rsshub 1.0.0-master.fc015b9 → 1.0.0-master.fc1b99f

package/lib/routes/medium/following.ts

@@ -0,0 +1,58 @@
+import { Route } from '@/types';
+import { config } from '@/config';
+
+import parseArticle from './parse-article.js';
+import { getFollowingFeedQuery } from './graphql.js';
+
+export const route: Route = {
+    path: '/following/:user',
+    categories: ['blog'],
+    example: '/medium/following/imsingee',
+    parameters: { user: 'Username' },
+    features: {
+        requireConfig: [
+            {
+                name: 'MEDIUM_COOKIE_*',
+                description: '',
+            },
+        ],
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    name: 'Personalized Recommendations - Following',
+    maintainers: ['ImSingee'],
+    handler,
+    description: `:::warning
+  Personalized recommendations require the cookie value after logging in, so only self-hosting is supported. See the configuration module on the deployment page for details.
+  :::`,
+};
+
+async function handler(ctx) {
+    const user = ctx.req.param('user');
+
+    const cookie = config.medium.cookies[user];
+    if (cookie === undefined) {
+        throw new Error(`缺少 Medium 用户 ${user} 登录后的 Cookie 值`);
+    }
+
+    const posts = await getFollowingFeedQuery(user, cookie);
+    ctx.set('json', posts);
+
+    if (!posts) {
+        // login failed
+        throw new Error(`Medium 用户 ${user} 的 Cookie 无效或已过期`);
+    }
+
+    const urls = posts.items.map((data) => data.post.mediumUrl);
+
+    const parsedArticles = await Promise.all(urls.map((url) => parseArticle(ctx, url)));
+
+    return {
+        title: `${user} Medium Following`,
+        link: 'https://medium.com/?feed=following',
+        item: parsedArticles,
+    };
+}

package/lib/routes/medium/for-you.ts

@@ -0,0 +1,58 @@
+import { Route } from '@/types';
+import { config } from '@/config';
+
+import parseArticle from './parse-article.js';
+import { getWebInlineRecommendedFeedQuery } from './graphql.js';
+
+export const route: Route = {
+    path: '/for-you/:user',
+    categories: ['blog'],
+    example: '/medium/for-you/imsingee',
+    parameters: { user: 'Username' },
+    features: {
+        requireConfig: [
+            {
+                name: 'MEDIUM_COOKIE_*',
+                description: '',
+            },
+        ],
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    name: 'Personalized Recommendations - For You',
+    maintainers: ['ImSingee'],
+    handler,
+    description: `:::warning
+  Personalized recommendations require the cookie value after logging in, so only self-hosting is supported. See the configuration module on the deployment page for details.
+  :::`,
+};
+
+async function handler(ctx) {
+    const user = ctx.req.param('user');
+
+    const cookie = config.medium.cookies[user];
+    if (cookie === undefined) {
+        throw new Error(`缺少 Medium 用户 ${user} 登录后的 Cookie 值`);
+    }
+
+    const posts = await getWebInlineRecommendedFeedQuery(user, cookie);
+    ctx.set('json', posts);
+
+    if (!posts) {
+        // login failed
+        throw new Error(`Medium 用户 ${user} 的 Cookie 无效或已过期`);
+    }
+
+    const urls = posts.items.map((data) => data.post.mediumUrl);
+
+    const parsedArticles = await Promise.all(urls.map((url) => parseArticle(ctx, url)));
+
+    return {
+        title: `${user} Medium For You`,
+        link: 'https://medium.com/',
+        item: parsedArticles,
+    };
+}

