diff --git a/package-lock.json b/package-lock.json index 4621044..39d05ef 100644 --- a/package-lock.json +++ b/package-lock.json @@ -14,6 +14,7 @@ "axios": "^1.13.2", "bcryptjs": "^3.0.3", "better-sqlite3": "^12.5.0", + "cheerio": "^1.1.2", "commander": "^14.0.2", "cors": "^2.8.5", "dotenv": "^17.2.3", @@ -30,6 +31,7 @@ "@biomejs/biome": "^1.9.4", "@types/bcryptjs": "^2.4.6", "@types/better-sqlite3": "^7.6.13", + "@types/cheerio": "^0.22.35", "@types/cors": "^2.8.19", "@types/express": "^5.0.6", "@types/inquirer": "^9.0.9", @@ -1599,6 +1601,16 @@ "@types/node": "*" } }, + "node_modules/@types/cheerio": { + "version": "0.22.35", + "resolved": "https://registry.npmjs.org/@types/cheerio/-/cheerio-0.22.35.tgz", + "integrity": "sha512-yD57BchKRvTV+JD53UZ6PD8KWY5g5rvvMLRnZR3EQBCZXiDT/HR+pKpMzFGlWNhFrXlo7VPZXtKvIEwZkAWOIA==", + "dev": true, + "license": "MIT", + "dependencies": { + "@types/node": "*" + } + }, "node_modules/@types/connect": { "version": "3.4.38", "resolved": "https://registry.npmjs.org/@types/connect/-/connect-3.4.38.tgz", @@ -2062,6 +2074,12 @@ "url": "https://opencollective.com/express" } }, + "node_modules/boolbase": { + "version": "1.0.0", + "resolved": "https://registry.npmjs.org/boolbase/-/boolbase-1.0.0.tgz", + "integrity": "sha512-JZOSA7Mo9sNGB8+UjSgzdLtokWAky1zbztM3WRLCbZ70/3cTANmQmOdR7y2g+J0e2WXywy1yS468tY+IruqEww==", + "license": "ISC" + }, "node_modules/buffer": { "version": "5.7.1", "resolved": "https://registry.npmjs.org/buffer/-/buffer-5.7.1.tgz", @@ -2145,6 +2163,48 @@ "integrity": "sha512-PsezH1rqdV9VvyNhxxOW32/d75r01NY7TQCmOqomRo15ZSOKbpTFVsfjghxo6JloQUCGnH4k1LGu0R4yCLlWQQ==", "license": "MIT" }, + "node_modules/cheerio": { + "version": "1.1.2", + "resolved": "https://registry.npmjs.org/cheerio/-/cheerio-1.1.2.tgz", + "integrity": "sha512-IkxPpb5rS/d1IiLbHMgfPuS0FgiWTtFIm/Nj+2woXDLTZ7fOT2eqzgYbdMlLweqlHbsZjxEChoVK+7iph7jyQg==", + "license": "MIT", + "dependencies": { + "cheerio-select": "^2.1.0", + "dom-serializer": "^2.0.0", + "domhandler": "^5.0.3", + "domutils": "^3.2.2", + "encoding-sniffer": "^0.2.1", + "htmlparser2": "^10.0.0", + "parse5": "^7.3.0", + "parse5-htmlparser2-tree-adapter": "^7.1.0", + "parse5-parser-stream": "^7.1.2", + "undici": "^7.12.0", + "whatwg-mimetype": "^4.0.0" + }, + "engines": { + "node": ">=20.18.1" + }, + "funding": { + "url": "https://github.com/cheeriojs/cheerio?sponsor=1" + } + }, + "node_modules/cheerio-select": { + "version": "2.1.0", + "resolved": "https://registry.npmjs.org/cheerio-select/-/cheerio-select-2.1.0.tgz", + "integrity": "sha512-9v9kG0LvzrlcungtnJtpGNxY+fzECQKhK4EGJX2vByejiMX84MFNQw4UxPJl3bFbTMw+Dfs37XaIkCwTZfLh4g==", + "license": "BSD-2-Clause", + "dependencies": { + "boolbase": "^1.0.0", + "css-select": "^5.1.0", + "css-what": "^6.1.0", + "domelementtype": "^2.3.0", + "domhandler": "^5.0.3", + "domutils": "^3.0.1" + }, + "funding": { + "url": "https://github.com/sponsors/fb55" + } + }, "node_modules/chownr": { "version": "1.1.4", "resolved": "https://registry.npmjs.org/chownr/-/chownr-1.1.4.tgz", @@ -2362,6 +2422,34 @@ "node": ">= 0.10" } }, + "node_modules/css-select": { + "version": "5.2.2", + "resolved": "https://registry.npmjs.org/css-select/-/css-select-5.2.2.tgz", + "integrity": "sha512-TizTzUddG/xYLA3NXodFM0fSbNizXjOKhqiQQwvhlspadZokn1KDy0NZFS0wuEubIYAV5/c1/lAr0TaaFXEXzw==", + "license": "BSD-2-Clause", + "dependencies": { + "boolbase": "^1.0.0", + "css-what": "^6.1.0", + "domhandler": "^5.0.2", + "domutils": "^3.0.1", + "nth-check": "^2.0.1" + }, + "funding": { + "url": "https://github.com/sponsors/fb55" + } + }, + "node_modules/css-what": { + "version": "6.2.2", + "resolved": "https://registry.npmjs.org/css-what/-/css-what-6.2.2.tgz", + "integrity": "sha512-u/O3vwbptzhMs3L1fQE82ZSLHQQfto5gyZzwteVIEyeaY5Fc7R4dapF/BvRoSYFeqfBk4m0V1Vafq5Pjv25wvA==", + "license": "BSD-2-Clause", + "engines": { + "node": ">= 6" + }, + "funding": { + "url": "https://github.com/sponsors/fb55" + } + }, "node_modules/data-uri-to-buffer": { "version": "6.0.2", "resolved": "https://registry.npmjs.org/data-uri-to-buffer/-/data-uri-to-buffer-6.0.2.tgz", @@ -2459,6 +2547,61 @@ "integrity": "sha512-26T91cV5dbOYnXdJi5qQHoTtUoNEqwkHcAyu/IKtjIAxiEqPMrDiRkDOPWVsGfNZGmlQVHQbZRSjD8sxagWVsQ==", "license": "BSD-3-Clause" }, + "node_modules/dom-serializer": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/dom-serializer/-/dom-serializer-2.0.0.tgz", + "integrity": "sha512-wIkAryiqt/nV5EQKqQpo3SToSOV9J0DnbJqwK7Wv/Trc92zIAYZ4FlMu+JPFW1DfGFt81ZTCGgDEabffXeLyJg==", + "license": "MIT", + "dependencies": { + "domelementtype": "^2.3.0", + "domhandler": "^5.0.2", + "entities": "^4.2.0" + }, + "funding": { + "url": "https://github.com/cheeriojs/dom-serializer?sponsor=1" + } + }, + "node_modules/domelementtype": { + "version": "2.3.0", + "resolved": "https://registry.npmjs.org/domelementtype/-/domelementtype-2.3.0.tgz", + "integrity": "sha512-OLETBj6w0OsagBwdXnPdN0cnMfF9opN69co+7ZrbfPGrdpPVNBUj02spi6B1N7wChLQiPn4CSH/zJvXw56gmHw==", + "funding": [ + { + "type": "github", + "url": "https://github.com/sponsors/fb55" + } + ], + "license": "BSD-2-Clause" + }, + "node_modules/domhandler": { + "version": "5.0.3", + "resolved": "https://registry.npmjs.org/domhandler/-/domhandler-5.0.3.tgz", + "integrity": "sha512-cgwlv/1iFQiFnU96XXgROh8xTeetsnJiDsTc7TYCLFd9+/WNkIqPTxiM/8pSd8VIrhXGTf1Ny1q1hquVqDJB5w==", + "license": "BSD-2-Clause", + "dependencies": { + "domelementtype": "^2.3.0" + }, + "engines": { + "node": ">= 