From 4aa1b5c56a912451a8c45165f13da5e149c7bdab Mon Sep 17 00:00:00 2001 From: Satsuki Akiba Date: Sun, 8 Jun 2025 21:34:11 +0900 Subject: [PATCH] Replace cheero with puppeteer --- admin-server.ts | 14 ++ bun.lock | 179 +++++++++++++++++++++++ package.json | 1 + scripts/fetch_and_generate.ts | 5 +- server.ts | 14 ++ services/content-extractor.ts | 267 ++++++++++++++++++++++------------ 6 files changed, 382 insertions(+), 98 deletions(-) diff --git a/admin-server.ts b/admin-server.ts index c494b38..eae27d0 100644 --- a/admin-server.ts +++ b/admin-server.ts @@ -6,6 +6,7 @@ import { basicAuth } from "hono/basic-auth"; import { addNewFeedUrl, batchProcess } from "./scripts/fetch_and_generate.js"; import { batchScheduler } from "./services/batch-scheduler.js"; import { config, validateConfig } from "./services/config.js"; +import { closeBrowser } from "./services/content-extractor.js"; import { deleteFeed, deleteEpisode, @@ -700,6 +701,19 @@ app.get("/", serveAdminIndex); app.get("/index.html", serveAdminIndex); app.get("*", serveAdminIndex); +// Graceful shutdown +process.on('SIGINT', async () => { + console.log('\nπŸ›‘ Received SIGINT. Graceful shutdown...'); + await closeBrowser(); + process.exit(0); +}); + +process.on('SIGTERM', async () => { + console.log('\nπŸ›‘ Received SIGTERM. Graceful shutdown...'); + await closeBrowser(); + process.exit(0); +}); + // Start admin server serve( { diff --git a/bun.lock b/bun.lock index 02fc308..85865ba 100644 --- a/bun.lock +++ b/bun.lock @@ -11,6 +11,7 @@ "ffmpeg-static": "^5.2.0", "hono": "^4.7.11", "openai": "^4.104.0", + "puppeteer": "^24.10.0", "react": "^19.1.0", "react-dom": "^19.1.0", "react-helmet-async": "^2.0.5", @@ -209,6 +210,8 @@ "@jridgewell/trace-mapping": ["@jridgewell/trace-mapping@0.3.25", "", { "dependencies": { "@jridgewell/resolve-uri": "^3.1.0", "@jridgewell/sourcemap-codec": "^1.4.14" } }, "sha512-vNk6aEwybGtawWmy/PzwnGDOjCkLWSD2wqvjGGAgOAwCGWySYXfYoxt00IJkTF+8Lb57DwOb3Aa0o9CApepiYQ=="], + "@puppeteer/browsers": ["@puppeteer/browsers@2.10.5", "", { "dependencies": { "debug": "^4.4.1", "extract-zip": "^2.0.1", "progress": "^2.0.3", "proxy-agent": "^6.5.0", "semver": "^7.7.2", "tar-fs": "^3.0.8", "yargs": "^17.7.2" }, "bin": { "browsers": "lib/cjs/main-cli.js" } }, "sha512-eifa0o+i8dERnngJwKrfp3dEq7ia5XFyoqB17S4gK8GhsQE4/P8nxOfQSE0zQHxzzLo/cmF+7+ywEQ7wK7Fb+w=="], + "@rolldown/pluginutils": ["@rolldown/pluginutils@1.0.0-beta.9", "", {}, "sha512-e9MeMtVWo186sgvFFJOPGy7/d2j2mZhLJIdVW0C/xDluuOvymEATqz6zKsP0ZmXGzQtqlyjz5sC1sYQUoJG98w=="], "@rollup/rollup-android-arm-eabi": ["@rollup/rollup-android-arm-eabi@4.41.1", "", { "os": "android", "cpu": "arm" }, "sha512-NELNvyEWZ6R9QMkiytB4/L4zSEaBC03KIXEghptLGLZWJ6VPrL63ooZQCOnlx36aQPGhzuOMwDerC1Eb2VmrLw=="], @@ -329,6 +332,8 @@ "@smithy/util-utf8": ["@smithy/util-utf8@4.0.0", "", { "dependencies": { "@smithy/util-buffer-from": "^4.0.0", "tslib": "^2.6.2" } }, "sha512-b+zebfKCfRdgNJDknHCob3O7FpeYQN6ZG6YLExMcasDHsCXlsXCEuiPZeLnJLpwa5dvPetGlnGCiMHuLwGvFow=="], + "@tootallnate/quickjs-emscripten": ["@tootallnate/quickjs-emscripten@0.23.0", "", {}, "sha512-C5Mc6rdnsaJDjO3UpGW/CQTHtCKaYlScZTly4JIu97Jxo/odCiH0ITnDXSJPTOrEKk/ycSZ0AOgTmkDtkOsvIA=="], + "@types/babel__core": ["@types/babel__core@7.20.5", "", { "dependencies": { "@babel/parser": "^7.20.7", "@babel/types": "^7.20.7", "@types/babel__generator": "*", "@types/babel__template": "*", "@types/babel__traverse": "*" } }, "sha512-qoQprZvz5wQFJwMDqeseRXWv3rqMvhgpbXFfVyWhbx9X47POIA6i/+dXefEmZKoAgOaTdaIgNSMqMIU61yRyzA=="], "@types/babel__generator": ["@types/babel__generator@7.27.0", "", { "dependencies": { "@babel/types": "^7.0.0" } }, "sha512-ufFd2Xi92OAVPYsy+P4n7/U7e68fex0+Ee8gSG9KX7eo084CWiQ4sdxktvdl0bOPupXtVJPY19zk6EwWqUQ8lg=="], @@ -353,6 +358,8 @@ "@types/xml2js": ["@types/xml2js@0.4.14", "", { "dependencies": { "@types/node": "*" } }, "sha512-4YnrRemBShWRO2QjvUin8ESA41rH+9nQGLUGZV/1IDhi3SL9OhdpNC/MrulTWuptXKwhx/aDxE7toV0f/ypIXQ=="], + "@types/yauzl": ["@types/yauzl@2.10.3", "", { "dependencies": { "@types/node": "*" } }, "sha512-oJoftv0LSuaDZE3Le4DbKX+KS9G36NzOeSap90UIK0yMA/NhKJhqlSGtNDORNRaIbQfzjXDrQa0ytJ6mNRGz/Q=="], + "@vitejs/plugin-react": ["@vitejs/plugin-react@4.5.1", "", { "dependencies": { "@babel/core": "^7.26.10", "@babel/plugin-transform-react-jsx-self": "^7.25.9", "@babel/plugin-transform-react-jsx-source": "^7.25.9", "@rolldown/pluginutils": "1.0.0-beta.9", "@types/babel__core": "^7.20.5", "react-refresh": "^0.17.0" }, "peerDependencies": { "vite": "^4.2.0 || ^5.0.0 || ^6.0.0" } }, "sha512-uPZBqSI0YD4lpkIru6M35sIfylLGTyhGHvDZbNLuMA73lMlwJKz5xweH7FajfcCAc2HnINciejA9qTz0dr0M7A=="], "abort-controller": ["abort-controller@3.0.0", "", { "dependencies": { "event-target-shim": "^5.0.0" } }, "sha512-h8lQ8tacZYnR3vNQTgibj+tODHI5/+l06Au2Pcriv/Gmet0eaj4TwWH41sO9wnHDiQsEj19q0drzdWdeAHtweg=="], @@ -361,20 +368,46 @@ "agentkeepalive": ["agentkeepalive@4.6.0", "", { "dependencies": { "humanize-ms": "^1.2.1" } }, "sha512-kja8j7PjmncONqaTsB8fQ+wE2mSU2DJ9D4XKoJ5PFWIdRMa6SLSN1ff4mOr4jCbfRSsxR4keIiySJU0N9T5hIQ=="], + "ansi-regex": ["ansi-regex@5.0.1", "", {}, "sha512-quJQXlTSUGL2LH9SUXo8VwsY4soanhgo6LNSm84E1LBcE8s3O0wpdiRzyR9z/ZZJMlMWv37qOOb9pdJlMUEKFQ=="], + + "ansi-styles": ["ansi-styles@4.3.0", "", { "dependencies": { "color-convert": "^2.0.1" } }, "sha512-zbB9rCJAT1rbjiVDb2hqKFHNYLxgtk8NURxZ3IZwD3F6NtxbXZQCnnSi1Lkx+IDohdPlFp222wVALIheZJQSEg=="], + + "argparse": ["argparse@2.0.1", "", {}, "sha512-8+9WqebbFzpX9OR+Wa6O29asIogeRMzcGtAINdpMHHyAg10f05aSFVBbcEqGf/PXw1EjAZ+q2/bEBg3DvurK3Q=="], + + "ast-types": ["ast-types@0.13.4", "", { "dependencies": { "tslib": "^2.0.1" } }, "sha512-x1FCFnFifvYDDzTaLII71vG5uvDwgtmDTEVWAxrgeiR8VjMONcCXJx7E+USjDtHlwFmt9MysbqgF9b9Vjr6w+w=="], + "asynckit": ["asynckit@0.4.0", "", {}, "sha512-Oei9OH4tRh0YqU3GxhX79dM/mwVgvbZJaSNaRk+bshkj0S5cfHcgYakreBjrHwatXKbz+IoIdYLxrKim2MjW0Q=="], + "b4a": ["b4a@1.6.7", "", {}, "sha512-OnAYlL5b7LEkALw87fUVafQw5rVR9RjwGd4KUwNQ6DrrNmaVaUCgLipfVlzrPQ4tWOR9P0IXGNOx50jYCCdSJg=="], + + "bare-events": ["bare-events@2.5.4", "", {}, "sha512-+gFfDkR8pj4/TrWCGUGWmJIkBwuxPS5F+a5yWjOHQt2hHvNZd5YLzadjmDUtFmMM4y429bnKLa8bYBMHcYdnQA=="], + + "bare-fs": ["bare-fs@4.1.5", "", { "dependencies": { "bare-events": "^2.5.4", "bare-path": "^3.0.0", "bare-stream": "^2.6.4" }, "peerDependencies": { "bare-buffer": "*" }, "optionalPeers": ["bare-buffer"] }, "sha512-1zccWBMypln0jEE05LzZt+V/8y8AQsQQqxtklqaIyg5nu6OAYFhZxPXinJTSG+kU5qyNmeLgcn9AW7eHiCHVLA=="], + + "bare-os": ["bare-os@3.6.1", "", {}, "sha512-uaIjxokhFidJP+bmmvKSgiMzj2sV5GPHaZVAIktcxcpCyBFFWO+YlikVAdhmUo2vYFvFhOXIAlldqV29L8126g=="], + + "bare-path": ["bare-path@3.0.0", "", { "dependencies": { "bare-os": "^3.0.1" } }, "sha512-tyfW2cQcB5NN8Saijrhqn0Zh7AnFNsnczRcuWODH0eYAXBsJ5gVxAUuNr7tsHSC6IZ77cA0SitzT+s47kot8Mw=="], + + "bare-stream": ["bare-stream@2.6.5", "", { "dependencies": { "streamx": "^2.21.0" }, "peerDependencies": { "bare-buffer": "*", "bare-events": "*" }, "optionalPeers": ["bare-buffer", "bare-events"] }, "sha512-jSmxKJNJmHySi6hC42zlZnq00rga4jjxcgNZjY9N5WlOe/iOoGRtdwGsHzQv2RlH2KOYMwGUXhf2zXd32BA9RA=="], + + "basic-ftp": ["basic-ftp@5.0.5", "", {}, "sha512-4Bcg1P8xhUuqcii/S0Z9wiHIrQVPMermM1any+MX5GeGD7faD3/msQUDGLol9wOcz4/jbg/WJnGqoJF6LiBdtg=="], + "boolbase": ["boolbase@1.0.0", "", {}, "sha512-JZOSA7Mo9sNGB8+UjSgzdLtokWAky1zbztM3WRLCbZ70/3cTANmQmOdR7y2g+J0e2WXywy1yS468tY+IruqEww=="], "bowser": ["bowser@2.11.0", "", {}, "sha512-AlcaJBi/pqqJBIQ8U9Mcpc9i8Aqxn88Skv5d+xBX006BY5u8N3mGLHa5Lgppa7L/HfwgwLgZ6NYs+Ag6uUmJRA=="], "browserslist": ["browserslist@4.25.0", "", { "dependencies": { "caniuse-lite": "^1.0.30001718", "electron-to-chromium": "^1.5.160", "node-releases": "^2.0.19", "update-browserslist-db": "^1.1.3" }, "bin": { "browserslist": "cli.js" } }, "sha512-PJ8gYKeS5e/whHBh8xrwYK+dAvEj7JXtz6uTucnMRB8OiGTsKccFekoRrjajPBHV8oOY+2tI4uxeceSimKwMFA=="], + "buffer-crc32": ["buffer-crc32@0.2.13", "", {}, "sha512-VO9Ht/+p3SN7SKWqcrgEzjGbRSJYTx+Q1pTQC0wrWqHx0vpJraQ6GtHx8tvcg1rlK1byhU5gccxgOgj7B0TDkQ=="], + "buffer-from": ["buffer-from@1.1.2", "", {}, "sha512-E+XQCRwSbaaiChtv6k6Dwgc+bx+Bs6vuKJHHl5kox/BaKbhiXzqQOwK4cO22yElGp2OCmjwVhT3HmxgyPGnJfQ=="], "bun-types": ["bun-types@1.2.15", "", { "dependencies": { "@types/node": "*" } }, "sha512-NarRIaS+iOaQU1JPfyKhZm4AsUOrwUOqRNHY0XxI8GI8jYxiLXLcdjYMG9UKS+fwWasc1uw1htV9AX24dD+p4w=="], "call-bind-apply-helpers": ["call-bind-apply-helpers@1.0.2", "", { "dependencies": { "es-errors": "^1.3.0", "function-bind": "^1.1.2" } }, "sha512-Sp1ablJ0ivDkSzjcaJdxEunN5/XvksFJ2sMBFfq6x0ryhQV/2b/KwFe21cMpmHtPOSij8K99/wSfoEuTObmuMQ=="], + "callsites": ["callsites@3.1.0", "", {}, "sha512-P8BjAsXvZS+VIDUI11hHCQEv74YT67YUi5JJFNWIqL235sBmjX4+qx9Muvls5ivyNENctx46xQLQ3aTuE7ssaQ=="], + "caniuse-lite": ["caniuse-lite@1.0.30001720", "", {}, "sha512-Ec/2yV2nNPwb4DnTANEV99ZWwm3ZWfdlfkQbWSDDt+PsXEVYwlhPH8tdMaPunYTKKmz7AnHi2oNEi1GcmKCD8g=="], "caseless": ["caseless@0.12.0", "", {}, "sha512-4tYFyifaFfGacoiObjJegolkwSU4xQNGbVgUiNYVUxbQ2x2lUsFvY4hVgVzGiIe6WLOPqycWXA40l+PWsxthUw=="], @@ -383,6 +416,14 @@ "cheerio-select": ["cheerio-select@2.1.0", "", { "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" } }, "sha512-9v9kG0LvzrlcungtnJtpGNxY+fzECQKhK4EGJX2vByejiMX84MFNQw4UxPJl3bFbTMw+Dfs37XaIkCwTZfLh4g=="], + "chromium-bidi": ["chromium-bidi@5.1.0", "", { "dependencies": { "mitt": "^3.0.1", "zod": "^3.24.1" }, "peerDependencies": { "devtools-protocol": "*" } }, "sha512-9MSRhWRVoRPDG0TgzkHrshFSJJNZzfY5UFqUMuksg7zL1yoZIZ3jLB0YAgHclbiAxPI86pBnwDX1tbzoiV8aFw=="], + + "cliui": ["cliui@8.0.1", "", { "dependencies": { "string-width": "^4.2.0", "strip-ansi": "^6.0.1", "wrap-ansi": "^7.0.0" } }, "sha512-BSeNnyus75C4//NQ9gQt1/csTXyo/8Sb+afLAkzAptFuMsod9HFokGNudZpi/oQV73hnVK+sR+5PVRMd+Dr7YQ=="], + + "color-convert": ["color-convert@2.0.1", "", { "dependencies": { "color-name": "~1.1.4" } }, "sha512-RRECPsj7iu/xb5oKYcsFHSppFNnsj/52OVTRKb4zP5onXwVF3zVmmToNcOfGC+CRDpfK/U584fMg38ZHCaElKQ=="], + + "color-name": ["color-name@1.1.4", "", {}, "sha512-dOy+3AuW3a2wNbZHIuMZpTcgjGuLU/uBL/ubcZF9OXbDo8ff4O8yVp5Bf0efS8uEoYo5q4Fx7dY9OgQGXgAsQA=="], + "combined-stream": ["combined-stream@1.0.8", "", { "dependencies": { "delayed-stream": "~1.0.0" } }, "sha512-FQN4MRfuJeHf7cBbBMJFXhKSDq+2kAArBlmRBvcvFE5BB1HZKXtSFASDhdlz9zOYwxh8lDdnvmMOe/+5cdoEdg=="], "concat-stream": ["concat-stream@2.0.0", "", { "dependencies": { "buffer-from": "^1.0.0", "inherits": "^2.0.3", "readable-stream": "^3.0.2", "typedarray": "^0.0.6" } }, "sha512-MWufYdFw53ccGjCA+Ol7XJYpAlW6/prSMzuPOTRnJGcGzuhLn4Scrz7qf6o8bROZ514ltazcIFJZevcfbo0x7A=="], @@ -391,16 +432,24 @@ "cookie": ["cookie@1.0.2", "", {}, "sha512-9Kr/j4O16ISv8zBBhJoi4bXOYNTkFLOqSL3UDB0njXxCXNezjeyVrJyGOWtgfs/q2km1gwBcfH8q1yEGoMYunA=="], + "cosmiconfig": ["cosmiconfig@9.0.0", "", { "dependencies": { "env-paths": "^2.2.1", "import-fresh": "^3.3.0", "js-yaml": "^4.1.0", "parse-json": "^5.2.0" }, "peerDependencies": { "typescript": ">=4.9.5" }, "optionalPeers": ["typescript"] }, "sha512-itvL5h8RETACmOTFc4UfIyB2RfEHi71Ax6E/PivVxq9NseKbOWpeyHEOIbmAw1rs8Ak0VursQNww7lf7YtUwzg=="], + "css-select": ["css-select@5.1.0", "", { "dependencies": { "boolbase": "^1.0.0", "css-what": "^6.1.0", "domhandler": "^5.0.2", "domutils": "^3.0.1", "nth-check": "^2.0.1" } }, "sha512-nwoRF1rvRRnnCqqY7updORDsuqKzqYJ28+oSMaJMMgOauh3fvwHqMS7EZpIPqK8GL+g9mKxF1vP/ZjSeNjEVHg=="], "css-what": ["css-what@6.1.0", "", {}, "sha512-HTUrgRJ7r4dsZKU6GjmpfRK1O76h97Z8MfS1G0FozR+oF2kG6Vfe8JE6zwrkbxigziPHinCJ+gCPjA9EaBDtRw=="], "csstype": ["csstype@3.1.3", "", {}, "sha512-M1uQkMl8rQK/szD0LNhtqxIPLpimGm8sOBwU7lLnCpSbTyY3yeU1Vc7l4KT5zT4s/yOxHH5O7tIuuLOCnLADRw=="], + "data-uri-to-buffer": ["data-uri-to-buffer@6.0.2", "", {}, "sha512-7hvf7/GW8e86rW0ptuwS3OcBGDjIi6SZva7hCyWC0yYry2cOPmLIjXAUHI6DK2HsnwJd9ifmt57i8eV2n4YNpw=="], + "debug": ["debug@4.4.1", "", { "dependencies": { "ms": "^2.1.3" } }, "sha512-KcKCqiftBJcZr++7ykoDIEwSa3XWowTfNPo92BYxjXiyYEVrUQh2aLyhxBCwww+heortUFxEJYcRzosstTEBYQ=="], + "degenerator": ["degenerator@5.0.1", "", { "dependencies": { "ast-types": "^0.13.4", "escodegen": "^2.1.0", "esprima": "^4.0.1" } }, "sha512-TllpMR/t0M5sqCXfj85i4XaAzxmS5tVA16dqvdkMwGmzI+dXLXnw3J+3Vdv7VKw+ThlTMboK6i9rnZ6Nntj5CQ=="], + "delayed-stream": ["delayed-stream@1.0.0", "", {}, "sha512-ZySD7Nf91aLB0RxL4KGrKHBXl7Eds1DAmEdcoVawXnLD7SDhpNgtuII2aAkg7a7QS41jxPSZ17p4VdGnMHk3MQ=="], + "devtools-protocol": ["devtools-protocol@0.0.1452169", "", {}, "sha512-FOFDVMGrAUNp0dDKsAU1TorWJUx2JOU1k9xdgBKKJF3IBh/Uhl2yswG5r3TEAOrCiGY2QRp1e6LVDQrCsTKO4g=="], + "dom-serializer": ["dom-serializer@2.0.0", "", { "dependencies": { "domelementtype": "^2.3.0", "domhandler": "^5.0.2", "entities": "^4.2.0" } }, "sha512-wIkAryiqt/nV5EQKqQpo3SToSOV9J0DnbJqwK7Wv/Trc92zIAYZ4FlMu+JPFW1DfGFt81ZTCGgDEabffXeLyJg=="], "domelementtype": ["domelementtype@2.3.0", "", {}, "sha512-OLETBj6w0OsagBwdXnPdN0cnMfF9opN69co+7ZrbfPGrdpPVNBUj02spi6B1N7wChLQiPn4CSH/zJvXw56gmHw=="], @@ -413,12 +462,18 @@ "electron-to-chromium": ["electron-to-chromium@1.5.162", "", {}, "sha512-hQA+Zb5QQwoSaXJWEAGEw1zhk//O7qDzib05Z4qTqZfNju/FAkrm5ZInp0JbTp4Z18A6bilopdZWEYrFSsfllA=="], + "emoji-regex": ["emoji-regex@8.0.0", "", {}, "sha512-MSjYzcWNOA0ewAHpz0MxpYFvwg6yjy1NG3xteoqz644VCo/RPgnr1/GGt+ic3iJTzQ8Eu3TdM14SawnVUmGE6A=="], + "encoding-sniffer": ["encoding-sniffer@0.2.0", "", { "dependencies": { "iconv-lite": "^0.6.3", "whatwg-encoding": "^3.1.1" } }, "sha512-ju7Wq1kg04I3HtiYIOrUrdfdDvkyO9s5XM8QAj/bN61Yo/Vb4vgJxy5vi4Yxk01gWHbrofpPtpxM8bKger9jhg=="], + "end-of-stream": ["end-of-stream@1.4.4", "", { "dependencies": { "once": "^1.4.0" } }, "sha512-+uw1inIHVPQoaVuHzRyXd21icM+cnt4CzD5rW+NC1wjOUSTOs+Te7FOv7AhN7vS9x/oIyhLP5PR1H+phQAHu5Q=="], + "entities": ["entities@2.2.0", "", {}, "sha512-p92if5Nz619I0w+akJrLZH0MX0Pb5DX39XOwQTtXSdQQOaYH03S1uIQp4mhOZtAXrxq4ViO67YTiLBo2638o9A=="], "env-paths": ["env-paths@2.2.1", "", {}, "sha512-+h1lkLKhZMTYjog1VEpJNG7NZJWcuc2DDk/qsqSTRRCOXiLjeQ1d1/udrUGhqMxUgAlwKNZ0cf2uqan5GLuS2A=="], + "error-ex": ["error-ex@1.3.2", "", { "dependencies": { "is-arrayish": "^0.2.1" } }, "sha512-7dFHNmqeFSEt2ZBsCriorKnn3Z2pj+fd9kmI6QoWw4//DL+icEBfc0U7qJCisqrTsKTjw4fNFy2pW9OqStD84g=="], + "es-define-property": ["es-define-property@1.0.1", "", {}, "sha512-e3nRfgfUZ4rNGL232gUgX06QNyyez04KdjFrF+LTRoOXmrOgFKDg4BCdsjW8EnT69eqdYGmRpJwiPVYNrCaW3g=="], "es-errors": ["es-errors@1.3.0", "", {}, "sha512-Zf5H2Kxt2xjTvbJvP2ZWLEICxA6j+hAmMzIlypy4xcBg1vKVnx89Wy0GbS+kf5cwCVFFzdCFh2XSCFNULS6csw=="], @@ -431,10 +486,24 @@ "escalade": ["escalade@3.2.0", "", {}, "sha512-WUj2qlxaQtO4g6Pq5c29GTcWGDyd8itL8zTlipgECz3JesAiiOKotd8JU6otB3PACgG6xkJUyVhboMS+bje/jA=="], + "escodegen": ["escodegen@2.1.0", "", { "dependencies": { "esprima": "^4.0.1", "estraverse": "^5.2.0", "esutils": "^2.0.2" }, "optionalDependencies": { "source-map": "~0.6.1" }, "bin": { "esgenerate": "bin/esgenerate.js", "escodegen": "bin/escodegen.js" } }, "sha512-2NlIDTwUWJN0mRPQOdtQBzbUHvdGY2P1VXSyU83Q3xKxM7WHX2Ql8dKq782Q9TgQUNOLEzEYu9bzLNj1q88I5w=="], + + "esprima": ["esprima@4.0.1", "", { "bin": { "esparse": "./bin/esparse.js", "esvalidate": "./bin/esvalidate.js" } }, "sha512-eGuFFw7Upda+g4p+QHvnW0RyTX/SVeJBDM/gCtMARO0cLuT2HcEKnTPvhjV6aGeqrCB/sbNop0Kszm0jsaWU4A=="], + + "estraverse": ["estraverse@5.3.0", "", {}, "sha512-MMdARuVEQziNTeJD8DgMqmhwR11BRQ/cBP+pLtYdSTnf3MIO8fFeiINEbX36ZdNlfU/7A9f3gUw49B3oQsvwBA=="], + + "esutils": ["esutils@2.0.3", "", {}, "sha512-kVscqXk4OCp68SZ0dkgEKVi6/8ij300KBWTJq32P/dYeWTSwK41WyTxalN1eRmA5Z9UU/LX9D7FWSmV9SAYx6g=="], + "event-target-shim": ["event-target-shim@5.0.1", "", {}, "sha512-i/2XbnSz/uxRCU6+NdVJgKWDTM427+MqYbkQzD321DuCQJUqOuJKIA0IM2+W2xtYHdKOmZ4dR6fExsd4SXL+WQ=="], + "extract-zip": ["extract-zip@2.0.1", "", { "dependencies": { "debug": "^4.1.1", "get-stream": "^5.1.0", "yauzl": "^2.10.0" }, "optionalDependencies": { "@types/yauzl": "^2.9.1" }, "bin": { "extract-zip": "cli.js" } }, "sha512-GDhU9ntwuKyGXdZBUgTIe+vXnWj0fppUEtMDL0+idd5Sta8TGpHssn/eusA9mrPr9qNDym6SxAYZjNvCn/9RBg=="], + + "fast-fifo": ["fast-fifo@1.3.2", "", {}, "sha512-/d9sfos4yxzpwkDkuN7k2SqFKtYNmCTzgfEpz82x34IM9/zc8KGxQoXg1liNC/izpRM/MBdt44Nmx41ZWqk+FQ=="], + "fast-xml-parser": ["fast-xml-parser@4.4.1", "", { "dependencies": { "strnum": "^1.0.5" }, "bin": { "fxparser": "src/cli/cli.js" } }, "sha512-xkjOecfnKGkSsOwtZ5Pz7Us/T6mrbPQrq0nh+aCO5V9nk5NLWmasAHumTKjiPJPWANe+kAZ84Jc8ooJkzZ88Sw=="], + "fd-slicer": ["fd-slicer@1.1.0", "", { "dependencies": { "pend": "~1.2.0" } }, "sha512-cE1qsB/VwyQozZ+q1dGxR8LBYNZeofhEdUNGSMbQD3Gw2lAzX9Zb3uIU6Ebc/Fmyjo9AWWfnn0AUCHqtevs/8g=="], + "fdir": ["fdir@6.4.5", "", { "peerDependencies": { "picomatch": "^3 || ^4" }, "optionalPeers": ["picomatch"] }, "sha512-4BG7puHpVsIYxZUbiUE3RqGloLaSSwzYie5jvasC4LWuBWzZawynvYouhjbQKw2JuIGYdm0DzIxl8iVidKlUEw=="], "ffmpeg-static": ["ffmpeg-static@5.2.0", "", { "dependencies": { "@derhuerst/http-basic": "^8.2.0", "env-paths": "^2.2.0", "https-proxy-agent": "^5.0.0", "progress": "^2.0.3" } }, "sha512-WrM7kLW+do9HLr+H6tk7LzQ7kPqbAgLjdzNE32+u3Ff11gXt9Kkkd2nusGFrlWMIe+XaA97t+I8JS7sZIrvRgA=="], @@ -451,10 +520,16 @@ "gensync": ["gensync@1.0.0-beta.2", "", {}, "sha512-3hN7NaskYvMDLQY55gnW3NQ+mesEAepTqlg+VEbj7zzqEMBVNhzcGYYeqFo/TlYz6eQiFcp1HcsCZO+nGgS8zg=="], + "get-caller-file": ["get-caller-file@2.0.5", "", {}, "sha512-DyFP3BM/3YHTQOCUL/w0OZHR0lpKeGrxotcHWcqNEdnltqFwXVfhEBQ94eIo34AfQpo0rGki4cyIiftY06h2Fg=="], + "get-intrinsic": ["get-intrinsic@1.3.0", "", { "dependencies": { "call-bind-apply-helpers": "^1.0.2", "es-define-property": "^1.0.1", "es-errors": "^1.3.0", "es-object-atoms": "^1.1.1", "function-bind": "^1.1.2", "get-proto": "^1.0.1", "gopd": "^1.2.0", "has-symbols": "^1.1.0", "hasown": "^2.0.2", "math-intrinsics": "^1.1.0" } }, "sha512-9fSjSaos/fRIVIp+xSJlE6lfwhES7LNtKaCBIamHsjr2na1BiABJPo0mOjjz8GJDURarmCPGqaiVg5mfjb98CQ=="], "get-proto": ["get-proto@1.0.1", "", { "dependencies": { "dunder-proto": "^1.0.1", "es-object-atoms": "^1.0.0" } }, "sha512-sTSfBjoXBp89JvIKIefqw7U2CCebsc74kiY6awiGogKtoSGbgjYE/G/+l9sF3MWFPNc9IcoOC4ODfKHfxFmp0g=="], + "get-stream": ["get-stream@5.2.0", "", { "dependencies": { "pump": "^3.0.0" } }, "sha512-nBF+F1rAZVCu/p7rjzgA+Yb4lfYXrpl7a6VmJrU8wF9I1CKvP/QwPNZHnOlwbTkY6dvtFIzFMSyQXbLoTQPRpA=="], + + "get-uri": ["get-uri@6.0.4", "", { "dependencies": { "basic-ftp": "^5.0.2", "data-uri-to-buffer": "^6.0.2", "debug": "^4.3.4" } }, "sha512-E1b1lFFLvLgak2whF2xDBcOy6NLVGZBqqjJjsIhvopKfWWEi64pLVTWWehV8KlLerZkfNTA95sTe2OdJKm1OzQ=="], + "globals": ["globals@11.12.0", "", {}, "sha512-WOBp/EEGUiIsJSp7wcv/y6MO+lV9UoncWqxuFfm8eBwzWNgyfBd6Gz+IeKQ9jCmyhoH99g15M3T+QaVHFjizVA=="], "gopd": ["gopd@1.2.0", "", {}, "sha512-ZUKRh6/kUFoAiTAtTYPZJ3hw9wNxx+BIBOijnlG9PnrJsCcSjs1wyyD6vJpaYtgnzDrKYRSqf3OO6Rfa93xsRg=="], @@ -469,6 +544,8 @@ "htmlparser2": ["htmlparser2@9.1.0", "", { "dependencies": { "domelementtype": "^2.3.0", "domhandler": "^5.0.3", "domutils": "^3.1.0", "entities": "^4.5.0" } }, "sha512-5zfg6mHUoaer/97TxnGpxmbR7zJtPwIYFMZ/H5ucTlPZhKvtum05yiPK3Mgai3a0DyVxv7qYqoweaEd2nrYQzQ=="], + "http-proxy-agent": ["http-proxy-agent@7.0.2", "", { "dependencies": { "agent-base": "^7.1.0", "debug": "^4.3.4" } }, "sha512-T1gkAiYYDWYx3V5Bmyu7HcfcvL7mUrTWiM6yOfa3PIphViJ/gFPbvidQ+veqSOHci/PxBcDabeUNCzpOODJZig=="], + "http-response-object": ["http-response-object@3.0.2", "", { "dependencies": { "@types/node": "^10.0.3" } }, "sha512-bqX0XTF6fnXSQcEJ2Iuyr75yVakyjIDCqroJQ/aHfSdlM743Cwqoi2nDYMzLGWUcuTWGWy8AAvOKXTfiv6q9RA=="], "https-proxy-agent": ["https-proxy-agent@5.0.1", "", { "dependencies": { "agent-base": "6", "debug": "4" } }, "sha512-dFcAjpTQFgoLMzC2VwU+C/CbS7uRL0lWmxDITmqm7C+7F0Odmj6s9l6alZc6AELXhrnggM2CeWSXHGOdX2YtwA=="], @@ -477,16 +554,32 @@ "iconv-lite": ["iconv-lite@0.6.3", "", { "dependencies": { "safer-buffer": ">= 2.1.2 < 3.0.0" } }, "sha512-4fCk79wshMdzMp2rH06qWrJE4iolqLhCUH+OiuIgU++RB0+94NlDL81atO7GX55uUKueo0txHNtvEyI6D7WdMw=="], + "import-fresh": ["import-fresh@3.3.1", "", { "dependencies": { "parent-module": "^1.0.0", "resolve-from": "^4.0.0" } }, "sha512-TR3KfrTZTYLPB6jUjfx6MF9WcWrHL9su5TObK4ZkYgBdWKPOFoSoQIdEuTuR82pmtxH2spWG9h6etwfr1pLBqQ=="], + "inherits": ["inherits@2.0.4", "", {}, "sha512-k/vGaX4/Yla3WzyMCvTQOXYeIHvqOKtnqBduzTHpzpQZzAskKMhZ2K+EnBiSM9zGSoIFeMpXKxa4dYeZIQqewQ=="], "invariant": ["invariant@2.2.4", "", { "dependencies": { "loose-envify": "^1.0.0" } }, "sha512-phJfQVBuaJM5raOpJjSfkiD6BpbCE4Ns//LaXl6wGYtUBY83nWS6Rf9tXm2e8VaK60JEjYldbPif/A2B1C2gNA=="], + "ip-address": ["ip-address@9.0.5", "", { "dependencies": { "jsbn": "1.1.0", "sprintf-js": "^1.1.3" } }, "sha512-zHtQzGojZXTwZTHQqra+ETKd4Sn3vgi7uBmlPoXVWZqYvuKmtI0l/VZTjqGmJY9x88GGOaZ9+G9ES8hC4T4X8g=="], + + "is-arrayish": ["is-arrayish@0.2.1", "", {}, "sha512-zz06S8t0ozoDXMG+ube26zeCTNXcKIPJZJi8hBrF4idCLms4CG9QtK7qBl1boi5ODzFpjswb5JPmHCbMpjaYzg=="], + + "is-fullwidth-code-point": ["is-fullwidth-code-point@3.0.0", "", {}, "sha512-zymm5+u+sCsSWyD9qNaejV3DFvhCKclKdizYaJUuHA83RLjb7nSuGnddCHGv0hk+KY7BMAlsWeK4Ueg6EV6XQg=="], + "js-tokens": ["js-tokens@4.0.0", "", {}, "sha512-RdJUflcE3cUzKiMqQgsCu06FPu9UdIJO0beYbPhHN4k6apgJtifcoCtT9bcxOpYBtpD2kCM6Sbzg4CausW/PKQ=="], + "js-yaml": ["js-yaml@4.1.0", "", { "dependencies": { "argparse": "^2.0.1" }, "bin": { "js-yaml": "bin/js-yaml.js" } }, "sha512-wpxZs9NoxZaJESJGIZTyDEaYpl0FKSA+FB9aJiyemKhMwkxQg63h4T1KJgUGHpTqPDNRcmmYLugrRjJlBtWvRA=="], + + "jsbn": ["jsbn@1.1.0", "", {}, "sha512-4bYVV3aAMtDTTu4+xsDYa6sy9GyJ69/amsu9sYF2zqjiEoZA5xJi3BrfX3uY+/IekIu7MwdObdbDWpoZdBv3/A=="], + "jsesc": ["jsesc@3.1.0", "", { "bin": { "jsesc": "bin/jsesc" } }, "sha512-/sM3dO2FOzXjKQhJuo0Q173wf2KOo8t4I8vHy6lF9poUp7bKT0/NHE8fPX23PwfhnykfqnC2xRxOnVw5XuGIaA=="], + "json-parse-even-better-errors": ["json-parse-even-better-errors@2.3.1", "", {}, "sha512-xyFwyhro/JEof6Ghe2iz2NcXoj2sloNsWr/XsERDK/oiPCfaNhl5ONfp+jQdAZRQQ0IJWNzH9zIZF7li91kh2w=="], + "json5": ["json5@2.2.3", "", { "bin": { "json5": "lib/cli.js" } }, "sha512-XmOWe7eyHYH14cLdVPoyg+GOH3rYX++KpzrylJwSW98t3Nk+U8XOl8FWKOgwtzdb8lXGf6zYwDUzeHMWfxasyg=="], + "lines-and-columns": ["lines-and-columns@1.2.4", "", {}, "sha512-7ylylesZQ/PV29jhEDl3Ufjo6ZX7gCqJr5F7PKrqc93v7fzSymt1BpwEU8nAUXs8qzzvqhbjhK5QZg6Mt/HkBg=="], + "loose-envify": ["loose-envify@1.4.0", "", { "dependencies": { "js-tokens": "^3.0.0 || ^4.0.0" }, "bin": { "loose-envify": "cli.js" } }, "sha512-lyuxPGr/Wfhrlem2CL/UcnUc1zcqKAImBDzukY7Y5F/yQiNdko6+fRLevlw1HgMySw7f611UIY408EtxRSoK3Q=="], "lru-cache": ["lru-cache@5.1.1", "", { "dependencies": { "yallist": "^3.0.2" } }, "sha512-KpNARQA3Iwv+jTA0utUVVbrh+Jlrr1Fv0e56GGzAFOXN7dk/FviaDW8LHmK52DlcH4WP2n6gI8vN1aesBFgo9w=="], @@ -497,10 +590,14 @@ "mime-types": ["mime-types@2.1.35", "", { "dependencies": { "mime-db": "1.52.0" } }, "sha512-ZDY+bPm5zTTF+YpCrAU9nK0UgICYPT0QtT1NZWFv4s++TNkcgVaT0g6+4R2uI4MjQjzysHB1zxuWL50hzaeXiw=="], + "mitt": ["mitt@3.0.1", "", {}, "sha512-vKivATfr97l2/QBCYAkXYDbrIWPM2IIKEl7YPhjCvKlG3kE2gm+uBo6nEXK3M5/Ffh/FLpKExzOQ3JJoJGFKBw=="], + "ms": ["ms@2.1.3", "", {}, "sha512-6FlzubTLZG3J2a/NVCAleEhjzq5oxgHyaCU9yYXvcLsvoVaHJq/s5xXI6/XXP6tz7R9xAOtHnSO/tXtF3WRTlA=="], "nanoid": ["nanoid@3.3.11", "", { "bin": { "nanoid": "bin/nanoid.cjs" } }, "sha512-N8SpfPUnUp1bK+PMYW8qSWdl9U+wwNWI4QKxOYDy9JAro3WMX7p2OeVRF9v+347pnakNevPmiHhNmZ2HbFA76w=="], + "netmask": ["netmask@2.0.2", "", {}, "sha512-dBpDMdxv9Irdq66304OLfEmQ9tbNRFnFTuZiLo+bD+r332bBmMJ8GBLXklIXXgxd3+v9+KUnZaUR5PJMa75Gsg=="], + "node-domexception": ["node-domexception@1.0.0", "", {}, "sha512-/jKZoMpw0F8GRwl4/eLROPA3cfcXtLApP0QzLmUT/HuPCZWyB7IY9ZrMeKw2O/nFIqPQB3PVM9aYm0F312AXDQ=="], "node-fetch": ["node-fetch@2.7.0", "", { "dependencies": { "whatwg-url": "^5.0.0" }, "peerDependencies": { "encoding": "^0.1.0" }, "optionalPeers": ["encoding"] }, "sha512-c4FRfUm/dbcWZ7U+1Wq0AwCyFL+3nt2bEw05wfxSz+DWpWsitgmSgYmy2dQdWyKC1694ELPqMs/YzUSNozLt8A=="], @@ -509,16 +606,28 @@ "nth-check": ["nth-check@2.1.1", "", { "dependencies": { "boolbase": "^1.0.0" } }, "sha512-lqjrjmaOoAnWfMmBPL+XNnynZh2+swxiX3WUE0s4yEHI6m+AwrK2UZOimIRl3X/4QctVqS8AiZjFqyOGrMXb/w=="], + "once": ["once@1.4.0", "", { "dependencies": { "wrappy": "1" } }, "sha512-lNaJgI+2Q5URQBkccEKHTQOPaXdUxnZZElQTZY0MFUAuaEqe1E+Nyvgdz/aIyNi6Z9MzO5dv1H8n58/GELp3+w=="], + "openai": ["openai@4.104.0", "", { "dependencies": { "@types/node": "^18.11.18", "@types/node-fetch": "^2.6.4", "abort-controller": "^3.0.0", "agentkeepalive": "^4.2.1", "form-data-encoder": "1.7.2", "formdata-node": "^4.3.2", "node-fetch": "^2.6.7" }, "peerDependencies": { "ws": "^8.18.0", "zod": "^3.23.8" }, "optionalPeers": ["ws", "zod"], "bin": { "openai": "bin/cli" } }, "sha512-p99EFNsA/yX6UhVO93f5kJsDRLAg+CTA2RBqdHK4RtK8u5IJw32Hyb2dTGKbnnFmnuoBv5r7Z2CURI9sGZpSuA=="], + "pac-proxy-agent": ["pac-proxy-agent@7.2.0", "", { "dependencies": { "@tootallnate/quickjs-emscripten": "^0.23.0", "agent-base": "^7.1.2", "debug": "^4.3.4", "get-uri": "^6.0.1", "http-proxy-agent": "^7.0.0", "https-proxy-agent": "^7.0.6", "pac-resolver": "^7.0.1", "socks-proxy-agent": "^8.0.5" } }, "sha512-TEB8ESquiLMc0lV8vcd5Ql/JAKAoyzHFXaStwjkzpOpC5Yv+pIzLfHvjTSdf3vpa2bMiUQrg9i6276yn8666aA=="], + + "pac-resolver": ["pac-resolver@7.0.1", "", { "dependencies": { "degenerator": "^5.0.0", "netmask": "^2.0.2" } }, "sha512-5NPgf87AT2STgwa2ntRMr45jTKrYBGkVU36yT0ig/n/GMAa3oPqhZfIQ2kMEimReg0+t9kZViDVZ83qfVUlckg=="], + + "parent-module": ["parent-module@1.0.1", "", { "dependencies": { "callsites": "^3.0.0" } }, "sha512-GQ2EWRpQV8/o+Aw8YqtfZZPfNRWZYkbidE9k5rpl/hC3vtHHBfGm2Ifi6qWV+coDGkrUKZAxE3Lot5kcsRlh+g=="], + "parse-cache-control": ["parse-cache-control@1.0.1", "", {}, "sha512-60zvsJReQPX5/QP0Kzfd/VrpjScIQ7SHBW6bFCYfEP+fp0Eppr1SHhIO5nd1PjZtvclzSzES9D/p5nFJurwfWg=="], + "parse-json": ["parse-json@5.2.0", "", { "dependencies": { "@babel/code-frame": "^7.0.0", "error-ex": "^1.3.1", "json-parse-even-better-errors": "^2.3.0", "lines-and-columns": "^1.1.6" } }, "sha512-ayCKvm/phCGxOkYRSCM82iDwct8/EonSEgCSxWxD7ve6jHggsFl4fZVQBPRNgQoKiuV/odhFrGzQXZwbifC8Rg=="], + "parse5": ["parse5@7.3.0", "", { "dependencies": { "entities": "^6.0.0" } }, "sha512-IInvU7fabl34qmi9gY8XOVxhYyMyuH2xUNpb2q8/Y+7552KlejkRvqvD19nMoUW/uQGGbqNpA6Tufu5FL5BZgw=="], "parse5-htmlparser2-tree-adapter": ["parse5-htmlparser2-tree-adapter@7.1.0", "", { "dependencies": { "domhandler": "^5.0.3", "parse5": "^7.0.0" } }, "sha512-ruw5xyKs6lrpo9x9rCZqZZnIUntICjQAd0Wsmp396Ul9lN/h+ifgVV1x1gZHi8euej6wTfpqX8j+BFQxF0NS/g=="], "parse5-parser-stream": ["parse5-parser-stream@7.1.2", "", { "dependencies": { "parse5": "^7.0.0" } }, "sha512-JyeQc9iwFLn5TbvvqACIF/VXG6abODeB3Fwmv/TGdLk2LfbWkaySGY72at4+Ty7EkPZj854u4CrICqNk2qIbow=="], + "pend": ["pend@1.2.0", "", {}, "sha512-F3asv42UuXchdzt+xXqfW1OGlVBe+mxa2mqI0pg5yAHZPvFmY3Y6drSf/GQ1A86WgWEN9Kzh/WrgKa6iGcHXLg=="], + "picocolors": ["picocolors@1.1.1", "", {}, "sha512-xceH2snhtb5M9liqDsmEw56le376mTZkEX/jEb/RxNFyegNul7eNslCXP9FDj/Lcu0X8KEyMceP2ntpaHrDEVA=="], "picomatch": ["picomatch@4.0.2", "", {}, "sha512-M7BAV6Rlcy5u+m6oPhAPFgJTzAioX/6B0DxyvDlo9l8+T3nLKbrczg2WLUyzd45L8RqfUMyGPzekbMvX2Ldkwg=="], @@ -527,6 +636,16 @@ "progress": ["progress@2.0.3", "", {}, "sha512-7PiHtLll5LdnKIMw100I+8xJXR5gW2QwWYkT6iJva0bXitZKa/XMrSbdmg3r2Xnaidz9Qumd0VPaMrZlF9V9sA=="], + "proxy-agent": ["proxy-agent@6.5.0", "", { "dependencies": { "agent-base": "^7.1.2", "debug": "^4.3.4", "http-proxy-agent": "^7.0.1", "https-proxy-agent": "^7.0.6", "lru-cache": "^7.14.1", "pac-proxy-agent": "^7.1.0", "proxy-from-env": "^1.1.0", "socks-proxy-agent": "^8.0.5" } }, "sha512-TmatMXdr2KlRiA2CyDu8GqR8EjahTG3aY3nXjdzFyoZbmB8hrBsTyMezhULIXKnC0jpfjlmiZ3+EaCzoInSu/A=="], + + "proxy-from-env": ["proxy-from-env@1.1.0", "", {}, "sha512-D+zkORCbA9f1tdWRK0RaCR3GPv50cMxcrz4X8k5LTSUD1Dkw47mKJEZQNunItRTkWwgtaUSo1RVFRIG9ZXiFYg=="], + + "pump": ["pump@3.0.2", "", { "dependencies": { "end-of-stream": "^1.1.0", "once": "^1.3.1" } }, "sha512-tUPXtzlGM8FE3P0ZL6DVs/3P58k9nk8/jZeQCurTJylQA8qFYzHFfhBJkuqyE0FifOsQ0uKWekiZ5g8wtr28cw=="], + + "puppeteer": ["puppeteer@24.10.0", "", { "dependencies": { "@puppeteer/browsers": "2.10.5", "chromium-bidi": "5.1.0", "cosmiconfig": "^9.0.0", "devtools-protocol": "0.0.1452169", "puppeteer-core": "24.10.0", "typed-query-selector": "^2.12.0" }, "bin": { "puppeteer": "lib/cjs/puppeteer/node/cli.js" } }, "sha512-Oua9