rsshub 1.0.0-master.fe99193 → 1.0.0-master.fe9c82a

package/lib/{routes → v2}/weibo/keyword.js

@@ -28,7 +28,7 @@ module.exports = async (ctx) => {
     );
 
     const routeParams = querystring.parse(ctx.params.routeParams);
-    ctx.state.data = {
+    ctx.state.data = weiboUtils.sinaimgTvax({
         title: `又有人在微博提到${keyword}了`,
         link: `http://s.weibo.com/weibo/${encodeURIComponent(keyword)}&b=1&nodup=1`,
         description: `又有人在微博提到${keyword}了`,
@@ -51,5 +51,5 @@ module.exports = async (ctx) => {
                 link: `https://weibo.com/${item.mblog.user.id}/${item.mblog.bid}`,
             };
         }),
-    };
+    });
 };

package/lib/v2/weibo/maintainer.js

@@ -0,0 +1,8 @@
+module.exports = {
+    '/keyword/:keyword/:routeParams?': ['DIYgod'],
+    '/oasis/user/:userid': ['kt286'],
+    '/search/hot': ['xyqfer'],
+    '/super_index/:id/:type?/:routeParams?': ['zengxs'],
+    '/timeline/:uid/:feature?/:routeParams?': ['zytomorrow', 'DIYgod ', 'Rongronggg9'],
+    '/user/:uid/:routeParams?': ['DIYgod', 'iplusx', 'Rongronggg9'],
+};

package/lib/v2/weibo/oasis/user.js

@@ -0,0 +1,20 @@
+const buildData = require('@/utils/common-config');
+const weiboUtils = require('../utils');
+
+module.exports = async (ctx) => {
+    const userid = ctx.params.userid;
+    const link = `https://oasis.weibo.cn/v1/h5/share?uid=${userid}`;
+    ctx.state.data = weiboUtils.sinaimgTvax(
+        await buildData({
+            link,
+            url: link,
+            title: `$('.name-main').text().trim() + ' - 用户 - 绿洲'`,
+            description: `$('.desc').text().trim()`,
+            item: {
+                item: '.container .item',
+                title: `$('.status-desc').text()`,
+                description: `$('.status-desc').text() + '<br>' + $('.media-wrapper').html()`,
+            },
+        })
+    );
+};

package/lib/v2/weibo/radar.js

@@ -0,0 +1,48 @@
+module.exports = {
+    'weibo.com': {
+        _name: '微博',
+        '.': [
+            {
+                title: '博主',
+                docs: 'https://docs.rsshub.app/social-media.html#wei-bo',
+                source: ['/u/:id', '/:id'],
+                target: (params, url, document) => {
+                    let uid = document?.documentElement.innerHTML.match(/\$CONFIG\['oid']='(\d+)'/)?.[1];
+                    if (!uid && !isNaN(params.id)) {
+                        uid = params.id;
+                    }
+                    return uid ? `/weibo/user/${uid}` : '';
+                },
+            },
+            {
+                title: '关键词',
+                docs: 'https://docs.rsshub.app/social-media.html#wei-bo',
+            },
+            {
+                title: '超话',
+                docs: 'https://docs.rsshub.app/social-media.html#wei-bo',
+                source: '/p/:id/super_index',
+                target: '/weibo/super_index/:id',
+            },
+        ],
+        s: [
+            {
+                title: '热搜榜',
+                docs: 'https://docs.rsshub.app/social-media.html#wei-bo',
+                source: '/top/summary',
+                target: '/weibo/search/hot',
+            },
+        ],
+    },
+    'weibo.cn': {
+        _name: '微博',
+        m: [
+            {
+                title: '博主',
+                docs: 'https://docs.rsshub.app/social-media.html#wei-bo',
+                source: ['/u/:uid', '/profile/:uid'],
+                target: '/weibo/user/:uid',
+            },
+        ],
+    },
+};

package/lib/v2/weibo/router.js

@@ -0,0 +1,8 @@
+module.exports = (router) => {
+    router.get('/keyword/:keyword/:routeParams?', require('./keyword'));
+    router.get('/oasis/user/:userid', require('./oasis/user'));
+    router.get('/search/hot', require('./search/hot'));
+    router.get('/super_index/:id/:type?/:routeParams?', require('./super_index'));
+    router.get('/timeline/:uid/:feature?/:routeParams?', require('./timeline'));
+    router.get('/user/:uid/:routeParams?', require('./user'));
+};

package/lib/{routes → v2}/weibo/search/hot.js

@@ -1,4 +1,5 @@
 const got = require('@/utils/got');
+// const weiboUtils = require('../utils');
 