package/lib/routes/medium/graphql.ts

@@ -0,0 +1,185 @@
+import got from '@/utils/got';
+
+async function graphqlRequest(body, cookie) {
+    const { data } = await got('https://medium.com/_/graphql', {
+        method: 'POST',
+        headers: {
+            accept: '*/*',
+            'accept-language': 'en-US,en;q=0.9,zh;q=0.8,zh-CN;q=0.7',
+            'apollographql-client-name': 'lite',
+            'apollographql-client-version': 'main-20230505-195233-209f54c418',
+            'cache-control': 'no-cache',
+            'content-type': 'application/json',
+            'medium-frontend-app': 'lite/main-20230505-195233-209f54c418',
+            'medium-frontend-path': '/',
+            'medium-frontend-route': 'homepage',
+            'ot-tracer-sampled': 'true',
+            'ot-tracer-spanid': '2db0b0d7263ffad8',
+            'ot-tracer-traceid': '679eb621b33147c4',
+            pragma: 'no-cache',
+            'sec-ch-ua': '"Chromium";v="113", "Not-A.Brand";v="24"',
+            'sec-ch-ua-mobile': '?0',
+            'sec-ch-ua-platform': '"macOS"',
+            'sec-fetch-dest': 'empty',
+            'sec-fetch-mode': 'cors',
+            'sec-fetch-site': 'same-origin',
+            'graphql-operation': body.operationName,
+            cookie,
+        },
+        data: JSON.stringify([body]),
+    });
+    return data[0].data;
+}
+
+async function getFollowingFeedQuery(user, cookie, pagingLimit = 20) {
+    return (await graphqlRequest(newFollowingFeedQuery(pagingLimit), cookie))?.followingFeed;
+}
+
+async function getWebInlineRecommendedFeedQuery(user, cookie, pagingLimit = 20) {
+    return (await graphqlRequest(newWebInlineRecommendedFeedQuery(pagingLimit), cookie))?.webRecommendedFeed;
+}
+
+async function getWebInlineTopicFeedQuery(user, tagSlug, cookie, pagingLimit = 20) {
+    return (await graphqlRequest(newWebInlineTopicFeedQuery(tagSlug, pagingLimit), cookie))?.personalisedTagFeed;
+}
+
+async function getUserCatalogMainContentQuery(user, catalogId, cookie, pagingLimit = 20) {
+    return (await graphqlRequest(newUserCatalogMainContentQuery(catalogId, pagingLimit), cookie))?.catalogById;
+}
+
+export { getWebInlineRecommendedFeedQuery, getFollowingFeedQuery, getWebInlineTopicFeedQuery, getUserCatalogMainContentQuery };
+
+function newFollowingFeedQuery(pagingLimit = 5) {
+    return {
+        operationName: 'FollowingFeedQuery',
+        variables: {
+            paging: {
+                limit: pagingLimit,
+            },
+        },
+        query: `query FollowingFeedQuery($paging: PagingOptions) {
+            followingFeed(paging: $paging) {
+              items {
+                feedId
+                post {
+                  mediumUrl
+                  __typename
+                }
+                __typename
+              }
+              pagingInfo {
+                next {
+                  to
+                  from
+                  limit
+                  source
+                  __typename
+                }
+                __typename
+              }
+              __typename
+            }
+        }`,
+    };
+}
+
+function newWebInlineRecommendedFeedQuery(pagingLimit = 5) {
+    return {
+        operationName: 'WebInlineRecommendedFeedQuery',
+        variables: {
+            forceRank: true,
+            paging: {
+                limit: pagingLimit,
+            },
+        },
+        query: `query WebInlineRecommendedFeedQuery($paging: PagingOptions, $forceRank: Boolean) {
+            webRecommendedFeed(paging: $paging, forceRank: $forceRank) {
+              items {
+                feedId
+                post {
+                  mediumUrl
+                  __typename
+                }
+                __typename
+              }
+              pagingInfo {
+                next {
+                  limit
+                  to
+                  source
+                  __typename
+                }
+                __typename
+              }
+              __typename
+            }
+        }`,
+    };
+}
+
+function newWebInlineTopicFeedQuery(tagSlug, pagingLimit = 5) {
+    return {
+        operationName: 'WebInlineTopicFeedQuery',
+        variables: {
+            tagSlug,
+            paging: {
+                limit: pagingLimit,
+            },
+            skipCache: true,
+        },
+        query: `query WebInlineTopicFeedQuery($tagSlug: String!, $paging: PagingOptions!, $skipCache: Boolean) {
+            personalisedTagFeed(tagSlug: $tagSlug, paging: $paging, skipCache: $skipCache) {
+              items {
+                feedId
+                post {
+                  mediumUrl
+                  __typename
+                }
+                __typename
+              }
+              pagingInfo {
+                next {
+                  source
+                  limit
+                  from
+                  to
+                  __typename
+                }
+                __typename
+              }
+              __typename
+            }
+        }`,
+    };
+}
+
+function newUserCatalogMainContentQuery(catalogId, pagingLimit = 20) {
+    return {
+        operationName: 'UserCatalogMainContentQuery',
+        variables: {
+            catalogId,
+            pagingOptions: {
+                limit: pagingLimit,
+            },
+        },
+        query: `query UserCatalogMainContentQuery($catalogId: ID!, $pagingOptions: CatalogPagingOptionsInput!) {
+            catalogById(catalogId: $catalogId) {
+              __typename
+              ... on Catalog {
+                name
+                itemsConnection(pagingOptions: $pagingOptions) {
+                  items {
+                    entity {
+                      ... on Post {
+                        mediumUrl
+                      }
+                    }
+                    __typename
+                  }
+                  __typename
+                }
+              }
+            }
+          }`,
+    };
+}

