const capture = cheerio.load(res.data);
-            const contents = capture('.content .article__body').html();
-
-            const single = {
-                title,
-                author,
-                description: contents,
-                link: address,
-                guid: address,
-                pubDate: new Date(time).toUTCString(),
-            };
-            ctx.cache.set(address, JSON.stringify(single));
-            return Promise.resolve(single);
-        })
-    );
-    ctx.state.data = {
-        title: `Nature | Latest News`,
-        description: `Nature, a nature research journal`,
-        link: url,
-        item: out,
-    };
-};

package/lib/routes/nature/research.js

@@ -1,184 +0,0 @@
-// example usage: `/nature/research/ng`
-// The journals from NPG are run by different group of people,
-// and the website of may not be consitent for all the journals
-//
-// This router has **just** been tested in:
-// nature:           Nature
-// nbt:              Nature Biotechnology
-// neuro:            Nature Neuroscience
-// ng:               Nature Genetics
-// ni:               Nature Immunology
-// nmeth:            Nature Method
-// nchem:            Nature Chemistry
-// nmat:             Nature Materials
-// natmachintell:    Nature Machine Intelligence
-
-const cheerio = require('cheerio');
-const got = require('@/utils/got');
-
-module.exports = async (ctx) => {
-    const baseURL = `https://www.nature.com`;
-
-    const journal = ctx.params.journal || 'nature';
-    const pageURL = `${baseURL}/${journal}/research`;
-
-    const pageResponse = await got.get(pageURL);
-    const pageCapture = cheerio.load(pageResponse.data);
-
-    const pageDescription = pageCapture('meta[name="description"]').attr('content') || `Nature, a nature research journal`;
-    const pageTitleName = pageCapture('meta[name="WT.cg_n"]').attr('content') || `Nature (${journal})`;
-    const pageTitleSub = pageCapture('meta[name="WT.cg_s"]').attr('content') || 'Latest Research';
-
-    const list = pageCapture('.border-bottom-1.pb20').get();
-
-    const items = await Promise.all(
-        list.map(async (el) => {
-            const $ = cheerio.load(el);
-            const title = $('h3 > a').text();
-            const partial = $('h3 > a').attr('href');
-            const address = `${baseURL}${partial}`;
-            const brief = $('.hide-overflow.inline').text();
-            const time = $('time').text();
-            let author;
-            if ($('.js-list-authors-3 li').length > 3) {
-                author = $('.js-list-authors-3 li').slice(0, 1).text() + ' et al.';
-            } else {
-                author = $('.js-list-authors-3 li').text();
-            }
-            const cache = await ctx.cache.get(address);
-            if (cache) {
-                return Promise.resolve(JSON.parse(cache));
-            }
-            const itemResponse = await got.get(address);
-            const itemCapture = cheerio.load(itemResponse.data);
-
-            // Brief [obtain from entry of each item]
-            let briefContents = '';
-            if (brief !== '') {
-                briefContents = `
-                <div id="rss-journal-brief">
-                  <h2 class="rss-journal-paragraph-title">Brief</h2>
-                  <p class="rss-journal-paragraph-text">${brief}</p>
-                </div>
-                `;
-            }
-            // Abstract [obtain form address of each page]
-            const abs = itemCapture('div#Abs1-content.c-article-section__content > p').html();
-            let absContents = '';
-            if (abs !== null) {
-                absContents = `
-                <div id="rss-journal-abs">
-                  <h2 class="rss-journal-paragraph-title">Abstract</h2>
-                  <p class="rss-journal-paragraph-text">${abs}</p>
-                </div>
-                `;
-            }
-            // Info [obtain form address of each page]
-            const subject = itemCapture('li.c-article-subject-list__subject > a')
-                .map(function () {
-                    const link = $(this).attr('href');
-                    const name = $(this).text();
-                    if (name !== '') {
-                        return `<li class="rss-journal-tag-topic"><a href="${link}">${name}</a></li>`;