 module.exports = async (ctx) => {
     const {
@@ -30,4 +31,5 @@ module.exports = async (ctx) => {
             };
         }),
     };
+    // ctx.state.data = weiboUtils.sinaimgTvax(ctx.state.data); // no image in the route
 };

package/lib/{routes → v2}/weibo/super_index.js

@@ -53,10 +53,10 @@ module.exports = async (ctx) => {
         }
     }
 
-    ctx.state.data = {
+    ctx.state.data = weiboUtils.sinaimgTvax({
         title: `微博超话 - ${containerData.pageInfo.page_title}`,
         link: `https://weibo.com/p/${id}/super_index`,
         description: `#${containerData.pageInfo.page_title}# 的超话`,
         item: resultItems,
-    };
+    });
 };

package/lib/{routes → v2}/weibo/timeline.js

@@ -125,13 +125,13 @@ module.exports = async (ctx) => {
             })
         );
 
-        ctx.state.data = {
+        ctx.state.data = weiboUtils.sinaimgTvax({
             title: `个人微博时间线--${name}`,
             link: `http://weibo.com/${uid}/`,
             description,
             image: profileImageUrl,
             item: resultItem,
-        };
+        });
     } else if (uid === '0' || ctx.querystring) {
         const { app_key = '', redirect_url = ctx.request.origin + '/weibo/timeline/0', app_secret = '' } = config.weibo;
 

package/lib/{routes → v2}/weibo/user.js

@@ -145,11 +145,11 @@ module.exports = async (ctx) => {
         resultItems = ordinaryItems;
     }
 
-    ctx.state.data = {
+    ctx.state.data = weiboUtils.sinaimgTvax({
         title: `${name}的微博`,
         link: `https://weibo.com/${uid}/`,
         description,
         image: profileImageUrl,
         item: resultItems,
-    };
+    });
 };

package/lib/{routes → v2}/weibo/utils.js

@@ -4,6 +4,16 @@ const cheerio = require('cheerio');
 const { fallback, queryToBoolean, queryToInteger } = require('@/utils/readable-social');
 
 const weiboUtils = {
+    formatTitle: (html) =>
+        html
+            .replace(/<span class=["']url-icon["']><img\s[^>]*?alt=["']?([^>]+?)["']?\s[^>]*?\/?><\/span>/g, '$1') // 表情转换
+            .replace(/<span class=["']url-icon["']>(<img\s[^>]*>)<\/span>/g, '') // 去掉所有图标
+            .replace(/<img\s[^<]*>/g, '[图片]')
+            // impossible to have inline script in weibo posts, but CodeQL complains about it
+            // Dismiss it through the UI: https://github.com/github/codeql/issues/11427
+            .replace(/<[^<]*>/g, '')
+            .replace(/\n/g, ' ')
+            .trim(),
     formatExtended: (ctx, status, params = {}, picsPrefixes = []) => {
         // undefined and strings like "1" is also safely parsed, so no if branch is needed
         const routeParams = querystring.parse(ctx.params.routeParams);
@@ -90,6 +100,13 @@ const weiboUtils = {
             html = usernameAndAvatar + html;
         }
 