package/lib/routes/medium/list.ts

@@ -0,0 +1,56 @@
+import { Route } from '@/types';
+import { config } from '@/config';
+
+import parseArticle from './parse-article.js';
+import { getUserCatalogMainContentQuery } from './graphql.js';
+
+export const route: Route = {
+    path: '/list/:user/:catalogId',
+    categories: ['blog'],
+    example: '/medium/list/imsingee/f2d8d48096a9',
+    parameters: { user: 'Username', catalogId: 'List ID' },
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    name: 'List',
+    maintainers: ['ImSingee'],
+    handler,
+    description: `The List ID is the last part of the URL after \`-\`, for example, the username in [https://medium.com/@imsingee/list/collection-7e67004f23f9](https://medium.com/@imsingee/list/collection-7e67004f23f9) is \`imsingee\`, and the ID is \`7e67004f23f9\`.
+
+  :::warning
+  To access private lists, only self-hosting is supported.
+  :::`,
+};
+
+async function handler(ctx) {
+    const user = ctx.req.param('user');
+    const catalogId = ctx.req.param('catalogId');
+
+    const cookie = config.medium.cookies[user];
+
+    const catalog = await getUserCatalogMainContentQuery(user, catalogId, cookie);
+    ctx.set('json', catalog);
+
+    if (catalog && catalog.__typename === 'Forbidden') {
+        throw new Error(`无权访问 id 为 ${catalogId} 的 List（可能是未设置 Cookie 或 Cookie 已过期）`);
+    }
+    if (!catalog || !catalog.itemsConnection) {
+        throw new Error(`id 为 ${catalogId} 的 List 不存在`);
+    }
+
+    const name = catalog.name;
+    const urls = catalog.itemsConnection.items.map((item) => item.entity.mediumUrl);
+
+    const parsedArticles = await Promise.all(urls.map((url) => parseArticle(ctx, url)));
+
+    return {
+        title: `List: ${name}`,
+        link: `https://medium.com/@${user}/list/${catalogId}`,
+        item: parsedArticles,
+    };
+}

package/lib/routes/medium/namespace.ts

@@ -0,0 +1,6 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: 'Medium',
+    url: 'medium.com',
+};

package/lib/routes/medium/parse-article.ts

@@ -0,0 +1,61 @@
+import cache from '@/utils/cache';
+import got from '@/utils/got';
+import { load } from 'cheerio';
+
+import { config } from '@/config';
+
+async function parse(url, cookie = '') {
+    const { data } = await got(url, {
+        headers: {
+            cookie,
+        },
+    });
+    const $ = load(data);
+
+    const publishedTime = $('meta[property="article:published_time"]').attr('content');
+    const author = $('meta[name="author"]').attr('content');
+
+    const article = $('body article');
+
+    // remove header actions
+    article.find('header').remove();
+
+    // get and remove title
+    const title = article.find('h1').first();
+    const titleText = title.text();
+    title.remove(); // remove title from html
+
+    // get subtitle and remove author actions
+    const subtitle = article.find('.pw-subtitle-paragraph');
+    const subtitleText = subtitle.text();
+    if (subtitle.length === 0) {
+        // no subtitle
+        article.find('.pw-post-body-paragraph').siblings().first().remove();
+    } else {
+        // preserve subtitle in html
+        subtitle.siblings().remove();
+    }
+
+    return {
+        title: titleText,
+        subtitle: subtitleText,
+        author,
+        publishedTime,
+        html: article.html(),
+        url,
+    };
+}
+
+export default function (ctx, url) {
+    return cache.tryGet(`medium:article:${url}`, async () => {
+        const { title, author, publishedTime, html } = await parse(url, config.medium.articleCookie);
+
+        return {
+            title,
+            author,
+            link: url,
+            description: html,
+            pubDate: publishedTime,
+        };
+    });
+}