VkGpj0S2psYu5e6mCer6W9AU9POEQh22wRgSXnLXASGH+MwLUVWgLCLeP9QPHHcJ7tySUlg4Sa9OJmaLpw=="], + + "puppeteer-core": ["puppeteer-core@24.10.0", "", { "dependencies": { "@puppeteer/browsers": "2.10.5", "chromium-bidi": "5.1.0", "debug": "^4.4.1", "devtools-protocol": "0.0.1452169", "typed-query-selector": "^2.12.0", "ws": "^8.18.2" } }, "sha512-xX0QJRc8t19iAwRDsAOR38Q/Zx/W6WVzJCEhKCAwp2XMsaWqfNtQ+rBfQW9PlF+Op24d7c8Zlgq9YNmbnA7hdQ=="], + "react": ["react@19.1.0", "", {}, "sha512-FS+XFBNvn3GTAWq26joslQgWNoFu08F4kl0J4CgdNKADkdSGXQyTCnKteIAJy96Br6YbpEU1LSzV5dYtjMkMDg=="], "react-dom": ["react-dom@19.1.0", "", { "dependencies": { "scheduler": "^0.26.0" }, "peerDependencies": { "react": "^19.1.0" } }, "sha512-Xs1hdnE+DyKgeHJeJznQmYMIBG3TKIHJJT95Q58nHLSrElKlGQqDTR2HQ9fx5CN/Gk6Vh/kupBTDLU11/nDk/g=="], @@ -543,6 +662,10 @@ "readable-stream": ["readable-stream@3.6.2", "", { "dependencies": { "inherits": "^2.0.3", "string_decoder": "^1.1.1", "util-deprecate": "^1.0.1" } }, "sha512-9u/sniCrY3D5WdsERHzHE4G2YCXqoG5FTHUiCC4SIbr6XcLZBY05ya9EKjYek9O5xOAwjGq+1JdGBAS7Q9ScoA=="], + "require-directory": ["require-directory@2.1.1", "", {}, "sha512-fGxEI7+wsG9xrvdjsrlmL22OMTTiHRwAMroiEeMgq8gzoLC/PQr7RsRDSTLUg/bZAZtF+TVIkHc6/4RIKrui+Q=="], + + "resolve-from": ["resolve-from@4.0.0", "", {}, "sha512-pb/MYmXstAkysRFx8piNI1tGFNQIFA3vkE3Gq4EuA1dF6gHp/+vgZqsCGJapvy8N3Q+4o7FwvquPJcnZ7RYy4g=="], + "rollup": ["rollup@4.41.1", "", { "dependencies": { "@types/estree": "1.0.7" }, "optionalDependencies": { "@rollup/rollup-android-arm-eabi": "4.41.1", "@rollup/rollup-android-arm64": "4.41.1", "@rollup/rollup-darwin-arm64": "4.41.1", "@rollup/rollup-darwin-x64": "4.41.1", "@rollup/rollup-freebsd-arm64": "4.41.1", "@rollup/rollup-freebsd-x64": "4.41.1", "@rollup/rollup-linux-arm-gnueabihf": "4.41.1", "@rollup/rollup-linux-arm-musleabihf": "4.41.1", "@rollup/rollup-linux-arm64-gnu": "4.41.1", "@rollup/rollup-linux-arm64-musl": "4.41.1", "@rollup/rollup-linux-loongarch64-gnu": "4.41.1", "@rollup/rollup-linux-powerpc64le-gnu": "4.41.1", "@rollup/rollup-linux-riscv64-gnu": "4.41.1", "@rollup/rollup-linux-riscv64-musl": "4.41.1", "@rollup/rollup-linux-s390x-gnu": "4.41.1", "@rollup/rollup-linux-x64-gnu": "4.41.1", "@rollup/rollup-linux-x64-musl": "4.41.1", "@rollup/rollup-win32-arm64-msvc": "4.41.1", "@rollup/rollup-win32-ia32-msvc": "4.41.1", "@rollup/rollup-win32-x64-msvc": "4.41.1", "fsevents": "~2.3.2" }, "bin": { "rollup": "dist/bin/rollup" } }, "sha512-cPmwD3FnFv8rKMBc1MxWCwVQFxwf1JEmSX3iQXrRVVG15zerAIXRjMFVWnd5Q5QvgKF7Aj+5ykXFhUl+QGnyOw=="], "rss-parser": ["rss-parser@3.13.0", "", { "dependencies": { "entities": "^2.0.3", "xml2js": "^0.5.0" } }, "sha512-7jWUBV5yGN3rqMMj7CZufl/291QAhvrrGpDNE4k/02ZchL0npisiYYqULF71jCEKoIiHvK/Q2e6IkDwPziT7+w=="], @@ -561,18 +684,42 @@ "shallowequal": ["shallowequal@1.1.0", "", {}, "sha512-y0m1JoUZSlPAjXVtPPW70aZWfIL/dSP7AFkRnniLCrK/8MDKog3TySTBmckD+RObVxH0v4Tox67+F14PdED2oQ=="], + "smart-buffer": ["smart-buffer@4.2.0", "", {}, "sha512-94hK0Hh8rPqQl2xXc3HsaBoOXKV20MToPkcXvwbISWLEs+64sBq5kFgn2kJDHb1Pry9yrP0dxrCI9RRci7RXKg=="], + + "socks": ["socks@2.8.4", "", { "dependencies": { "ip-address": "^9.0.5", "smart-buffer": "^4.2.0" } }, "sha512-D3YaD0aRxR3mEcqnidIs7ReYJFVzWdd6fXJYUM8ixcQcJRGTka/b3saV0KflYhyVJXKhb947GndU35SxYNResQ=="], + + "socks-proxy-agent": ["socks-proxy-agent@8.0.5", "", { "dependencies": { "agent-base": "^7.1.2", "debug": "^4.3.4", "socks": "^2.8.3" } }, "sha512-HehCEsotFqbPW9sJ8WVYB6UbmIMv7kUUORIF2Nncq4VQvBfNBLibW9YZR5dlYCSUhwcD628pRllm7n+E+YTzJw=="], + + "source-map": ["source-map@0.6.1", "", {}, "sha512-UjgapumWlbMhkBgzT7Ykc5YXUT46F0iKu8SGXq0bcwP5dz/h0Plj6enJqjz1Zbq2l5WaqYnrVbwWOWMyF3F47g=="], + "source-map-js": ["source-map-js@1.2.1", "", {}, "sha512-UXWMKhLOwVKb728IUtQPXxfYU+usdybtUrK/8uGE8CQMvrhOpwvzDBwj0QhSL7MQc7vIsISBG8VQ8+IDQxpfQA=="], + "sprintf-js": ["sprintf-js@1.1.3", "", {}, "sha512-Oo+0REFV59/rz3gfJNKQiBlwfHaSESl1pcGyABQsnnIfWOFt6JNj5gCog2U6MLZ//IGYD+nA8nI+mTShREReaA=="], + + "streamx": ["streamx@2.22.1", "", { "dependencies": { "fast-fifo": "^1.3.2", "text-decoder": "^1.1.0" }, "optionalDependencies": { "bare-events": "^2.2.0" } }, "sha512-znKXEBxfatz2GBNK02kRnCXjV+AA4kjZIUxeWSr3UGirZMJfTE9uiwKHobnbgxWyL/JWro8tTq+vOqAK1/qbSA=="], + + "string-width": ["string-width@4.2.3", "", { "dependencies": { "emoji-regex": "^8.0.0", "is-fullwidth-code-point": "^3.0.0", "strip-ansi": "^6.0.1" } }, "sha512-wKyQRQpjJ0sIp62ErSZdGsjMJWsap5oRNihHhu6G7JVO/9jIB6UyevL+tXuOqrng8j/cxKTWyWUwvSTriiZz/g=="], + "string_decoder": ["string_decoder@1.3.0", "", { "dependencies": { "safe-buffer": "~5.2.0" } }, "sha512-hkRX8U1WjJFd8LsDJ2yQ/wWWxaopEsABU1XfkM8A+j0+85JAGppt16cr1Whg6KIbb4okU6Mql6BOj+uup/wKeA=