+        // status.pics can be either an array or an object:
+        // array: [ object, object, ... ]
+        // object: { '0': object, '1': object, ... }  // REALLY AMAZING data structure
+        if (status.pics && !Array.isArray(status.pics) && typeof status.pics === 'object') {
+            status.pics = Object.values(status.pics);
+        }
+
         // 添加文章头图，此处不需要回落到被转发的微博，后续处理被转发的微博时，还会执行到这里
         if (status.page_info && status.page_info.type === 'article' && status.page_info.page_pic && status.page_info.page_pic.url) {
             // 如果以后后续流程会用到其他字段，记得修改这里
@@ -200,23 +217,11 @@ const weiboUtils = {
             title += status.user.screen_name + ': ';
         }
         if (!status.retweeted_status || showRetweetTextInTitle) {
-            title += htmlNewLineUnreplaced
-                .replace(/<span class=["']url-icon["']><img\s[^>]*?alt=["']?([^>]+?)["']?\s[^>]*?\/><\/span>/g, '$1') // 表情转换
-                .replace(/<span class=["']url-icon["']>(<img\s[^>]*?>)<\/span>/g, '') // 去掉所有图标
-                .replace(/<img[\s\S]*?>/g, '[图片]')
-                .replace(/<.*?>/g, '')
-                .replace('\n', '')
-                .trim();
+            title += weiboUtils.formatTitle(htmlNewLineUnreplaced);
         }
         if (status.retweeted_status) {
             title += showEmojiForRetweet ? '🔁 ' : ' - 转发 ';
-            title += retweeted
-                .replace(/<span class=["']url-icon["']><img\s[^>]*?alt=["']?([^>]+?)["']?\s[^>]*?\/><\/span>/g, '$1') // 表情转换
-                .replace(/<span class=["']url-icon["']>(<img\s[^>]*?>)<\/span>/g, '') // 去掉所有图标
-                .replace(/<img[\s\S]*?>/g, '[图片]')
-                .replace(/<.*?>/g, '')
-                .replace('\n', '')
-                .trim();
+            title += weiboUtils.formatTitle(retweeted);
         }
         if (livePhotoCount > 0) {
             title += ' ';
@@ -417,6 +422,37 @@ const weiboUtils = {
         }
         return itemDesc;
     },
+    sinaimgTvax: (() => {
+        // https://datatracker.ietf.org/doc/html/rfc1808#section-2.4.3
+        const regex = /(?<=\/\/)wx(?=[1-4]\.sinaimg\.cn\/)/gi;
+        // const prefixes = ['tva', 'tvax'];
+        // let cnt = 0;
+        // const replace = (html) => {
+        //     cnt = (cnt + 1) % 2;
+        //     return html.replace(regex, prefixes[cnt]);
+        // };
+        const replace = (html) => html.replace(regex, 'tvax'); // enforce `tvax` as `tva` has a strict WAF
+        const replaceKV = (obj, keys) => {
+            keys.forEach((key) => {
+                if (obj[key]) {
+                    obj[key] = replace(obj[key]);
+                }
+            });
+        };
+        const dataKeys = ['description', 'image'];
+        const itemKeys = ['description'];
+        return (data) => {
+            if (data) {
+                replaceKV(data, dataKeys);
+                if (data.item) {
+                    data.item.forEach((item) => {
+                        replaceKV(item, itemKeys);
+                    });
+                }
+            }
+            return data;
+        };
+    })(),
 };
 
 module.exports = weiboUtils;

package/lib/v2/wfu/news.js

@@ -80,7 +80,7 @@ module.exports = async (ctx) => {
 
                 // 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));
+                const other = await ctx.cache.tryGet($item_url, () => load($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 };
             })

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

@@ -43,28 +43,27 @@ module.exports = async (ctx) => {
     }
 
     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,
-                    });
+        list.map((item) =>
+            ctx.cache.tryGet(item.link, async () => {
+                const detailResponse = await got({
+                    method: 'get',
+                    url: item.link,
+                });
 
-                    const matches = detailResponse.data.match(/"headline":"(.*)","description":"(.*)","datePublished":"(.*)","image"/);
+                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);
+                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();
-                    }
+                    item.description = content('.sf-content-block').html();
+                }
 
-                    return item;
-                })
+                return item;
+            })
         )
     );
 

package/lib/v2/who/news.js

@@ -20,18 +20,17 @@ module.exports = async (ctx) => {
     }));
 
     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;
-                })
+        list.map((item) =>
+            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;
+            })
         )
     );
 

