@jackwener/opencli 1.5.5 → 1.5.7

package/dist/clis/tieba/utils.js

@@ -0,0 +1,240 @@
+import { createHash } from 'node:crypto';
+/**
+ * Shared Tieba parsing helpers used by the browser adapters.
+ */
+export const MAX_TIEBA_LIMIT = 20;
+const TIEBA_PC_SIGN_SALT = '36770b1f34c9bbf2e7d1a99d2b82fa9e';
+const TIEBA_TIME_ZONE = 'Asia/Shanghai';
+/**
+ * Keep the public CLI limit contract aligned with the real implementation.
+ */
+export function normalizeTiebaLimit(value, fallback = MAX_TIEBA_LIMIT) {
+    const parsed = Number(value ?? fallback);
+    if (!Number.isFinite(parsed) || parsed < 1)
+        return fallback;
+    return Math.min(Math.trunc(parsed), MAX_TIEBA_LIMIT);
+}
+export function normalizeText(value) {
+    return typeof value === 'string' ? value.replace(/\s+/g, ' ').trim() : '';
+}
+/**
+ * Match Tieba PC's signed request contract so forum list fetching stays stable.
+ */
+export function signTiebaPcParams(params) {
+    const payload = Object.keys(params)
+        .sort((left, right) => left.localeCompare(right))
+        .map((key) => `${key}=${params[key]}`)
+        .join('') + TIEBA_PC_SIGN_SALT;
+    return createHash('md5').update(payload).digest('hex');
+}
+export function parseTiebaCount(text) {
+    const value = normalizeText(text).toUpperCase();
+    if (!value)
+        return 0;
+    const compact = value.replace(/[^\d.W万]/g, '');
+    if (compact.endsWith('万')) {
+        return Math.round(parseFloat(compact.slice(0, -1)) * 10000);
+    }
+    if (compact.endsWith('W')) {
+        return Math.round(parseFloat(compact.slice(0, -1)) * 10000);
+    }
+    return parseInt(compact.replace(/[^\d]/g, ''), 10) || 0;
+}
+export function parseTiebaLastReply(text) {
+    const normalized = normalizeText(text).replace(/^回复于/, '').trim();
+    const match = normalized.match(/(刚刚|\d+\s*(?:分钟|小时|天)前|\d{2}-\d{2}(?:\s+\d{2}:\d{2})?|\d{4}-\d{2}-\d{2}(?:\s+\d{2}:\d{2})?)/);
+    return match ? match[1].trim() : normalized;
+}
+function buildTiebaThreadUrl(id, rawUrl) {
+    const explicitUrl = normalizeText(rawUrl);
+    if (explicitUrl)
+        return explicitUrl;
+    return id ? `https://tieba.baidu.com/p/${id}` : '';
+}
+function resolveTiebaThreadId(raw) {
+    const direct = normalizeText(raw.threadId);
+    if (direct)
+        return direct;
+    const fromUrl = normalizeText(raw.url).match(/\/p\/(\d+)/);
+    return fromUrl ? fromUrl[1] : '';
+}
+function getTiebaFeedComponent(feed, name) {
+    const components = Array.isArray(feed?.components) ? feed.components : [];
+    const match = components.find((entry) => normalizeText(entry.component) === name);
+    if (!match)
+        return {};
+    const payload = match[name];
+    return payload && typeof payload === 'object' ? payload : {};
+}
+function extractTiebaFeedAuthor(feed) {
+    const head = getTiebaFeedComponent(feed, 'feed_head');
+    const mainData = Array.isArray(head.main_data) ? head.main_data : [];
+    for (const item of mainData) {
+        const textRecord = item.text;
+        const author = normalizeText(textRecord?.text);
+        if (author)
+            return author;
+    }
+    return '';
+}
+function extractTiebaFeedTitle(feed) {
+    const title = getTiebaFeedComponent(feed, 'feed_title');
+    const titleData = Array.isArray(title.data) ? title.data : [];
+    const firstTitle = titleData[0];
