publishport-opencli 1.8.5-pp.2 → 1.8.5-pp.21

package/clis/github-trending/repos.js

@@ -1,168 +1 @@
-// github-trending — repositories from https://github.com/trending (public HTML, no auth).
-import { cli, Strategy } from '@jackwener/opencli/registry';
-import { ArgumentError, CommandExecutionError, EmptyResultError } from '@jackwener/opencli/errors';
-
-const SINCE = {
-    daily: 'daily',
-    weekly: 'weekly',
-    monthly: 'monthly',
-};
-
-function decodeHtmlEntities(value) {
-    return String(value ?? '')
-        .replace(/&/g, '&')
-        .replace(/&lt;/g, '<')
-        .replace(/&gt;/g, '>')
-        .replace(/&quot;/g, '"')
-        .replace(/&#0?39;/g, "'")
-        .replace(/&#x27;/gi, "'")
-        .replace(/&nbsp;/g, ' ');
-}
-
-function stripTags(value) {
-    return String(value ?? '').replace(/<[^>]*>/g, '');
-}
-
-function parseCount(value) {
-    if (value == null) return null;
-    const digits = String(value).replace(/[,\s]/g, '');
-    if (!/^\d+$/.test(digits)) return null;
-    return Number(digits);
-}
-
-function escapeRegExp(value) {
-    return String(value).replace(/[.*+?^${}()|[\]\\]/g, '\\$&');
-}
-
-function assertCount(value, field, repo) {
-    const count = parseCount(value);
-    if (count == null) {
-        throw new CommandExecutionError(`github-trending parser drift: missing ${field} for ${repo}`);
-    }
-    return count;
-}
-
-function hasExplicitEmptyTrending(html) {
-    return /don.t have any trending repositories/i.test(stripTags(html))
-        || /no trending repositories/i.test(stripTags(html));
-}
-
-function parseTrendingHtml(html, limit) {
-    const blocks = Array.from(String(html ?? '').matchAll(/<article\b[^>]*class="[^"]*\bBox-row\b[^"]*"[^>]*>([\s\S]*?)<\/article>/g))
-        .map((match) => match[1]);
-    const rows = [];
-
-    if (blocks.length === 0) {
-        if (hasExplicitEmptyTrending(html)) return rows;
-        throw new CommandExecutionError('github-trending parser drift: no repository rows found');
-    }
-
-    for (const raw of blocks) {
-        const block = raw;
-
-        const nameMatch = block.match(/<h2\b[\s\S]*?href="\/([^"/?#]+\/[^"/?#]+)"/);
-        if (!nameMatch) {
-            throw new CommandExecutionError('github-trending parser drift: missing repository link');
-        }
-        const repo = decodeHtmlEntities(nameMatch[1]).trim();
-        if (!/^[A-Za-z0-9_.-]+\/[A-Za-z0-9_.-]+$/.test(repo)) {
-            throw new CommandExecutionError(`github-trending parser drift: invalid repository identity "${repo}"`);
-        }
-
-        const descMatch = block.match(/<p class="col-9 color-fg-muted[^"]*">([\s\S]*?)<\/p>/);
-        const description = descMatch
-            ? decodeHtmlEntities(stripTags(descMatch[1]).replace(/\s+/g, ' ')).trim()
-            : '';
-
-        const langMatch = block.match(/<span itemprop="programmingLanguage">([\s\S]*?)<\/span>/);
-        const language = langMatch ? decodeHtmlEntities(stripTags(langMatch[1])).trim() : null;
-
-        const escapedRepo = escapeRegExp(repo);
-        const starsMatch = block.match(new RegExp(`<a\\b[^>]*href="/${escapedRepo}/stargazers"[^>]*>([\\s\\S]*?)</a>`));
-        const forksMatch = block.match(new RegExp(`<a\\b[^>]*href="/${escapedRepo}/forks"[^>]*>([\\s\\S]*?)</a>`));
-        const sinceMatch = block.match(/([\d,]+)\s+stars\s+(?:today|this week|this month)/i);
-
-        rows.push({
-            repo,
-            description,
-            language,
-            stars: assertCount(starsMatch ? stripTags(starsMatch[1]) : null, 'stars', repo),
-            forks: assertCount(forksMatch ? stripTags(forksMatch[1]) : null, 'forks', repo),
-            starsSince: assertCount(sinceMatch?.[1], 'period stars', repo),
-            url: `https://github.com/${repo}`,
-        });
-        if (rows.length >= limit) break;
-    }
-    return rows;
-}
-
-cli({
-    site: 'github-trending',
-    name: 'repos',
-    access: 'read',
-    description: 'GitHub Trending repositories (public, no login). Filter by --language and --since.',
-    domain: 'github.com',
-    strategy: Strategy.PUBLIC,
-    browser: false,
-    args: [
-        { name: 'since', type: 'string', default: 'daily', help: 'Time range: daily / weekly / monthly' },
-        { name: 'language', type: 'string', default: '', help: 'Filter by programming language slug, e.g. python, rust, "c++"' },
-        { name: 'limit', type: 'int', default: 25, help: 'Number of repositories to return (max 25)' },
-    ],
-    columns: ['rank', 'repo', 'description', 'language', 'stars', 'forks', 'starsSince', 'url'],
-    func: async (args) => {
-        const sinceKey = String(args.since ?? 'daily').toLowerCase();
-        const since = SINCE[sinceKey];
-        if (!since) {
-            throw new ArgumentError(`Unknown --since "${sinceKey}". Valid: ${Object.keys(SINCE).join(', ')}`);
-        }
-
-        const n = Number(args.limit ?? 25);
-        if (!Number.isInteger(n) || n <= 0) {
-            throw new ArgumentError('--limit must be a positive integer');
-        }
-        if (n > 25) {
-            throw new ArgumentError('--limit must be <= 25 (GitHub Trending lists at most 25 repositories)');
-        }
-        const limit = n;
-
-        const language = String(args.language ?? '').trim();