-                    } else {
-                        return '';
-                    }
-                })
-                .get()
-                .join('');
-            const subjectContents = subject !== '' ? `<ul>${subject}</ul>` : '';
-            const citation = itemCapture('p.c-bibliographic-information__download-citation > a').attr('href');
-            const citationContents = citation !== undefined ? `<a href="${baseURL}${citation}">Download citation</a>` : '';
-            const doi = itemCapture('meta[name="DOI"]').attr('content');
-            const doiContents = doi !== undefined ? `<a href="https://doi.org/${doi}">DOI: ${doi}</a>` : '';
-            const pdf = itemCapture('meta[name="citation_pdf_url"]').attr('content');
-            const pdfContents = pdf !== undefined ? `<a href="${pdf}">Offical PDF</a>` : '';
-            const linkContents = '<ul>' + [citationContents, doiContents, pdfContents].filter((x) => x !== '').map((x) => `<li class="rss-journal-tag-icon">${x}</li>`) + '</ul>';
-            const infoContents = `
-                <div id="rss-journal-info">
-                  <h2 class="rss-journal-paragraph-title">About this article</h2>
-                  <p>Subjects:</p>
-                  ${subjectContents}
-                  <br>
-                  <p>Links:</p>
-                  ${linkContents}
-                </div>
-                `;
-            // Add style
-            const contentStyle = `
-            <style>
-              .rss-journal-paragraph-title {
-                color: #222;
-                padding: 0;
-                margin: 12px 0 12px;
-                font-family: "Harding","Lora",Palatino,Times,"Times New Roman",serif;
-                font-size: 1.8rem;
-                line-height: 1.4;
-                border-bottom: 1px solid #d5d5d5;
-                font-weight: 200;
-              }
-              .rss-journal-paragraph-text {
-                color: #222;
-                font-size: 1.2em;
-                font-family: Lora,Palatino,Times,"Times New Roman",serif;
-                padding: 0;
-                margin: 0 0 28px;
-                line-height: 1.5;
-                word-wrap: break-word;
-              }
-              .rss-journal-tag-topic {
-                line-height: 1.5;
-                color: #222;
-                font-size: 0.8rem;
-                font-family: -apple-system,BlinkMacSystemFont,"Segoe UI",Roboto,Oxygen-Sans,Ubuntu,Cantarell,"Helvetica Neue",sans-serif;
-                background-color: #dae5ea;
-                border-radius: 15px;
-                padding: 6px 6px;
-                font-weight: 700;
-                margin: 8px 4px 8px;
-                display:inline-block;
-              }
-              .rss-journal-tag-icon {
-                line-height: 1.5;
-                color:#fff;
-                font-size: 0.8rem;
-                font-family: -apple-system,BlinkMacSystemFont,"Segoe UI",Roboto,Oxygen-Sans,Ubuntu,Cantarell,"Helvetica Neue",sans-serif;
-                background-color:#ffb74d;
-                border-radius: 3px;
-                padding: 2px 4px;
-                font-weight: 700;
-                margin: 8px 4px 8px;
-                display:inline-block;
-              }
-              a:link.rss-journal-tag-topic, a:link.rss-journal-tag-icon {
-                color: white;
-              }
-              a:visited.rss-journal-tag-topic, a:link.rss-journal-tag-icon {
-                color: grey;
-              }
-              a:active.rss-journal-tag-topic, a:link.rss-journal-tag-icon {
-                color: hotpink;
-              }
-            </style>
-            `;
-            const contents = briefContents + absContents + infoContents + contentStyle;
-
-            const item = {
-                title,
-                author,
-                description: contents,
-                link: address,
-                guid: address,
-                pubDate: new Date(time).toUTCString(),
-            };
-            ctx.cache.set(address, JSON.stringify(item));
-            return Promise.resolve(item);
-        })
-    );
-    ctx.state.data = {
-        title: `${pageTitleName} | ${pageTitleSub}`,
-        description: pageDescription,
-        link: pageURL,
-        item: items,
-    };
-};