+    const textInfo = firstTitle?.text_info;
+    return normalizeText(textInfo?.text) || normalizeText(feed?.business_info_map?.title);
+}
+function extractTiebaFeedCommentCount(feed) {
+    const social = getTiebaFeedComponent(feed, 'feed_social');
+    const commentCount = Number(social.comment_num ?? feed?.business_info_map?.comment_num ?? 0);
+    return Number.isFinite(commentCount) ? commentCount : 0;
+}
+function extractTiebaFeedThreadId(feed) {
+    const direct = normalizeText(feed?.business_info_map?.thread_id);
+    if (direct)
+        return direct;
+    const logParams = Array.isArray(feed?.log_param) ? feed.log_param : [];
+    const fromLog = normalizeText(logParams.find((item) => normalizeText(item?.key) === 'tid')?.value);
+    if (fromLog)
+        return fromLog;
+    const fromSchema = normalizeText(feed?.schema).match(/[?&]tid=(\d+)/);
+    return fromSchema ? fromSchema[1] : '';
+}
+function extractTiebaFeedLastReply(feed) {
+    const head = getTiebaFeedComponent(feed, 'feed_head');
+    const extraData = Array.isArray(head.extra_data) ? head.extra_data : [];
+    const first = extraData[0];
+    const prefix = normalizeText(first?.business_info_map?.time_prefix);
+    const textRecord = first?.text;
+    const rawTime = normalizeText(textRecord?.text);
+    const formattedTime = /^\d+$/.test(rawTime) ? formatTiebaUnixTime(rawTime) : rawTime;
+    return [prefix, formattedTime].filter(Boolean).join('');
+}
+/**
+ * Convert Tieba's signed `page_pc` feed entries into the stable card shape used by the CLI.
+ */
+export function buildTiebaPostCardsFromPagePc(rawFeeds) {
+    return rawFeeds
+        .filter((entry) => normalizeText(entry.layout) === 'feed' && entry.feed)
+        .map((entry) => {
+        const feed = entry.feed;
+        const threadId = extractTiebaFeedThreadId(feed);
+        return {
+            title: extractTiebaFeedTitle(feed),
+            author: extractTiebaFeedAuthor(feed),
+            descInfo: extractTiebaFeedLastReply(feed),
+            commentCount: extractTiebaFeedCommentCount(feed),
+            actionTexts: [],
+            threadId,
+            url: buildTiebaThreadUrl(threadId),
+        };
+    })
+        .filter((entry) => normalizeText(entry.title));
+}
+export function buildTiebaPostItems(rawCards, requestedLimit) {
+    const limit = normalizeTiebaLimit(requestedLimit);
+    return rawCards
+        .map((raw) => {
+        const title = normalizeText(raw.title);
+        const id = resolveTiebaThreadId(raw);
+        const actionTexts = Array.isArray(raw.actionTexts) ? raw.actionTexts.map(normalizeText).filter(Boolean) : [];
+        const commentText = actionTexts.find((text) => /评论/.test(text)) || actionTexts[actionTexts.length - 1] || '';
+        return {
+            title,
+            author: normalizeText(raw.author),
+            replies: Number.isFinite(Number(raw.commentCount))
+                ? Number(raw.commentCount)
+                : parseTiebaCount(commentText),
+            last_reply: parseTiebaLastReply(String(raw.descInfo ?? '')),
+            id,
+            url: buildTiebaThreadUrl(id, raw.url),
+        };
+    })
+        .filter((item) => item.title)
+        .slice(0, limit)
+        .map((item, index) => ({ rank: index + 1, ...item }));
+}
+export function buildTiebaSearchItems(rawItems, requestedLimit) {