-        const path = language ? `/trending/${encodeURIComponent(language)}` : '/trending';
-        const url = new URL(`https://github.com${path}`);
-        url.searchParams.set('since', since);
-
-        let resp;
-        try {
-            resp = await fetch(url, {
-                headers: {
-                    'User-Agent': 'Mozilla/5.0 (compatible; opencli/github-trending)',
-                    Accept: 'text/html',
-                },
-            });
-        } catch (error) {
-            throw new CommandExecutionError(`github-trending request failed: ${error?.message || error}`);
-        }
-        if (!resp.ok) {
-            throw new CommandExecutionError(`github-trending request failed: HTTP ${resp.status}`);
-        }
-
-        const html = await resp.text();
-        const rows = parseTrendingHtml(html, limit);
-        if (rows.length === 0) {
-            throw new EmptyResultError('github-trending', language
-                ? `no trending repositories for language "${language}" (${since})`
-                : `no trending repositories (${since})`);
-        }
-
-        return rows.map((row, index) => ({
-            rank: index + 1,
-            repo: row.repo,
-            description: row.description,
-            language: row.language,
-            stars: row.stars,
-            forks: row.forks,
-            starsSince: row.starsSince,
-            url: row.url,
-        }));
-    },
-});
+import{cli as $,Strategy as E}from"@jackwener/opencli/registry";import{ArgumentError as d,CommandExecutionError as c,EmptyResultError as x}from"@jackwener/opencli/errors";const k={daily:"daily",weekly:"weekly",monthly:"monthly"};function f(t){return String(t??"").replace(/&amp;/g,"&").replace(/&lt;/g,"<").replace(/&gt;/g,">").replace(/&quot;/g,'"').replace(/&#0?39;/g,"'").replace(/&#x27;/gi,"'").replace(/&nbsp;/g," ")}function g(t){return String(t??"").replace(/<[^>]*>/g,"")}function T(t){if(t==null)return null;const s=String(t).replace(/[,\s]/g,"");if(!/^\d+$/.test(s))return null;return Number(s)}function M(t){return String(t).replace(/[.*+?^${}()|[\]\\]/g,"\\$&")}function b(t,s,o){const e=T(t);if(e==null)throw new c(`github-trending parser drift: missing ${s} for ${o}`);return e}function A(t){return/don.t have any trending repositories/i.test(g(t))||/no trending repositories/i.test(g(t))}function C(t,s){const o=Array.from(String(t??"").matchAll(/<article\b[^>]*class="[^"]*\bBox-row\b[^"]*"[^>]*>([\s\S]*?)<\/article>/g)).map((l)=>l[1]),e=[];if(o.length===0){if(A(t))return e;throw new c("github-trending parser drift: no repository rows found")}for(const l of o){const n=l,p=n.match(/<h2\b[\s\S]*?href="\/([^"/?#]+\/[^"/?#]+)"/);if(!p)throw new c("github-trending parser drift: missing repository link");const i=f(p[1]).trim();if(!/^[A-Za-z0-9_.-]+\/[A-Za-z0-9_.-]+$/.test(i))throw new c(`github-trending parser drift: invalid repository identity "${i}"`);const a=n.match(/<p class="col-9 color-fg-muted[^"]*">([\s\S]*?)<\/p>/),h=a?f(g(a[1]).replace(/\s+/g," ")).trim():"",u=n.match(/<span itemprop="programmingLanguage">([\s\S]*?)<\/span>/),r=u?f(g(u[1])).trim():null,m=M(i),y=n.match(new RegExp(`<a\\b[^>]*href="/${m}/stargazers"[^>]*>([\\s\\S]*?)</a>`)),w=n.match(new RegExp(`<a\\b[^>]*href="/${m}/forks"[^>]*>([\\s\\S]*?)</a>`)),S=n.match(/([\d,]+)\s+stars\s+(?:today|this week|this month)/i);e.push({repo:i,description:h,language:r,stars:b(y?g(y[1]):null,"stars",i),forks:b(w?g(w[1]):null,"forks",i),starsSince:b(S?.[1],"period stars",i),url:`https://github.com/${i}`});if(e.length>=s)break}return e}$({site:"github-trending",name:"repos",access:"read",description:"GitHub Trending repositories (public, no login). Filter by --language and --since.",domain:"github.com",strategy:E.PUBLIC,browser:!1,args:[{name:"since",type:"string",default:"daily",help:"Time range: daily / weekly / monthly"},{name:"language",type:"string",default:"",help:'Filter by programming language slug, e.g. python, rust, "c++"'},{name:"limit",type:"int",default:25,help:"Number of repositories to return (max 25)"}],columns:["rank","repo","description","language","stars","forks","starsSince","url"],func:async(t)=>{const s=String(t.since??"daily").toLowerCase(),o=k[s];if(!o)throw new d(`Unknown --since "${s}". Valid: ${Object.keys(k).join(", ")}`);const e=Number(t.limit??25);if(!Number.isInteger(e)||e<=0)throw new d("--limit must be a positive integer");if(e>25)throw new d("--limit must be <= 25 (GitHub Trending lists at most 25 repositories)");const l=e,n=String(t.language??"").trim(),p=n?`/trending/${encodeURIComponent(n)}`:"/trending",i=new URL(`https://github.com${p}`);i.searchParams.set("since",o);let a;try{a=await fetch(i,{headers:{"User-Agent":"Mozilla/5.0 (compatible; opencli/github-trending)",Accept:"text/html"}})}catch(r){throw new c(`github-trending request failed: ${r?.message||r}`)}if(!a.ok)throw new c(`github-trending request failed: HTTP ${a.status}`);const h=await a.text(),u=C(h,l);if(u.length===0)throw new x("github-trending",n?`no trending repositories for language "${n}" (${o})`:`no trending repositories (${o})`);return u.map((r,m)=>({rank:m+1,repo:r.repo,description:r.description,language:r.language,stars:r.stars,forks:r.forks,starsSince:r.starsSince,url:r.url}))}});