package/lib/routes/medium/tag.ts

@@ -0,0 +1,61 @@
+import { Route } from '@/types';
+import { config } from '@/config';
+
+import parseArticle from './parse-article.js';
+import { getWebInlineTopicFeedQuery } from './graphql.js';
+
+export const route: Route = {
+    path: '/tag/:user/:tag',
+    categories: ['blog'],
+    example: '/medium/tag/imsingee/cybersecurity',
+    parameters: { user: 'Username', tag: 'Subscribed Tag' },
+    features: {
+        requireConfig: [
+            {
+                name: 'MEDIUM_COOKIE_*',
+                description: '',
+            },
+        ],
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    name: 'Personalized Recommendations - Tag',
+    maintainers: ['ImSingee'],
+    handler,
+    description: `There are many tags, which can be obtained by clicking on a tag from the homepage and looking at the URL. For example, if the URL is \`https://medium.com/?tag=web3\`, then the tag is \`web3\`.
+
+  :::warning
+  Personalized recommendations require the cookie value after logging in, so only self-hosting is supported. See the configuration module on the deployment page for details.
+  :::`,
+};
+
+async function handler(ctx) {
+    const user = ctx.req.param('user');
+    const tag = ctx.req.param('tag');
+
+    const cookie = config.medium.cookies[user];
+    if (cookie === undefined) {
+        throw new Error(`缺少 Medium 用户 ${user} 登录后的 Cookie 值`);
+    }
+
+    const posts = await getWebInlineTopicFeedQuery(user, tag, cookie);
+    ctx.set('json', posts);
+
+    if (!posts) {
+        // login failed
+        throw new Error(`Medium 用户 ${user} 的 Cookie 无效或已过期`);
+    }
+
+    const urls = posts.items.map((data) => data.post.mediumUrl);
+
+    const parsedArticles = await Promise.all(urls.map((url) => parseArticle(ctx, url)));
+
+    return {
+        title: `${user} Medium Following Tag ${tag}`,
+        link: `https://medium.com/?tag=${tag}`,
+        item: parsedArticles,
+    };
+}