+    const limit = normalizeTiebaLimit(requestedLimit);
+    return rawItems
+        .map((raw) => {
+        const url = normalizeText(raw.url);
+        const directId = normalizeText(raw.id);
+        const idFromUrl = url.match(/\/p\/(\d+)/)?.[1] || '';
+        return {
+            title: normalizeText(raw.title),
+            forum: normalizeText(raw.forum),
+            author: normalizeText(raw.author),
+            time: normalizeText(raw.time),
+            snippet: normalizeText(raw.snippet).slice(0, 200),
+            id: directId || idFromUrl,
+            url,
+        };
+    })
+        .filter((item) => item.title)
+        .slice(0, limit)
+        .map((item, index) => ({ rank: index + 1, ...item }));
+}
+function formatTiebaUnixTime(value) {
+    const ts = Number(value || 0);
+    if (!Number.isFinite(ts) || ts <= 0)
+        return '';
+    const parts = new Intl.DateTimeFormat('sv-SE', {
+        timeZone: TIEBA_TIME_ZONE,
+        year: 'numeric',
+        month: '2-digit',
+        day: '2-digit',
+        hour: '2-digit',
+        minute: '2-digit',
+        hour12: false,
+    }).formatToParts(new Date(ts * 1000));
+    const values = Object.fromEntries(parts.map((part) => [part.type, part.value]));
+    return `${values.year}-${values.month}-${values.day} ${values.hour}:${values.minute}`;
+}
+function parseTiebaReplyTime(text) {
+    const normalized = normalizeText(text);
+    const withoutFloor = normalized.replace(/^第\d+楼\s+/, '').trim();
+    const match = withoutFloor.match(/^(刚刚|昨天|前天|\d+\s*(?:分钟|小时|天)前|\d{2}-\d{2}(?:\s+\d{2}:\d{2})?|\d{4}-\d{2}-\d{2}(?:\s+\d{2}:\d{2})?)/);
+    return match ? match[1].trim() : withoutFloor;
+}
+function buildMainPostItem(mainPost) {
+    if (!mainPost)
+        return null;
+    const title = normalizeText(mainPost.title);
+    const author = normalizeText(mainPost.author) || normalizeText(mainPost.fallbackAuthor);
+    const body = normalizeText(mainPost.contentText) || normalizeText(mainPost.structuredText);
+    const hasMedia = Boolean(mainPost.hasMedia);
+    const content = [title, body || (hasMedia ? '[media]' : '')].filter(Boolean).join(' ').trim();
+    if (!content)
+        return null;
+    return {
+        floor: 1,
+        author,
+        content,
+        time: normalizeText(mainPost.visibleTime) || formatTiebaUnixTime(mainPost.structuredTime),
+    };
+}
+export function buildTiebaReadItems(payload, options = {}) {
+    const fallback = Number.isFinite(Number(options.limit)) ? Number(options.limit) : 30;
+    const limit = Math.max(1, Math.trunc(fallback));
+    const includeMainPost = options.includeMainPost !== false;
+    const items = [];
+    const mainPost = buildMainPostItem(payload.mainPost);
+    if (includeMainPost && mainPost)
+        items.push(mainPost);
+    const replies = Array.isArray(payload.replies) ? payload.replies : [];
+    const replyItems = [];
+    for (const reply of replies) {
+        const floor = Number(reply.floor || 0);
+        const content = normalizeText(reply.content);
+        if (!Number.isFinite(floor) || floor < 1 || !content)
+            continue;
+        replyItems.push({
+            floor,
+            author: normalizeText(reply.author),
+            content,
+            time: parseTiebaReplyTime(String(reply.time ?? '')),
+        });
+    }
+    return items.concat(replyItems.slice(0, limit));
+}