package/clis/google/news.js

@@ -1,59 +1 @@
-/**
- * Google News via public RSS feed.
- * Supports top stories (no keyword) and search (with keyword).
- */
-import { cli, Strategy } from '@jackwener/opencli/registry';
-import { CliError } from '@jackwener/opencli/errors';
-import { parseRssItems } from './utils.js';
-cli({
-    site: 'google',
-    name: 'news',
-    access: 'read',
-    description: 'Get Google News headlines',
-    strategy: Strategy.PUBLIC,
-    browser: false,
-    args: [
-        { name: 'keyword', positional: true, help: 'Search query (omit for top stories)' },
-        { name: 'limit', type: 'int', default: 10, help: 'Number of results' },
-        { name: 'lang', default: 'en', help: 'Language short code (e.g. en, zh)' },
-        { name: 'region', default: 'US', help: 'Region code (e.g. US, CN)' },
-    ],
-    columns: ['title', 'source', 'date', 'url'],
-    func: async (args) => {
-        const limit = Math.max(1, Math.min(Number(args.limit), 100));
-        const lang = encodeURIComponent(args.lang);
-        const region = encodeURIComponent(args.region);
-        const ceid = `${args.region}:${args.lang}`;
-        // Top stories or search
-        const base = args.keyword
-            ? `https://news.google.com/rss/search?q=${encodeURIComponent(args.keyword)}&hl=${lang}&gl=${region}&ceid=${ceid}`
-            : `https://news.google.com/rss?hl=${lang}&gl=${region}&ceid=${ceid}`;
-        const resp = await fetch(base);
-        if (!resp.ok) {
-            throw new CliError('FETCH_ERROR', `HTTP ${resp.status}`, 'Check your network connection');
-        }
-        const xml = await resp.text();
-        const items = parseRssItems(xml, ['title', 'link', 'pubDate', 'source']);
-        if (!items.length) {
-            throw new CliError('NOT_FOUND', 'No news articles found', 'Try a different keyword or region');
-        }
-        return items.slice(0, limit).map(item => {
-            // Extract source: prefer <source> element, fallback to parsing title
-            let title = item['title'] || '';
-            let source = item['source'] || '';
-            if (!source) {
-                const idx = title.lastIndexOf(' - ');
-                if (idx !== -1) {
-                    source = title.slice(idx + 3);
-                    title = title.slice(0, idx);
-                }
-            }
-            return {
-                title,
-                source,
-                date: item['pubDate'] || '',
-                url: item['link'] || '',
-            };
-        });
-    },
-});
+import{cli as N,Strategy as O}from"@jackwener/opencli/registry";import{CliError as J}from"@jackwener/opencli/errors";import{parseRssItems as P}from"./utils.js";N({site:"google",name:"news",access:"read",description:"Get Google News headlines",strategy:O.PUBLIC,browser:!1,args:[{name:"keyword",positional:!0,help:"Search query (omit for top stories)"},{name:"limit",type:"int",default:10,help:"Number of results"},{name:"lang",default:"en",help:"Language short code (e.g. en, zh)"},{name:"region",default:"US",help:"Region code (e.g. US, CN)"}],columns:["title","source","date","url"],func:async(h)=>{const K=Math.max(1,Math.min(Number(h.limit),100)),D=encodeURIComponent(h.lang),F=encodeURIComponent(h.region),G=`${h.region}:${h.lang}`,L=h.keyword?`https://news.google.com/rss/search?q=${encodeURIComponent(h.keyword)}&hl=${D}&gl=${F}&ceid=${G}`:`https://news.google.com/rss?hl=${D}&gl=${F}&ceid=${G}`,z=await fetch(L);if(!z.ok)throw new J("FETCH_ERROR",`HTTP ${z.status}`,"Check your network connection");const M=await z.text(),H=P(M,["title","link","pubDate","source"]);if(!H.length)throw new J("NOT_FOUND","No news articles found","Try a different keyword or region");return H.slice(0,K).map((v)=>{let q=v.title||"",A=v.source||"";if(!A){const B=q.lastIndexOf(" - ");if(B!==-1){A=q.slice(B+3);q=q.slice(0,B)}}return{title:q,source:A,date:v.pubDate||"",url:v.link||""}})}});