4" + }, + "funding": { + "url": "https://github.com/fb55/domhandler?sponsor=1" + } + }, + "node_modules/domutils": { + "version": "3.2.2", + "resolved": "https://registry.npmjs.org/domutils/-/domutils-3.2.2.tgz", + "integrity": "sha512-6kZKyUajlDuqlHKVX1w7gyslj9MPIXzIFiz/rGu35uC1wMi+kMhQwGhl4lt9unC9Vb9INnY9Z3/ZA3+FhASLaw==", + "license": "BSD-2-Clause", + "dependencies": { + "dom-serializer": "^2.0.0", + "domelementtype": "^2.3.0", + "domhandler": "^5.0.3" + }, + "funding": { + "url": "https://github.com/fb55/domutils?sponsor=1" + } + }, "node_modules/dotenv": { "version": "17.2.3", "resolved": "https://registry.npmjs.org/dotenv/-/dotenv-17.2.3.tgz", @@ -2515,6 +2658,31 @@ "node": ">= 0.8" } }, + "node_modules/encoding-sniffer": { + "version": "0.2.1", + "resolved": "https://registry.npmjs.org/encoding-sniffer/-/encoding-sniffer-0.2.1.tgz", + "integrity": "sha512-5gvq20T6vfpekVtqrYQsSCFZ1wEg5+wW0/QaZMWkFr6BqD3NfKs0rLCx4rrVlSWJeZb5NBJgVLswK/w2MWU+Gw==", + "license": "MIT", + "dependencies": { + "iconv-lite": "^0.6.3", + "whatwg-encoding": "^3.1.1" + }, + "funding": { + "url": "https://github.com/fb55/encoding-sniffer?sponsor=1" + } + }, + "node_modules/encoding-sniffer/node_modules/iconv-lite": { + "version": "0.6.3", + "resolved": "https://registry.npmjs.org/iconv-lite/-/iconv-lite-0.6.3.tgz", + "integrity": "sha512-4fCk79wshMdzMp2rH06qWrJE4iolqLhCUH+OiuIgU++RB0+94NlDL81atO7GX55uUKueo0txHNtvEyI6D7WdMw==", + "license": "MIT", + "dependencies": { + "safer-buffer": ">= 2.1.2 < 3.0.0" + }, + "engines": { + "node": ">=0.10.0" + } + }, "node_modules/end-of-stream": { "version": "1.4.5", "resolved": "https://registry.npmjs.org/end-of-stream/-/end-of-stream-1.4.5.tgz", @@ -2524,6 +2692,18 @@ "once": "^1.4.0" } }, + "node_modules/entities": { + "version": "4.5.0", + "resolved": "https://registry.npmjs.org/entities/-/entities-4.5.0.tgz", + "integrity": "sha512-V0hjH4dGPh9Ao5p0MoRY6BVqtwCjhz6vI5LT8AJ55H+4g9/4vbHx1I54fS0XuclLhDHArPQCiMjDxjaL8fPxhw==", + "license": "BSD-2-Clause", + "engines": { + "node": ">=0.12" + }, + "funding": { + "url": "https://github.com/fb55/entities?sponsor=1" + } + }, "node_modules/es-define-property": { "version": "1.0.1", "resolved": "https://registry.npmjs.org/es-define-property/-/es-define-property-1.0.1.tgz", @@ -3089,6 +3269,37 @@ "node": ">= 0.4" } }, + "node_modules/htmlparser2": { + "version": "10.0.0", + "resolved": "https://registry.npmjs.org/htmlparser2/-/htmlparser2-10.0.0.tgz", + "integrity": "sha512-TwAZM+zE5Tq3lrEHvOlvwgj1XLWQCtaaibSN11Q+gGBAS7Y1uZSWwXXRe4iF6OXnaq1riyQAPFOBtYc77Mxq0g==", + "funding": [ + "https://github.com/fb55/htmlparser2?sponsor=1", + { + "type": "github", + "url": "https://github.com/sponsors/fb55" + } + ], + "license": "MIT", + "dependencies": { + "domelementtype": "^2.3.0", + "domhandler": "^5.0.3", + "domutils": "^3.2.1", + "entities": "^6.0.0" + } + }, + "node_modules/htmlparser2/node_modules/entities": { + "version": "6.0.1", + "resolved": "https://registry.npmjs.org/entities/-/entities-6.0.1.tgz", + "integrity": "sha512-aN97NXWF6AWBTahfVOIrB/NShkzi5H7F9r1s9mD3cDj4Ko5f2qhhVoYMibXF7GlLveb/D2ioWay8lxI97Ven3g==", + "license": "BSD-2-Clause", + "engines": { + "node": ">=0.12" + }, + "funding": { + "url": "https://github.com/fb55/entities?sponsor=1" + } + }, "node_modules/http-errors": { "version": "2.0.1", "resolved": "https://registry.npmjs.org/http-errors/-/http-errors-2.0.1.tgz", @@ -3532,6 +3743,18 @@ "node": ">=6.0.0" } }, + "node_modules/nth-check": { + "version": "2.1.1", + "resolved": "https://registry.npmjs.org/nth-check/-/nth-check-2.1.1.tgz", + "integrity": "sha512-lqjrjmaOoAnWfMmBPL+XNnynZh2+swxiX3WUE0s4yEHI6m+AwrK2UZOimIRl3X/4QctVqS8AiZjFqyOGrMXb/w==", + "license": "BSD-2-Clause", + "dependencies": { + "boolbase": "^1.0.0" + }, + "funding": { + "url": "https://github.com/fb55/nth-check?sponsor=1" + } + }, "node_modules/object-assign": { "version": "4.1.1", "resolved": "https://registry.npmjs.org/object-assign/-/object-assign-4.1.1.tgz", @@ -3606,6 +3829,55 @@ "node": ">= 14" } }, + "node_modules/parse5": { + "version": "7.3.0", + "resolved": "https://registry.npmjs.org/parse5/-/parse5-7.3.0.tgz", + "integrity": "sha512-IInvU7fabl34qmi9gY8XOVxhYyMyuH2xUNpb2q8/Y+7552KlejkRvqvD19nMoUW/uQGGbqNpA6Tufu5FL5BZgw==", + "license": "MIT", + "dependencies": { + "entities": "^6.0.0" + }, + "funding": { + "url": "https://github.com/inikulin/parse5?sponsor=1" + } + }, + "node_modules/parse5-htmlparser2-tree-adapter": { + "version": "7.1.0", + "resolved": "https://registry.npmjs.org/parse5-htmlparser2-tree-adapter/-/parse5-htmlparser2-tree-adapter-7.1.0.tgz", + "integrity": "sha512-ruw5xyKs6lrpo9x9rCZqZZnIUntICjQAd0Wsmp396Ul9lN/h+ifgVV1x1gZHi8euej6wTfpqX8j+BFQxF0NS/g==", + "license": "MIT", + "dependencies": { + "domhandler": "^5.0.3", + "parse5": "^7.0.0" + }, + "funding": { + "url": "https://github.com/inikulin/parse5?sponsor=1" + } + }, + "node_modules/parse5-parser-stream": { + "version": "7.1.2", + "resolved": "https://registry.npmjs.org/parse5-parser-stream/-/parse5-parser-stream-7.1.2.tgz", + "integrity": "sha512-JyeQc9iwFLn5TbvvqACIF/VXG6abODeB3Fwmv/TGdLk2LfbWkaySGY72at4+Ty7EkPZj854u4CrICqNk2qIbow==", + "license": "MIT", + "dependencies": { + "parse5": "^7.0.0" + }, + "funding": { + "url": "https://github.com/inikulin/parse5?sponsor=1" + } + }, + "node_modules/parse5/node_modules/entities": { + "version": "6.0.1", + "resolved": "https://registry.npmjs.org/entities/-/entities-6.0.1.tgz", + "integrity": "sha512-aN97NXWF6AWBTahfVOIrB/NShkzi5H7F9r1s9mD3cDj4Ko5f2qhhVoYMibXF7GlLveb/D2ioWay8lxI97Ven3g==", + "license": "BSD-2-Clause", + "engines": { + "node": ">=0.12" + }, + "funding": { + "url": "https://github.com/fb55/entities?sponsor=1" + } + }, "node_modules/parseurl": { "version": "1.3.3", "resolved": "https://registry.npmjs.org/parseurl/-/parseurl-1.3.3.tgz", @@ -4458,6 +4730,15 @@ "multiformats": "^9.4.2" } }, + "node_modules/undici": { + "version": "7.18.2", + "resolved": "https://registry.npmjs.org/undici/-/undici-7.18.2.tgz", + "integrity": "sha512-y+8YjDFzWdQlSE9N5nzKMT3g4a5UBX1HKowfdXh0uvAnTaqqwqB92Jt4UXBAeKekDs5IaDKyJFR4X1gYVCgXcw==", + "license": "MIT", + "engines": { + "node": ">=20.18.1" + } + }, "node_modules/undici-types": { "version": "6.21.0", "resolved": "https://registry.npmjs.org/undici-types/-/undici-types-6.21.0.tgz", @@ -4501,6 +4782,40 @@ "integrity": "sha512-5LAE43jAVLOhB/QqX4bwSiv0Hg1HBfMmOuwBSXHdvg4GMGu9Y0lIq7p4R/yySu6w74WmaR4GM4H9t2IwLW7hgw==", "license": "Apache-2.0" }, + "node_modules/whatwg-encoding": { + "version": "3.1.1", + "resolved": "https://registry.npmjs.org/whatwg-encoding/-/whatwg-encoding-3.1.1.tgz", + "integrity": "sha512-6qN4hJdMwfYBtE3YBTTHhoeuUrDBPZmbQaxWAqSALV/MeEnR5z1xd8UKud2RAkFoPkmB+hli1TZSnyi84xz1vQ==", + "deprecated": "Use @exodus/bytes instead for a more spec-conformant and faster implementation", + "license": "MIT", + "dependencies": { + "iconv-lite": "0.6.3" + }, + "engines": { + "node": ">=18" + } + }, + "node_modules/whatwg-encoding/node_modules/iconv-lite": { + "version": "0.6.3", + "resolved": "https://registry.npmjs.org/iconv-lite/-/iconv-lite-0.6.3.tgz", + "integrity": "sha512-4fCk79wshMdzMp2rH06qWrJE4iolqLhCUH+OiuIgU++RB0+94NlDL81atO7GX55uUKueo0txHNtvEyI6D7WdMw==", + "license": "MIT", + "dependencies": { + "safer-buffer": ">= 2.1.2 < 3.0.0" + }, + "engines": { + "node": ">=0.10.0" + } + }, + "node_modules/whatwg-mimetype": { + "version": "4.0.0", + "resolved": "https://registry.npmjs.org/whatwg-mimetype/-/whatwg-mimetype-4.0.0.tgz", + "integrity": "sha512-QaKxh0eNIi2mE9p2vEdzfagOKHCcj1pJ56EEHGQOVxp8r9/iszLUUV7v89x9O1p/T+NlTM5W7jW6+cz4Fq1YVg==", + "license": "MIT", + "engines": { + "node": ">=18" + } + }, "node_modules/wrap-ansi": { "version": "9.0.2", "resolved": "https://registry.npmjs.org/wrap-ansi/-/wrap-ansi-9.0.2.tgz", diff --git a/package.json b/package.json index ec41ba0..d45fb28 100644 --- a/package.json +++ b/package.json @@ -30,6 +30,7 @@ "axios": "^1.13.2", "bcryptjs": "^3.0.3", "better-sqlite3": "^12.5.0", + "cheerio": "^1.1.2", "commander": "^14.0.2", "cors": "^2.8.5", "dotenv": "^17.2.3", @@ -46,6 +47,7 @@ "@biomejs/biome": "^1.9.4", "@types/bcryptjs": "^2.4.6", "@types/better-sqlite3": "^7.6.13", + "@types/cheerio": "^0.22.35", "@types/cors": "^2.8.19", "@types/express": "^5.0.6", "@types/inquirer": "^9.0.9", diff --git a/src/index.ts b/src/index.ts index 12c11f1..e1c5262 100644 --- a/src/index.ts +++ b/src/index.ts @@ -12,6 +12,7 @@ import * as francModule from 'franc-min'; import iso6391 from 'iso-639-1'; import os from 'node:os'; import puppeteer from 'puppeteer-core'; +import * as cheerio from 'cheerio'; import sharp from 'sharp'; import { getConfig } from './config-manager.js'; @@ -498,6 +499,57 @@ async function pollForVideoProcessing(agent: BskyAgent, jobId: string): Promise< return blob!; } +async function fetchEmbedUrlCard(agent: BskyAgent, url: string): Promise { + try { + const response = await axios.get(url, { + headers: { + 'User-Agent': 'Mozilla/5.0 (compatible; Tweets2Bsky/1.0; +https://github.com/j4ckxyz/tweets-2-bsky)', + }, + timeout: 10000, + }); + + const $ = cheerio.load(response.data); + const title = $('meta[property="og:title"]').attr('content') || $('title').text() || ''; + const description = $('meta[property="og:description"]').attr('content') || $('meta[name="description"]').attr('content') || ''; + let thumbBlob: BlobRef | undefined; + + let imageUrl = $('meta[property="og:image"]').attr('content'); + if (imageUrl) { + if (!imageUrl.startsWith('http')) { + const baseUrl = new URL(url); + imageUrl = new URL(imageUrl, baseUrl.origin).toString(); + } + try { + const { buffer, mimeType } = await downloadMedia(imageUrl); + thumbBlob = await uploadToBluesky(agent, buffer, mimeType); + } catch (e) { + console.warn(`Failed to upload thumbnail for ${url}:`, e); + } + } + + if (!title && !description) return null; + + const external: any = { + uri: url, + title: title || url, + description: description, + }; + + if (thumbBlob) { + external.thumb = thumbBlob; + } + + return { + $type: 'app.bsky.embed.external', + external, + }; + + } catch (err) { + console.warn(`Failed to fetch embed card for ${url}:`, err); + return null; + } +} + async function uploadVideoToBluesky(agent: BskyAgent, buffer: Buffer, filename: string): Promise { const sanitizedFilename = filename.split("?")[0] || "video.mp4"; console.log( @@ -847,6 +899,7 @@ async function processTweets( // 3. Quoting Logic let quoteEmbed: { $type: string; record: { uri: string; cid: string } } | null = null; let externalQuoteUrl: string | null = null; + let linkCard: any = null; if (tweet.is_quote_status && tweet.quoted_status_id_str) { const quoteId = tweet.quoted_status_id_str; @@ -882,6 +935,20 @@ async function processTweets( console.log(`[${twitterUsername}] 🔁 Quoted tweet is a self-quote, skipping link.`); } } + } else if (images.length === 0 && !videoBlob) { + // If no media and no quote, check for external links to embed + // We prioritize the LAST link found as it's often the main content + const potentialLinks = urls + .map(u => u.expanded_url) + .filter(u => u && !u.includes('twitter.com') && !u.includes('x.com')) as string[]; + + if (potentialLinks.length > 0) { + const linkToEmbed = potentialLinks[potentialLinks.length - 1]; + if (linkToEmbed) { + console.log(`[${twitterUsername}] 🃏 Fetching link card for: ${linkToEmbed}`); + linkCard = await fetchEmbedUrlCard(agent, linkToEmbed); + } + } } // Only append link for external quotes IF we couldn't natively embed it OR screenshot it @@ -930,6 +997,8 @@ async function processTweets( } } else if (quoteEmbed) { postRecord.embed = quoteEmbed; + } else if (linkCard) { + postRecord.embed = linkCard; } }