package/dist/clis/tieba/utils.test.d.ts

@@ -0,0 +1 @@
+export {};

package/dist/clis/tieba/utils.test.js

@@ -0,0 +1,290 @@
+import { describe, expect, it } from 'vitest';
+import { MAX_TIEBA_LIMIT, buildTiebaPostCardsFromPagePc, buildTiebaPostItems, buildTiebaSearchItems, buildTiebaReadItems, normalizeTiebaLimit, signTiebaPcParams, } from './utils.js';
+describe('normalizeTiebaLimit', () => {
+    it('caps list commands at the declared tieba maximum', () => {
+        expect(MAX_TIEBA_LIMIT).toBe(20);
+        expect(normalizeTiebaLimit(undefined)).toBe(20);
+        expect(normalizeTiebaLimit(25)).toBe(20);
+        expect(normalizeTiebaLimit(7)).toBe(7);
+    });
+});
+describe('signTiebaPcParams', () => {
+    it('matches Tieba PC forum-list signing for stable page_pc requests', () => {
+        expect(signTiebaPcParams({
+            kw: encodeURIComponent('李毅'),
+            pn: '1',
+            sort_type: '-1',
+            is_newfrs: '1',
+            is_newfeed: '1',
+            rn: '30',
+            rn_need: '20',
+            tbs: '',
+            subapp_type: 'pc',
+            _client_type: '20',
+        })).toBe('466f2e091dd4ed17c6661a842b5ec342');
+    });
+});
+describe('buildTiebaPostCardsFromPagePc', () => {
+    it('extracts thread cards from signed page_pc feed payloads', () => {
+        const cards = buildTiebaPostCardsFromPagePc([
+            {
+                layout: 'feed',
+                feed: {
+                    schema: 'tiebaapp://router/portal?params=%7B%22pageParams%22%3A%7B%22tid%22%3A10596901456%7D%7D',
+                    log_param: [
+                        { key: 'tid', value: '10596901456' },
+                    ],
+                    business_info_map: {
+                        thread_id: '10596901456',
+                        title: '崇拜希特勒的人都是日本的汉奸走狗',
+                    },
+                    components: [
+                        {
+                            component: 'feed_head',
+                            feed_head: {
+                                extra_data: [
+                                    {
+                                        business_info_map: { time_prefix: '回复于' },
+                                        text: { text: '1774343231' },
+                                    },
+                                ],
+                                main_data: [
+                                    {
+                                        text: { text: '上帝的子民º♬' },
+                                    },
+                                ],
+                            },
+                        },
+                        {
+                            component: 'feed_title',
+                            feed_title: {
+                                data: [{ text_info: { text: '崇拜希特勒的人都是日本的汉奸走狗' } }],
+                            },
+                        },
+                        {
+                            component: 'feed_social',
+                            feed_social: {
+                                comment_num: 12,
+                            },
+                        },
+                    ],
+                },
+            },
+        ]);
+        expect(cards).toEqual([
+            {
+                title: '崇拜希特勒的人都是日本的汉奸走狗',
+                author: '上帝的子民º♬',
+                descInfo: '回复于2026-03-24 17:07',
+                commentCount: 12,
+                actionTexts: [],
+                threadId: '10596901456',
+                url: 'https://tieba.baidu.com/p/10596901456',
+            },
+        ]);
+    });
+});
+describe('buildTiebaPostItems', () => {
+    it('builds stable thread ids and urls from card props without page hops', () => {
+        const items = buildTiebaPostItems([
+            {
+                title: '我来说个事',
+                author: '暴躁的小伙子',
+                descInfo: '回复于2分钟前',
+                actionTexts: ['分享', '评论 5', '点赞 2'],
+                threadId: '10590564788',
+            },
+        ], 5);
+        expect(items).toEqual([
+            {
+                rank: 1,
+                title: '我来说个事',
+                author: '暴躁的小伙子',
+                replies: 5,
+                last_reply: '2分钟前',
+                id: '10590564788',
+                url: 'https://tieba.baidu.com/p/10590564788',
+            },
+        ]);
+    });
+    it('honors the public 20-item limit contract', () => {
+        const raw = Array.from({ length: 25 }, (_, index) => ({
+            title: `帖子 ${index + 1}`,
+            author: `作者 ${index + 1}`,
+            descInfo: '回复于刚刚',
+            actionTexts: ['分享', `评论 ${index + 1}`],
+            threadId: String(1000 + index),
+        }));
+        const items = buildTiebaPostItems(raw, 25);
+        expect(items).toHaveLength(20);
+        expect(items[19]).toMatchObject({
+            rank: 20,
+            id: '1019',
+            url: 'https://tieba.baidu.com/p/1019',
+        });
+    });
+    it('parses Chinese count units and keeps date-time last-reply text intact', () => {
+        const items = buildTiebaPostItems([
+            {
+                title: '复杂格式帖子',
+                author: '作者',
+                descInfo: '回复于03-29 11:35',
+                actionTexts: ['分享', '评论 1.2万'],
+                url: 'https://tieba.baidu.com/p/123456',
+            },
+        ], 5);
+        expect(items[0]).toMatchObject({