package/clis/google/search.js

@@ -1,45 +1,4 @@
-/**
- * Google Web Search via browser DOM extraction.
- * Uses browser mode to navigate google.com and extract results from the DOM.
- *
- * Extraction strategy (2026-03): Google no longer uses `.g` class containers.
- * Instead, we find all `a` tags containing `h3` within `#rso`, then walk up
- * to the result container (`div.tF2Cxc` or closest `div[data-hveid]`) to find
- * snippets. This approach is resilient to class name changes.
- */
-import { cli, Strategy } from '@jackwener/opencli/registry';
-import { CliError } from '@jackwener/opencli/errors';
-cli({
-    site: 'google',
-    name: 'search',
-    access: 'read',
-    description: 'Search Google',
-    domain: 'google.com',
-    strategy: Strategy.PUBLIC,
-    browser: true,
-    args: [
-        { name: 'keyword', positional: true, required: true, help: 'Search query' },
-        { name: 'limit', type: 'int', default: 10, help: 'Number of results (1-100)' },
-        { name: 'lang', default: 'en', help: 'Language short code (e.g. en, zh)' },
-    ],
-    columns: ['type', 'title', 'url', 'snippet'],
-    func: async (page, args) => {
-        const limit = Math.max(1, Math.min(Number(args.limit), 100));
-        const keyword = encodeURIComponent(args.keyword);
-        const lang = encodeURIComponent(args.lang);
-        const url = `https://www.google.com/search?q=${keyword}&hl=${lang}&num=${limit}`;
-        await page.goto(url);
-        // Wait until at least one SERP title link is present. On Chrome 148 /
-        // Linux Wayland, DOM stability can be reached before #rso anchors are
-        // populated, making browser execution look visually correct while the
-        // adapter extracts an empty array.
-        try {
-            await page.wait({ selector: '#rso a h3', timeout: 5 });
-        }
-        catch {
-            await page.wait(2);
-        }
-        const wrapper = await page.evaluate(`
+import{cli as D,Strategy as F}from"@jackwener/opencli/registry";import{CliError as G}from"@jackwener/opencli/errors";D({site:"google",name:"search",access:"read",description:"Search Google",domain:"google.com",strategy:F.PUBLIC,browser:!0,args:[{name:"keyword",positional:!0,required:!0,help:"Search query"},{name:"limit",type:"int",default:10,help:"Number of results (1-100)"},{name:"lang",default:"en",help:"Language short code (e.g. en, zh)"}],columns:["type","title","url","snippet"],func:async(b,f)=>{const v=Math.max(1,Math.min(Number(f.limit),100)),z=encodeURIComponent(f.keyword),A=encodeURIComponent(f.lang),B=`https://www.google.com/search?q=${z}&hl=${A}&num=${v}`;await b.goto(B);try{await b.wait({selector:"#rso a h3",timeout:5})}catch{await b.wait(2)}const h=await b.evaluate(`
       (function() {
         var results = [];
         var seenUrls = {};
@@ -98,7 +57,7 @@ cli({
             if (text.length < 40 || text.length > 500) continue;
             if (text === titleText) continue;
             // Skip URL breadcrumbs (e.g. "https://example.com › path..." or "Site Namehttps://...")
-            if (text.indexOf('\u203A') !== -1) continue;
+            if (text.indexOf('›') !== -1) continue;
             if (new RegExp('https?://').test(text.slice(0, 60))) continue;
             snippetText = text;
             break;
@@ -128,11 +87,4 @@ cli({
 
         return {items: results};
       })()
-    `);
-        const results = (wrapper && wrapper.items) || [];
-        if (results.length === 0) {
-            throw new CliError('NOT_FOUND', 'No search results found', 'Try a different keyword or check for CAPTCHA');
-        }
-        return results;
-    },
-});
+    `),q=h&&h.items||[];if(q.length===0)throw new G("NOT_FOUND","No search results found","Try a different keyword or check for CAPTCHA");return q}});