package/lib/v2/wnacg/index.js

@@ -0,0 +1,110 @@
+const got = require('@/utils/got');
+const cheerio = require('cheerio');
+const { parseDate } = require('@/utils/parse-date');
+const { art } = require('@/utils/render');
+const path = require('path');
+
+const categories = {
+    1: '同人誌 漢化',
+    2: '同人誌 CG畫集',
+    3: '同人誌 Cosplay',
+    5: '同人誌',
+    6: '單行本',
+    7: '雜誌&短篇',
+    9: '單行本 漢化',
+    10: '雜誌&短篇 漢化',
+    12: '同人誌 日語',
+    13: '單行本 日語',
+    14: '雜誌&短篇 日語',
+    16: '同人誌 English',
+    17: '單行本 English',
+    19: '韓漫',
+    20: '韓漫 漢化',
+    21: '韓漫 生肉',
+};
+
+const baseUrl = 'https://wnacg.org';
+
+module.exports = async (ctx) => {
+    const { cid, tag } = ctx.params;
+    if (cid && !Object.keys(categories).includes(cid)) {
+        throw Error('此分类不存在');
+    }
+
+    const url = `${baseUrl}/albums${cid ? `-index-cate-${cid}` : ''}${tag ? `-index-tag-${tag}` : ''}.html`;
+    const { data } = await got(url);
+    const $ = cheerio.load(data);
+
+    const list = $('.gallary_item')
+        .toArray()
+        .map((item) => {
+            item = $(item);
+            const href = item.find('a').attr('href');
+            const aid = href.match(/^\/photos-index-aid-(\d+)\.html$/)[1];
+            return {
+                title: item.find('a').attr('title'),
+                link: `${baseUrl}${href}`,
+                pubDate: parseDate(
+                    item
+                        .find('.info_col')
+                        .text()
+                        .replace(/\d+張照片，\n創建於/, ''),
+                    'YYYY-MM-DD'
+                ),
+                aid,
+            };
+        });
+
+    const items = await Promise.all(
+        list.map((item) =>
+            ctx.cache.tryGet(item.link, async () => {
+                const { data: descRes } = await got(item.link, {
+                    headers: {
+                        referer: encodeURI(url),
+                    },
+                });
+                let $ = cheerio.load(descRes);
+                const author = $('.uwuinfo p').first().text();
+                const category = $('.tagshow')
+                    .toArray()
+                    .map((item) => $(item).text());
+                $('.addtags').remove();
+                const description = $('.uwconn').html();
+
+                const { data } = await got(`${baseUrl}/photos-gallery-aid-${item.aid}.html`, {
+                    headers: {
+                        referer: `${baseUrl}/photos-slide-aid-${item.aid}.html`,
+                    },
+                });
+                $ = cheerio.load(data);
+
+                const imgListMatch = $('script')
+                    .text()
+                    .match(/var imglist = (\[.*\]);"\);/)[1];
+
+                const imgList = JSON.parse(
+                    imgListMatch
+                        .replace(/url:/g, '"url":')
+                        .replace(/caption:/g, '"caption":')
+                        .replace(/fast_img_host\+\\/g, '')
+                        .replace(/\\/g, '')
+                );
+
+                item.author = author;
+                item.category = category;
+                item.description = art(path.join(__dirname, 'templates/manga.art'), {
+                    description,
+                    imgList,
+                });
+
+                return item;
+            })
+        )
+    );
+
+    ctx.state.data = {
+        title: $('head title').text(),
+        link: url,
+        item: items,
+    };
+};

package/lib/v2/wnacg/maintainer.js

@@ -0,0 +1,5 @@
+module.exports = {
+    '/': ['KenMizz'],
+    '/category/:cid': ['Gandum2077'],
+    '/tag/:tag': ['Gandum2077'],
+};

package/lib/v2/wnacg/radar.js

@@ -0,0 +1,25 @@
+module.exports = {
+    'wnacg.org': {
+        _name: '紳士漫畫',
+        '.': [
+            {
+                title: '最新',
+                docs: 'https://docs.rsshub.app/anime.html#shen-shi-man-hua',
+                source: ['/albums.html', '/'],
+                target: '/wnacg',
+            },
+            {
+                title: '分类更新',
+                docs: 'https://docs.rsshub.app/anime.html#shen-shi-man-hua',
+                source: ['/*'],
+                target: (_, url) => `/wnacg/category/${new URL(url).pathname.match(/albums-index-cate-(\d+)\.html$/)[1]}`,
+            },
+            {
+                title: '標籤更新',
+                docs: 'https://docs.rsshub.app/anime.html#shen-shi-man-hua',
+                source: ['/*'],
+                target: (_, url) => `/wnacg/tag/${new URL(url).pathname.match(/albums-index-tag-(.+?)\.html$/)[1]}`,
+            },
+        ],
+    },
+};

package/lib/v2/wnacg/router.js

@@ -0,0 +1,5 @@
+module.exports = (router) => {
+    router.get('/', require('./index'));
+    router.get('/category/:cid', require('./index'));
+    router.get('/tag/:tag', require('./index'));
+};

package/lib/v2/wnacg/templates/manga.art

@@ -0,0 +1,9 @@
+{{ if description }}
+{{@ description }}
+{{ /if }}
+<br>
+{{ if imgList }}
+{{ each imgList img }}
+<img src="https:{{ img.url }}" alt="{{ img.caption }}">
+{{ /each }}
+{{ /if }}

package/lib/v2/woshipm/bookmarks.js

@@ -0,0 +1,34 @@
+const got = require('@/utils/got');
+const { parseDate } = require('@/utils/parse-date');
+const { baseUrl, parseArticle } = require('./utils');
+
+module.exports = async (ctx) => {
+    const id = ctx.params.id;
+    const { data: profile } = await got(`${baseUrl}/api2/user/profile`, {
+        searchParams: {
+            uid: id,
+        },
+    });
+    const userInfo = profile.RESULT.userInfoVo;
+    const name = userInfo.nickName;
+
+    const remark_api = `${baseUrl}/__api/v1/users/${id}/bookmarks`;
+    const response_api = await got(remark_api);
+    const list = response_api.data.payload.value.map((item) => ({
+        title: item.title,
+        description: item.snipper,
+        link: item.permalink,
+        pubDate: parseDate(item.date, 'YYYY/MM/DD'),
+        author: item.author.name,
+    }));
+
+    const out = await Promise.all(list.map((info) => parseArticle(info, ctx.cache.tryGet)));
+
+    ctx.state.data = {
+        title: `${name}的收藏-人人都是产品经理`,
+        description: userInfo.description,
+        image: userInfo.avartar,
+        link: `${baseUrl}/u/${id}`,
+        item: out,
+    };
+};