+            replies: 12000,
+            last_reply: '03-29 11:35',
+            id: '123456',
+            url: 'https://tieba.baidu.com/p/123456',
+        });
+    });
+});
+describe('buildTiebaSearchItems', () => {
+    it('keeps up to 20 search results when the page provides more than 10 cards', () => {
+        const raw = Array.from({ length: 25 }, (_, index) => ({
+            title: `结果 ${index + 1}`,
+            forum: '编程吧',
+            author: `作者 ${index + 1}`,
+            time: '2026-03-29',
+            snippet: `摘要 ${index + 1}`,
+            id: String(2000 + index),
+            url: `https://tieba.baidu.com/p/${2000 + index}`,
+        }));
+        const items = buildTiebaSearchItems(raw, 25);
+        expect(items).toHaveLength(20);
+        expect(items[19]).toMatchObject({
+            rank: 20,
+            id: '2019',
+            url: 'https://tieba.baidu.com/p/2019',
+        });
+    });
+    it('fills missing search ids from stable thread urls', () => {
+        const items = buildTiebaSearchItems([
+            {
+                title: '搜索结果',
+                forum: '编程吧',
+                author: '作者',
+                time: '2026-03-29 11:35',
+                snippet: '摘要',
+                id: '',
+                url: 'https://tieba.baidu.com/p/654321',
+            },
+        ], 5);
+        expect(items[0]).toMatchObject({
+            id: '654321',
+            url: 'https://tieba.baidu.com/p/654321',
+        });
+    });
+});
+describe('buildTiebaReadItems', () => {
+    it('prefers visible main-post fields and still keeps floor 1 for media-only threads', () => {
+        const items = buildTiebaReadItems({
+            mainPost: {
+                title: '刚开始读博士的人据说都这样',
+                author: '湖水之岸',
+                contentText: '',
+                structuredText: '',
+                visibleTime: '03-24',
+                structuredTime: 1774343231,
+                hasMedia: true,
+            },
+            replies: [],
+        }, { limit: 5, includeMainPost: true });
+        expect(items).toEqual([
+            {
+                floor: 1,
+                author: '湖水之岸',
+                content: '刚开始读博士的人据说都这样 [media]',
+                time: '03-24',
+            },
+        ]);
+    });
+    it('falls back to structured main-post data when visible text is missing', () => {
+        const items = buildTiebaReadItems({
+            mainPost: {
+                title: '标题',
+                author: '',
+                fallbackAuthor: '结构化作者',
+                contentText: '',
+                structuredText: '结构化正文',
+                visibleTime: '',
+                structuredTime: 1774343231,
+                hasMedia: false,
+            },
+            replies: [
+                { floor: 2, author: '回复者', content: '二楼内容', time: '第2楼 2026-03-25 12:34 广东' },
+            ],
+        }, { limit: 5, includeMainPost: true });
+        expect(items[0]).toMatchObject({
+            floor: 1,
+            author: '结构化作者',
+            content: '标题 结构化正文',
+            time: '2026-03-24 17:07',
+        });
+        expect(items[1]).toMatchObject({
+            floor: 2,
+            author: '回复者',
+            content: '二楼内容',
+            time: '2026-03-25 12:34',
+        });
+    });
+    it('strips trailing location metadata from reply times', () => {
+        const items = buildTiebaReadItems({
+            mainPost: {
+                title: '主楼',
+                author: '楼主',
+                contentText: '正文',
+                visibleTime: '03-24',
+            },
+            replies: [
+                { floor: 2, author: '二楼', content: '二楼内容', time: '第2楼 3小时前 福建' },
+                { floor: 3, author: '三楼', content: '三楼内容', time: '第3楼 刚刚 江苏' },
+            ],
+        }, { limit: 5, includeMainPost: false });
+        expect(items).toEqual([
+            {
+                floor: 2,
+                author: '二楼',
+                content: '二楼内容',
+                time: '3小时前',
+            },
+            {
+                floor: 3,
+                author: '三楼',
+                content: '三楼内容',
+                time: '刚刚',
+            },
+        ]);
+    });
+    it('counts limit as replies and skips main post on later pages', () => {
+        const items = buildTiebaReadItems({
+            mainPost: {
+                title: '主楼',
+                author: '楼主',
+                contentText: '正文',
+                visibleTime: '03-24',
+            },
+            replies: [
+                { floor: 2, author: '二楼', content: '二楼内容', time: '第2楼 03-25' },
+                { floor: 3, author: '三楼', content: '三楼内容', time: '第3楼 03-26' },
+                { floor: 4, author: '四楼', content: '四楼内容', time: '第4楼 03-27' },
+            ],
+        }, { limit: 2, includeMainPost: true });
+        expect(items).toHaveLength(3);
+        expect(items.map((item) => item.floor)).toEqual([1, 2, 3]);
+        const page2 = buildTiebaReadItems({
+            mainPost: {
+                title: '主楼',
+                author: '楼主',
+                contentText: '正文',
+                visibleTime: '03-24',
+            },
+            replies: [
+                { floor: 26, author: '二十六楼', content: '二十六楼内容', time: '第26楼 03-29' },
+            ],
+        }, { limit: 2, includeMainPost: false });
+        expect(page2.map((item) => item.floor)).toEqual([26]);
+    });
+});