package/clis/google/suggest.js

@@ -1,35 +1 @@
-/**
- * Google Search Suggestions via public JSON API.
- * Uses suggestqueries.google.com with client=firefox for pure JSON (not JSONP).
- */
-import { cli, Strategy } from '@jackwener/opencli/registry';
-import { CliError } from '@jackwener/opencli/errors';
-cli({
-    site: 'google',
-    name: 'suggest',
-    access: 'read',
-    description: 'Get Google search suggestions',
-    strategy: Strategy.PUBLIC,
-    browser: false,
-    args: [
-        { name: 'keyword', positional: true, required: true, help: 'Search query' },
-        { name: 'lang', default: 'zh-CN', help: 'Language code' },
-    ],
-    columns: ['suggestion'],
-    func: async (args) => {
-        const keyword = encodeURIComponent(args.keyword);
-        const lang = encodeURIComponent(args.lang);
-        const url = `https://suggestqueries.google.com/complete/search?client=firefox&q=${keyword}&hl=${lang}`;
-        const resp = await fetch(url);
-        if (!resp.ok) {
-            throw new CliError('FETCH_ERROR', `HTTP ${resp.status}`, 'Check your network connection');
-        }
-        const data = await resp.json();
-        // Response format: ["query", ["suggestion1", "suggestion2", ...]]
-        const suggestions = Array.isArray(data) && Array.isArray(data[1]) ? data[1] : [];
-        if (!suggestions.length) {
-            throw new CliError('NOT_FOUND', 'No suggestions found', 'Try a different keyword');
-        }
-        return suggestions.map(s => ({ suggestion: s }));
-    },
-});
+import{cli as G,Strategy as H}from"@jackwener/opencli/registry";import{CliError as z}from"@jackwener/opencli/errors";G({site:"google",name:"suggest",access:"read",description:"Get Google search suggestions",strategy:H.PUBLIC,browser:!1,args:[{name:"keyword",positional:!0,required:!0,help:"Search query"},{name:"lang",default:"zh-CN",help:"Language code"}],columns:["suggestion"],func:async(v)=>{const A=encodeURIComponent(v.keyword),B=encodeURIComponent(v.lang),D=`https://suggestqueries.google.com/complete/search?client=firefox&q=${A}&hl=${B}`,b=await fetch(D);if(!b.ok)throw new z("FETCH_ERROR",`HTTP ${b.status}`,"Check your network connection");const h=await b.json(),x=Array.isArray(h)&&Array.isArray(h[1])?h[1]:[];if(!x.length)throw new z("NOT_FOUND","No suggestions found","Try a different keyword");return x.map((F)=>({suggestion:F}))}});

package/clis/google/trends.js

@@ -1,39 +1 @@
-/**
- * Google Trends via public RSS feed.
- * Shows daily trending searches for a given region.
- */
-import { cli, Strategy } from '@jackwener/opencli/registry';
-import { CliError } from '@jackwener/opencli/errors';
-import { parseRssItems } from './utils.js';
-cli({
-    site: 'google',
-    name: 'trends',
-    access: 'read',
-    description: 'Get Google Trends daily trending searches',
-    strategy: Strategy.PUBLIC,
-    browser: false,
-    args: [
-        { name: 'region', default: 'US', help: 'Region code (e.g. US, CN, JP)' },
-        { name: 'limit', type: 'int', default: 20, help: 'Number of results' },
-    ],
-    columns: ['title', 'traffic', 'date'],
-    func: async (args) => {
-        const limit = Math.max(1, Math.min(Number(args.limit), 100));
-        const region = encodeURIComponent(args.region);
-        const url = `https://trends.google.com/trending/rss?geo=${region}`;
-        const resp = await fetch(url);
-        if (!resp.ok) {
-            throw new CliError('FETCH_ERROR', `HTTP ${resp.status}`, 'Check your network connection or region code');
-        }
-        const xml = await resp.text();
-        const items = parseRssItems(xml, ['title', 'pubDate', 'ht:approx_traffic']);
-        if (!items.length) {
-            throw new CliError('NOT_FOUND', 'No trending data found', 'Try a different region code');
-        }
-        return items.slice(0, limit).map(item => ({
-            title: item['title'],
-            traffic: item['ht:approx_traffic'], // raw string e.g. "1,000,000+", no numeric conversion
-            date: item['pubDate'],
-        }));
-    },
-});
+import{cli as D,Strategy as F}from"@jackwener/opencli/registry";import{CliError as q}from"@jackwener/opencli/errors";import{parseRssItems as G}from"./utils.js";D({site:"google",name:"trends",access:"read",description:"Get Google Trends daily trending searches",strategy:F.PUBLIC,browser:!1,args:[{name:"region",default:"US",help:"Region code (e.g. US, CN, JP)"},{name:"limit",type:"int",default:20,help:"Number of results"}],columns:["title","traffic","date"],func:async(f)=>{const z=Math.max(1,Math.min(Number(f.limit),100)),A=`https://trends.google.com/trending/rss?geo=${encodeURIComponent(f.region)}`,b=await fetch(A);if(!b.ok)throw new q("FETCH_ERROR",`HTTP ${b.status}`,"Check your network connection or region code");const B=await b.text(),h=G(B,["title","pubDate","ht:approx_traffic"]);if(!h.length)throw new q("NOT_FOUND","No trending data found","Try a different region code");return h.slice(0,z).map((d)=>({title:d.title,traffic:d["ht:approx_traffic"],date:d.pubDate}))}});