package/lib/routes/medsci/index.ts

@@ -0,0 +1,128 @@
+import { Route } from '@/types';
+import cache from '@/utils/cache';
+import got from '@/utils/got';
+import { load } from 'cheerio';
+import { parseDate, parseRelativeDate } from '@/utils/parse-date';
+
+export const route: Route = {
+    path: '/:sid?/:tid?',
+    categories: ['new-media'],
+    example: '/medsci',
+    parameters: { sid: '科室，见下表，默认为推荐', tid: '亚专业，可在对应科室页 URL 中找到，默认为该科室的全部' },
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    name: '资讯',
+    maintainers: ['nczitzk'],
+    handler,
+    description: `:::tip
+  下表为科室对应的 sid，若想获得 tid，可以到对应科室页面 URL 中寻找 \`t_id\` 字段的值，下面是一个例子：
+
+  如 [肿瘤 - NSCLC](https://www.medsci.cn/department/details?s_id=5\&t_id=277) 的 URL 为 \`https://www.medsci.cn/department/details?s_id=5&t_id=277\`，可以看到此时 \`s_id\` 对应 \`sid\` 的值为 5， \`t_id\` 对应 \`tid\` 的值为 277，所以可以得到路由 [\`/medsci/5/277\`](https://rsshub.app/medsci/5/277)
+  :::
+
+  | 心血管 | 内分泌 | 消化 | 呼吸 | 神经科 |
+  | ------ | ------ | ---- | ---- | ------ |
+  | 2      | 6      | 4    | 12   | 17     |
+
+  | 传染科 | 精神心理 | 肾内科 | 风湿免疫 | 血液科 |
+  | ------ | -------- | ------ | -------- | ------ |
+  | 9      | 13       | 14     | 15       | 21     |
+
+  | 老年医学 | 胃肠外科 | 血管外科 | 肝胆胰外 | 骨科 |
+  | -------- | -------- | -------- | -------- | ---- |
+  | 19       | 76       | 92       | 91       | 10   |
+
+  | 普通外科 | 胸心外科 | 神经外科 | 泌尿外科 | 烧伤科 |
+  | -------- | -------- | -------- | -------- | ------ |
+  | 23       | 24       | 25       | 26       | 27     |
+
+  | 整形科 | 麻醉疼痛 | 罕见病 | 康复医学 | 药械 |
+  | ------ | -------- | ------ | -------- | ---- |
+  | 28     | 29       | 304    | 95       | 11   |
+
+  | 儿科 | 耳鼻咽喉 | 口腔科 | 眼科 | 政策人文 |
+  | ---- | -------- | ------ | ---- | -------- |
+  | 18   | 30       | 31     | 32   | 33       |
+
+  | 营养全科 | 预防公卫 | 妇产科 | 中医科 | 急重症 |
+  | -------- | -------- | ------ | ------ | ------ |
+  | 34       | 35       | 36     | 37     | 38     |
+
+  | 皮肤性病 | 影像放射 | 转化医学 | 检验病理 | 护理 |
+  | -------- | -------- | -------- | -------- | ---- |
+  | 39       | 40       | 42       | 69       | 79   |
+
+  | 糖尿病 | 冠心病 | 肝病 | 乳腺癌 |
+  | ------ | ------ | ---- | ------ |
+  | 8      | 43     | 22   | 89     |`,
+};
+
+async function handler(ctx) {
+    let sid = ctx.req.param('sid') ?? '';
+    const tid = ctx.req.param('tid') ?? '';
+
+    sid = sid === 'recommend' ? '' : sid;
+
+    const rootUrl = 'https://www.medsci.cn';
+    const currentUrl = `${rootUrl}${sid ? `/department/details?s_id=${sid}&module=article${tid ? `&t_id=${tid}` : ''}` : ''}`;
+
+    const response = await got({
+        method: 'get',
+        url: currentUrl,
+    });
+
+    const $ = load(response.data);
+
+    let items = $('#articleList')
+        .find('.ms-link')
+        .toArray()
+        .map((item) => {
+            item = $(item);
+
+            const pubDate = item.parent().parent().find('.item-meta-item').first().text();
+
+            return {
+                title: item.text(),
+                link: `${rootUrl}${item.attr('href').replace(/;jsessionid=[\dA-Z]+/, '')}`,
+                pubDate: pubDate.indexOf('-') > 0 ? parseDate(pubDate) : parseRelativeDate(pubDate),
+            };
+        });
+
+    items = await Promise.all(
+        items.map((item) =>
+            cache.tryGet(item.link, async () => {
+                const detailResponse = await got({
+                    method: 'get',
+                    url: item.link,
+                });
+
+                const content = load(detailResponse.data);
+
+                const pubDateMatches = detailResponse.data.match(/"publishedTime":"(.*)","publishedTimeString"/);
+
+                item.author = content('.name').text();
+                item.description = content('#content').html();
+                item.pubDate = pubDateMatches ? parseDate(pubDateMatches[1]) : item.pubDate;
+                item.category =
+                    content('meta[name="keywords"]')
+                        .attr('content')
+                        ?.split(/,|，/)
+                        .filter((c) => c !== '' && c !== 'undefined') ?? [];
+
+                return item;
+            })
+        )
+    );
+
+    return {
+        title: `${sid ? $('.department-header-active').text() : '推荐'} -${tid ? ` ${$('.department-keywords-ul .active').text()} -` : ''} MedSci.cn`,
+        link: currentUrl,
+        item: items,
+    };
+}

package/lib/routes/medsci/namespace.ts

@@ -0,0 +1,6 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: '梅斯医学 MedSci',
+    url: 'medsci.cn',
+};