package/lib/v2/woshipm/latest.js

@@ -0,0 +1,27 @@
+const got = require('@/utils/got');
+const { parseDate } = require('@/utils/parse-date');
+const { baseUrl, parseArticle } = require('./utils');
+
+module.exports = async (ctx) => {
+    const pages = 3;
+    const urlList = Array.from({ length: pages }, (_, v) => `${baseUrl}/__api/v1/stream-list${v < 1 ? '' : `/page/${v + 1}`}`);
+    const responses = await got.all(urlList.map((url) => got(url)));
+
+    const payload = responses.map((response) => response.data.payload).flat();
+
+    const list = payload.map((item) => ({
+        title: item.title,
+        description: item.snipper,
+        link: item.permalink,
+        pubDate: parseDate(item.date, 'YYYY/MM/DD'),
+        author: item.author.name,
+    }));
+
+    const result = await Promise.all(list.map((item) => parseArticle(item, ctx.cache.tryGet)));
+
+    ctx.state.data = {
+        title: '最新文章 - 人人都是产品经理',
+        link: baseUrl,
+        item: result,
+    };
+};

package/lib/v2/woshipm/maintainer.js

@@ -0,0 +1,7 @@
+module.exports = {
+    '/bookmarks/:id': ['LogicJake'],
+    '/latest': ['Director-0428'],
+    '/popular/:range?': ['WenryXu'],
+    '/user_article/:id': ['LogicJake'],
+    '/wen': ['WenryXu'],
+};

package/lib/v2/woshipm/popular.js

@@ -0,0 +1,33 @@
+const got = require('@/utils/got');
+const { parseDate } = require('@/utils/parse-date');
+const { baseUrl, parseArticle } = require('./utils');
+
+const rangeMap = {
+    daily: '日榜',
+    weekly: '周榜',
+    monthly: '月榜',
+};
+
+module.exports = async (ctx) => {
+    const { range = 'daily' } = ctx.params;
+    const { data: response } = await got(`${baseUrl}/api2/app/article/popular/${range}`);
+
+    const list = response.RESULT.map((item) => {
+        item = item.data;
+        return {
+            title: item.articleTitle,
+            description: item.articleSummary,
+            link: `${baseUrl}/${item.type}/${item.id}.html`,
+            pubDate: parseDate(item.publishTime, 'x'),
+            author: item.articleAuthor,
+        };
+    });
+
+    const result = await Promise.all(list.map((item) => parseArticle(item, ctx.cache.tryGet)));
+
+    ctx.state.data = {
+        title: `热门文章 - ${rangeMap[range]} - 人人都是产品经理`,
+        link: baseUrl,
+        item: result,
+    };
+};

package/lib/v2/woshipm/radar.js

@@ -0,0 +1,39 @@
+module.exports = {
+    'woshipm.com': {
+        _name: '人人都是产品经理',
+        '.': [
+            {
+                title: '热门文章',
+                docs: 'https://docs.rsshub.app/new-media.html#ren-ren-dui-shi-chan-pin-jing-li',
+                source: ['/'],
+                target: '/woshipm/popular',
+            },
+            {
+                title: '用户收藏',
+                docs: 'https://docs.rsshub.app/new-media.html#ren-ren-dui-shi-chan-pin-jing-li',
+                source: ['/u/:id'],
+                target: '/woshipm/bookmarks/:id',
+            },
+            {
+                title: '用户文章',
+                docs: 'https://docs.rsshub.app/new-media.html#ren-ren-dui-shi-chan-pin-jing-li',
+                source: ['/u/:id'],
+                target: '/woshipm/user_article/:id',
+            },
+            {
+                title: '最新文章',
+                docs: 'https://docs.rsshub.app/new-media.html#ren-ren-dui-shi-chan-pin-jing-li',
+                source: ['/'],
+                target: '/woshipm/latest',
+            },
+        ],
+        wen: [
+            {
+                title: '天天问',
+                docs: 'https://docs.rsshub.app/new-media.html#ren-ren-dui-shi-chan-pin-jing-li',
+                source: ['/'],
+                target: '/woshipm/wen',
+            },
+        ],
+    },
+};