package/clis/google/utils.js

@@ -1,23 +1 @@
-/**
- * Google adapter utilities.
- * Shared RSS parser for news and trends commands.
- */
-/**
- * Parse RSS XML by splitting into <item> blocks, then extracting fields per block.
- * Handles both plain text and CDATA-wrapped content.
- */
-export function parseRssItems(xml, fields) {
-    const items = xml.match(/<item>([\s\S]*?)<\/item>/g) || [];
-    return items.map(block => {
-        const record = {};
-        for (const field of fields) {
-            // Escape regex special characters in field name (e.g. ht:approx_traffic is safe, but defensive)
-            const escaped = field.replace(/[.*+?^${}()|[\]\\]/g, '\\$&');
-            // Handle tags with attributes (e.g. <source url="...">text</source>) and CDATA wrapping
-            // (?:\s[^>]*)? ensures we don't match prefix tags (e.g. <sourceUrl> when looking for <source>)
-            const match = block.match(new RegExp(`<${escaped}(?:\\s[^>]*)?>(?:<!\\[CDATA\\[)?([\\s\\S]*?)(?:\\]\\]>)?</${escaped}>`));
-            record[field] = match ? match[1].trim() : '';
-        }
-        return record;
-    });
-}
+export function parseRssItems(z,A){return(z.match(/<item>([\s\S]*?)<\/item>/g)||[]).map((B)=>{const j={};for(const q of A){const v=q.replace(/[.*+?^${}()|[\]\\]/g,"\\$&"),y=B.match(new RegExp(`<${v}(?:\\s[^>]*)?>(?:<!\\[CDATA\\[)?([\\s\\S]*?)(?:\\]\\]>)?</${v}>`));j[q]=y?y[1].trim():""}return j})}

package/clis/google-scholar/cite.js

@@ -1,74 +1,20 @@
-import { cli, Strategy } from '@jackwener/opencli/registry';
-import { CommandExecutionError } from '@jackwener/opencli/errors';
-import { requireNonEmptyQuery } from '../_shared/common.js';
-
-cli({
-    site: 'google-scholar',
-    name: 'cite',
-    access: 'read',
-    description: 'Get citation for a Google Scholar paper',
-    domain: 'scholar.google.com',
-    strategy: Strategy.PUBLIC,
-    browser: true,
-    args: [
-        { name: 'query', positional: true, required: true, help: 'Paper title to search for' },
-        { name: 'style', default: 'bibtex', choices: ['bibtex', 'endnote', 'refman', 'refworks'], help: 'Citation format' },
-        { name: 'index', type: 'int', default: 1, help: 'Which search result to cite (1-based)' },
-    ],
-    columns: ['title', 'format', 'citation'],
-    func: async (page, kwargs) => {
-        const query = requireNonEmptyQuery(kwargs.query);
-        const format = kwargs.style || 'bibtex';
-        const index = Math.max(1, kwargs.index || 1) - 1;
-
-        await page.goto(`https://scholar.google.com/scholar?q=${encodeURIComponent(query)}&hl=en`);
-        await page.wait(3);
-
-        const clicked = await page.evaluate(`(() => {
+import{cli as u,Strategy as m}from"@jackwener/opencli/registry";import{CommandExecutionError as n}from"@jackwener/opencli/errors";import{requireNonEmptyQuery as f}from"../_shared/common.js";u({site:"google-scholar",name:"cite",access:"read",description:"Get citation for a Google Scholar paper",domain:"scholar.google.com",strategy:m.PUBLIC,browser:!0,args:[{name:"query",positional:!0,required:!0,help:"Paper title to search for"},{name:"style",default:"bibtex",choices:["bibtex","endnote","refman","refworks"],help:"Citation format"},{name:"index",type:"int",default:1,help:"Which search result to cite (1-based)"}],columns:["title","format","citation"],func:async(t,r)=>{const s=f(r.query),a=r.style||"bibtex",e=Math.max(1,r.index||1)-1;await t.goto(`https://scholar.google.com/scholar?q=${encodeURIComponent(s)}&hl=en`);await t.wait(3);const o=await t.evaluate(`(() => {
             var cites = document.querySelectorAll('a.gs_or_cit');
-            if (cites.length <= ${index}) return { ok: false, reason: 'result not found at index ${index + 1}' };
-            var titleEl = document.querySelectorAll('.gs_r.gs_or.gs_scl')[${index}];
+            if (cites.length <= ${e}) return { ok: false, reason: 'result not found at index ${e+1}' };
+            var titleEl = document.querySelectorAll('.gs_r.gs_or.gs_scl')[${e}];
             var title = '';
             if (titleEl) {
                 var t = titleEl.querySelector('.gs_rt a, h3 a');
                 title = t ? t.textContent.trim() : '';
             }
-            cites[${index}].click();
+            cites[${e}].click();
             return { ok: true, title: title };
-        })()`);
-
-        if (!clicked?.ok) {
-            throw new CommandExecutionError(clicked?.reason || `Could not find search result at index ${index + 1}`);
-        }
-
-        await page.wait(2);
-
-        const formatMap = { bibtex: 'BibTeX', endnote: 'EndNote', refman: 'RefMan', refworks: 'RefWorks' };
-        const formatLabel = formatMap[format] || 'BibTeX';
-
-        const citeUrl = await page.evaluate(`(() => {
+        })()`);if(!o?.ok)throw new n(o?.reason||`Could not find search result at index ${e+1}`);await t.wait(2);const i={bibtex:"BibTeX",endnote:"EndNote",refman:"RefMan",refworks:"RefWorks"}[a]||"BibTeX",l=await t.evaluate(`(() => {
             var links = document.querySelectorAll('#gs_cit a.gs_citi');
             for (var i = 0; i < links.length; i++) {
-                if (links[i].textContent.trim() === '${formatLabel}') return links[i].href;
+                if (links[i].textContent.trim() === '${i}') return links[i].href;
             }
             return null;
-        })()`);
-
-        if (!citeUrl) {
-            throw new CommandExecutionError(`Could not find ${formatLabel} citation link for result ${index + 1}`);
-        }
-
-        await page.goto(citeUrl);
-        await page.wait(2);
-
-        const citation = await page.evaluate(`(() => {
+        })()`);if(!l)throw new n(`Could not find ${i} citation link for result ${e+1}`);await t.goto(l);await t.wait(2);const c=await t.evaluate(`(() => {
             return (document.body.innerText || '').trim();
-        })()`);
-
-        if (!citation) {
-            throw new CommandExecutionError(`${formatLabel} citation page returned an empty response`);
-        }
-
-        return [{ title: clicked.title, format: format, citation }];
-    },
-});
+        })()`);if(!c)throw new n(`${i} citation page returned an empty response`);return[{title:o.title,format:a,citation:c}]}});