package/dist/clis/v2ex/hot.yaml

@@ -16,10 +16,13 @@ pipeline:
       url: https://www.v2ex.com/api/topics/hot.json
 
   - map:
+      id: ${{ item.id }}
       rank: ${{ index + 1 }}
       title: ${{ item.title }}
+      node: ${{ item.node.title }}
       replies: ${{ item.replies }}
+      url: ${{ item.url }}
 
   - limit: ${{ args.limit }}
 
-columns: [rank, title, replies]
+columns: [id, rank, title, node, replies, url]

package/dist/clis/v2ex/latest.yaml

@@ -16,10 +16,13 @@ pipeline:
       url: https://www.v2ex.com/api/topics/latest.json
 
   - map:
+      id: ${{ item.id }}
       rank: ${{ index + 1 }}
       title: ${{ item.title }}
+      node: ${{ item.node.title }}
       replies: ${{ item.replies }}
+      url: ${{ item.url }}
 
   - limit: ${{ args.limit }}
 
-columns: [rank, title, replies]
+columns: [id, rank, title, node, replies, url]

package/dist/clis/v2ex/topic.yaml

@@ -19,10 +19,15 @@ pipeline:
         id: ${{ args.id }}
 
   - map:
+      id: ${{ item.id }}
       title: ${{ item.title }}
+      content: ${{ item.content }}
+      member: ${{ item.member.username }}
+      created: ${{ item.created }}
+      node: ${{ item.node.title }}
       replies: ${{ item.replies }}
       url: ${{ item.url }}
 
   - limit: 1
 
-columns: [title, replies, url]
+columns: [id, title, content, member, created, node, replies, url]

package/dist/clis/weixin/download.d.ts

@@ -23,7 +23,16 @@ export declare function extractWechatCreateTimeValue(htmlStr: string): string;
  * Extract the publish time from DOM text first, then fall back to numeric create_time values.
  */
 export declare function extractWechatPublishTime(publishTimeText: string | null | undefined, htmlStr: string): string;
+/**
+ * Detect WeChat anti-bot / verification gate pages before we try to parse the article.
+ */
+export declare function detectWechatAccessIssue(pageText: string | null | undefined, htmlStr: string): string;
+export declare function pickFirstWechatMetaText(...candidates: Array<string | null | undefined>): string;
 /**
  * Build a self-contained helper for execution inside page.evaluate().
  */
 export declare function buildExtractWechatPublishTimeJs(): string;
+/**
+ * Build a self-contained access-issue detector for execution inside page.evaluate().
+ */
+export declare function buildDetectWechatAccessIssueJs(): string;