package/clis/google-scholar/profile.js

@@ -1,45 +1,8 @@
-import { cli, Strategy } from '@jackwener/opencli/registry';
-import { CommandExecutionError } from '@jackwener/opencli/errors';
-import { clampInt, requireNonEmptyQuery } from '../_shared/common.js';
-
-cli({
-    site: 'google-scholar',
-    name: 'profile',
-    access: 'read',
-    description: 'View a Google Scholar author profile',
-    domain: 'scholar.google.com',
-    strategy: Strategy.PUBLIC,
-    browser: true,
-    args: [
-        { name: 'author', positional: true, required: true, help: 'Author name or Scholar user ID (e.g. JicYPdAAAAAJ)' },
-        { name: 'limit', type: 'int', default: 10, help: 'Max papers to show (max 20)' },
-    ],
-    columns: ['rank', 'title', 'cited', 'year'],
-    func: async (page, kwargs) => {
-        const author = requireNonEmptyQuery(kwargs.author, 'author');
-        const limit = clampInt(kwargs.limit, 10, 1, 20);
-
-        const isUserId = /^[A-Za-z0-9_-]{12}$/.test(author);
-        if (isUserId) {
-            await page.goto(`https://scholar.google.com/citations?user=${author}&hl=en&sortby=citedby`);
-        } else {
-            await page.goto(`https://scholar.google.com/citations?view_op=search_authors&mauthors=${encodeURIComponent(author)}&hl=en`);
-            await page.wait(3);
-
-            const profileClicked = await page.evaluate(`(() => {
+import{cli as n,Strategy as s}from"@jackwener/opencli/registry";import{CommandExecutionError as o}from"@jackwener/opencli/errors";import{clampInt as l,requireNonEmptyQuery as c}from"../_shared/common.js";n({site:"google-scholar",name:"profile",access:"read",description:"View a Google Scholar author profile",domain:"scholar.google.com",strategy:s.PUBLIC,browser:!0,args:[{name:"author",positional:!0,required:!0,help:"Author name or Scholar user ID (e.g. JicYPdAAAAAJ)"},{name:"limit",type:"int",default:10,help:"Max papers to show (max 20)"}],columns:["rank","title","cited","year"],func:async(e,a)=>{const r=c(a.author,"author"),i=l(a.limit,10,1,20);if(/^[A-Za-z0-9_-]{12}$/.test(r))await e.goto(`https://scholar.google.com/citations?user=${r}&hl=en&sortby=citedby`);else{await e.goto(`https://scholar.google.com/citations?view_op=search_authors&mauthors=${encodeURIComponent(r)}&hl=en`);await e.wait(3);if(!await e.evaluate(`(() => {
                 var link = document.querySelector('.gs_ai_pho, .gsc_oai_photo, a[href*="citations?user="]');
                 if (link) { link.click(); return true; }
                 return false;
-            })()`);
-
-            if (!profileClicked) {
-                throw new CommandExecutionError(`No profile found for: ${author}`);
-            }
-        }
-
-        await page.wait(3);
-
-        const data = await page.evaluate(`(() => {
+            })()`))throw new o(`No profile found for: ${r}`)}await e.wait(3);const t=await e.evaluate(`(() => {
             var name = (document.querySelector('#gsc_prf_in') || {}).textContent || '';
             var affiliation = (document.querySelector('.gsc_prf_il') || {}).textContent || '';
 
@@ -50,7 +13,7 @@ cli({
 
             var papers = [];
             var rows = document.querySelectorAll('#gsc_a_b .gsc_a_tr');
-            for (var i = 0; i < rows.length && i < ${limit}; i++) {
+            for (var i = 0; i < rows.length && i < ${i}; i++) {
                 var titleEl = rows[i].querySelector('.gsc_a_at');
                 var citedEl = rows[i].querySelector('.gsc_a_ac');
                 var yearEl = rows[i].querySelector('.gsc_a_y span');
@@ -70,23 +33,4 @@ cli({
                 i10Index: i10Index,
                 papers: papers,
             };
-        })()`);
-
-        if (!data?.name) {
-            throw new CommandExecutionError(`Could not load Google Scholar profile for: ${author}`);
-        }
-
-        if (!data.papers || data.papers.length === 0) {
-            throw new CommandExecutionError(`No papers found for: ${data.name || author}`);
-        }
-
-        const summary = {
-            rank: 0,
-            title: data.name + (data.affiliation ? ' (' + data.affiliation + ')' : ''),
-            cited: 'h=' + data.hIndex + ' i10=' + data.i10Index + ' total=' + data.citations,
-            year: '-',
-        };
-
-        return [summary, ...data.papers];
-    },
-});
+        })()`);if(!t?.name)throw new o(`Could not load Google Scholar profile for: ${r}`);if(!t.papers||t.papers.length===0)throw new o(`No papers found for: ${t.name||r}`);return[{rank:0,title:t.name+(t.affiliation?" ("+t.affiliation+")":""),cited:"h="+t.hIndex+" i10="+t.i10Index+" total="+t.citations,year:"-"},...t.papers]}});

package/clis/google-scholar/search.js

@@ -1,30 +1,4 @@
-import { cli, Strategy } from '@jackwener/opencli/registry';
-import { CommandExecutionError, EmptyResultError } from '@jackwener/opencli/errors';
-import { clampInt, requireNonEmptyQuery } from '../_shared/common.js';
-
-cli({
-    site: 'google-scholar',
-    name: 'search',
-    access: 'read',
-    description: 'Google Scholar 学术搜索',
-    domain: 'scholar.google.com',
-    strategy: Strategy.PUBLIC,
-    browser: true,
-    args: [
-        { name: 'query', positional: true, required: true, help: '搜索关键词' },
-        { name: 'limit', type: 'int', default: 10, help: '返回结果数量 (max 20)' },
-    ],
-    columns: ['rank', 'title', 'authors', 'source', 'year', 'cited', 'url'],
-    func: async (page, kwargs) => {
-        const limit = clampInt(kwargs.limit, 10, 1, 20);
-        const query = requireNonEmptyQuery(kwargs.query);
-        await page.goto(`https://scholar.google.com/scholar?q=${encodeURIComponent(query)}&hl=zh-CN`);
-        try {
-            await page.wait({ selector: '.gs_r.gs_or.gs_scl', timeout: 5 });
-        } catch {
-            await page.wait(3);
-        }
-        const wrapper = await page.evaluate(`
+import{cli as l,Strategy as n}from"@jackwener/opencli/registry";import{CommandExecutionError as o,EmptyResultError as a}from"@jackwener/opencli/errors";import{clampInt as i,requireNonEmptyQuery as u}from"../_shared/common.js";l({site:"google-scholar",name:"search",access:"read",description:"Google Scholar 学术搜索",domain:"scholar.google.com",strategy:n.PUBLIC,browser:!0,args:[{name:"query",positional:!0,required:!0,help:"搜索关键词"},{name:"limit",type:"int",default:10,help:"返回结果数量 (max 20)"}],columns:["rank","title","authors","source","year","cited","url"],func:async(t,r)=>{const s=i(r.limit,10,1,20),c=u(r.query);await t.goto(`https://scholar.google.com/scholar?q=${encodeURIComponent(c)}&hl=zh-CN`);try{await t.wait({selector:".gs_r.gs_or.gs_scl",timeout:5})}catch{await t.wait(3)}const e=await t.evaluate(`
       (() => {
         const normalize = v => (v || '').replace(/\\s+/g, ' ').trim();
         const results = [];
@@ -54,20 +28,8 @@ cli({
             cited,
             url,
           });
-          if (results.length >= ${limit}) break;
+          if (results.length >= ${s}) break;
         }
         return { items: results, resultCount: resultCards.length };
       })()
-    `);
-        if (!wrapper || typeof wrapper !== 'object' || !Array.isArray(wrapper.items)) {
-            throw new CommandExecutionError('Google Scholar search returned an unexpected payload shape');
-        }
-        if (wrapper.items.length === 0) {
-            if (Number(wrapper.resultCount) > 0) {
-                throw new CommandExecutionError('Google Scholar result cards were present but no rows could be extracted');
-            }
-            throw new EmptyResultError('google-scholar/search', 'Try a different query or check whether Google Scholar returned a CAPTCHA.');
-        }
-        return wrapper.items;
-    },
-});
+    `);if(!e||typeof e!=="object"||!Array.isArray(e.items))throw new o("Google Scholar search returned an unexpected payload shape");if(e.items.length===0){if(Number(e.resultCount)>0)throw new o("Google Scholar result cards were present but no rows could be extracted");throw new a("google-scholar/search","Try a different query or check whether Google Scholar returned a CAPTCHA.")}return e.items}});