="], + "strip-ansi": ["strip-ansi@6.0.1", "", { "dependencies": { "ansi-regex": "^5.0.1" } }, "sha512-Y38VPSHcqkFrCpFnQ9vuSXmquuv5oXOKpGeT6aGrr3o3Gc9AlVa6JBfUSOCnbxGGZF+/0ooI7KrPuUSztUdU5A=="], + "strnum": ["strnum@1.1.2", "", {}, "sha512-vrN+B7DBIoTTZjnPNewwhx6cBA/H+IS7rfW68n7XxC1y7uoiGQBxaKzqucGUgavX15dJgiGztLJ8vxuEzwqBdA=="], + "tar-fs": ["tar-fs@3.0.9", "", { "dependencies": { "pump": "^3.0.0", "tar-stream": "^3.1.5" }, "optionalDependencies": { "bare-fs": "^4.0.1", "bare-path": "^3.0.0" } }, "sha512-XF4w9Xp+ZQgifKakjZYmFdkLoSWd34VGKcsTCwlNWM7QG3ZbaxnTsaBwnjFZqHRf/rROxaR8rXnbtwdvaDI+lA=="], + + "tar-stream": ["tar-stream@3.1.7", "", { "dependencies": { "b4a": "^1.6.4", "fast-fifo": "^1.2.0", "streamx": "^2.15.0" } }, "sha512-qJj60CXt7IU1Ffyc3NJMjh6EkuCFej46zUqJ4J7pqYlThyd9bO0XBTmcOIhSzZJVWfsLks0+nle/j538YAW9RQ=="], + + "text-decoder": ["text-decoder@1.2.3", "", { "dependencies": { "b4a": "^1.6.4" } }, "sha512-3/o9z3X0X0fTupwsYvR03pJ/DjWuqqrfwBgTQzdWDiQSm9KitAyz/9WqsT2JQW7KV2m+bC2ol/zqpW37NHxLaA=="], + "tinyglobby": ["tinyglobby@0.2.14", "", { "dependencies": { "fdir": "^6.4.4", "picomatch": "^4.0.2" } }, "sha512-tX5e7OM1HnYr2+a2C/4V0htOcSQcoSTH9KgJnVvNm5zm/cyEWKJ7j7YutsH9CxMdtOkkLFy2AHrMci9IM8IPZQ=="], "tr46": ["tr46@0.0.3", "", {}, "sha512-N3WMsuqV66lT30CrXNbEjx4GEwlow3v6rr4mCcv6prnfwhS01rkgyFdjPNBYd9br7LpXV1+Emh01fHnq2Gdgrw=="], "tslib": ["tslib@2.8.1", "", {}, "sha512-oJFu94HQb+KVduSUQL7wnpmqnfmLsOA/nAh6b6EH0wCEoK0/mPeXU6c3wKDV83MkOuHPRHtSXKKU99IBazS/2w=="], + "typed-query-selector": ["typed-query-selector@2.12.0", "", {}, "sha512-SbklCd1F0EiZOyPiW192rrHZzZ5sBijB6xM+cpmrwDqObvdtunOHHIk9fCGsoK5JVIYXoyEp4iEdE3upFH3PAg=="], + "typedarray": ["typedarray@0.0.6", "", {}, "sha512-/aCDEGatGvZ2BIk+HmLf4ifCJFwvKFNb9/JeZPMulfgFracn9QFcAf5GO8B/mweUjSoblS5In0cWhqpfs/5PQA=="], "typescript": ["typescript@5.8.3", "", { "bin": { "tsc": "bin/tsc", "tsserver": "bin/tsserver" } }, "sha512-p1diW6TqL9L07nNxvRMM7hMMw4c5XOo/1ibL4aAIGmSAt9slTE1Xgw5KWuof2uTOvCg9BY7ZRi+GaF+7sfgPeQ=="], @@ -599,16 +746,34 @@ "whatwg-url": ["whatwg-url@5.0.0", "", { "dependencies": { "tr46": "~0.0.3", "webidl-conversions": "^3.0.0" } }, "sha512-saE57nupxk6v3HY35+jzBwYa0rKSy0XR8JSxZPwgLr7ys0IBzhGviA1/TUGJLmSVqs8pb9AnvICXEuOHLprYTw=="], + "wrap-ansi": ["wrap-ansi@7.0.0", "", { "dependencies": { "ansi-styles": "^4.0.0", "string-width": "^4.1.0", "strip-ansi": "^6.0.0" } }, "sha512-YVGIj2kamLSTxw6NsZjoBxfSwsn0ycdesmc4p+Q21c5zPuZ1pl+NfxVdxPtdHvmNVOQ6XSYG4AUtyt/Fi7D16Q=="], + + "wrappy": ["wrappy@1.0.2", "", {}, "sha512-l4Sp/DRseor9wL6EvV2+TuQn63dMkPjZ/sp9XkghTEbV9KlPS1xUsZ3u7/IQO4wxtcFB4bgpQPRcR3QCvezPcQ=="], + + "ws": ["ws@8.18.2", "", { "peerDependencies": { "bufferutil": "^4.0.1", "utf-8-validate": ">=5.0.2" }, "optionalPeers": ["bufferutil", "utf-8-validate"] }, "sha512-DMricUmwGZUVr++AEAe2uiVM7UoO9MAVZMDu05UQOaUII0lp+zOzLLU4Xqh/JvTqklB1T4uELaaPBKyjE1r4fQ=="], + "xml2js": ["xml2js@0.6.2", "", { "dependencies": { "sax": ">=0.6.0", "xmlbuilder": "~11.0.0" } }, "sha512-T4rieHaC1EXcES0Kxxj4JWgaUQHDk+qwHcYOCFHfiwKz7tOVPLq7Hjq9dM1WCMhylqMEfP7hMcOIChvotiZegA=="], "xmlbuilder": ["xmlbuilder@11.0.1", "", {}, "sha512-fDlsI/kFEx7gLvbecc0/ohLG50fugQp8ryHzMTuW9vSa1GJ0XYWKnhsUx7oie3G98+r56aTQIUB4kht42R3JvA=="], + "y18n": ["y18n@5.0.8", "", {}, "sha512-0pfFzegeDWJHJIAmTLRP2DwHjdF5s7jo9tuztdQxAhINCdvS+3nGINqPd00AphqJR/0LhANUS6/+7SCb98YOfA=="], + "yallist": ["yallist@3.1.1", "", {}, "sha512-a4UGQaWPH59mOXUYnAG2ewncQS4i4F43Tv3JoAM+s2VDAmS9NsK8GpDMLrCHPksFT7h3K6TOoUNn2pb7RoXx4g=="], + "yargs": ["yargs@17.7.2", "", { "dependencies": { "cliui": "^8.0.1", "escalade": "^3.1.1", "get-caller-file": "^2.0.5", "require-directory": "^2.1.1", "string-width": "^4.2.3", "y18n": "^5.0.5", "yargs-parser": "^21.1.1" } }, "sha512-7dSzzRQ++CKnNI/krKnYRV7JKKPUXMEh61soaHKg9mrWEhzFWhFnxPxGl+69cD1Ou63C13NUPCnmIcrvqCuM6w=="], + + "yargs-parser": ["yargs-parser@21.1.1", "", {}, "sha512-tVpsJW7DdjecAiFpbIB1e3qxIQsE6NoPc5/eTdrbbIC4h0LVsWhnoa3g+m2HclBIujHzsxZ4VJVA+GUuc2/LBw=="], + + "yauzl": ["yauzl@2.10.0", "", { "dependencies": { "buffer-crc32": "~0.2.3", "fd-slicer": "~1.1.0" } }, "sha512-p4a9I6X6nu6IhoGmBqAcbJy1mlC4j27vEPZX9F4L4/vZT3Lyq1VkFHw/V/PUcB9Buo+DG3iHkT0x3Qya58zc3g=="], + + "zod": ["zod@3.25.56", "", {}, "sha512-rd6eEF3BTNvQnR2e2wwolfTmUTnp70aUTqr0oaGbHifzC3BKJsoV+Gat8vxUMR1hwOKBs6El+qWehrHbCpW6SQ=="], + "@aws-crypto/sha256-browser/@smithy/util-utf8": ["@smithy/util-utf8@2.3.0", "", { "dependencies": { "@smithy/util-buffer-from": "^2.2.0", "tslib": "^2.6.2" } }, "sha512-R8Rdn8Hy72KKcebgLiv8jQcQkXoLMOGGv5uI1/k0l+snqkOzQ1R0ChUBCxWMlBsFMekWjq0wRudIweFs7sKT5A=="], "@aws-crypto/util/@smithy/util-utf8": ["@smithy/util-utf8@2.3.0", "", { "dependencies": { "@smithy/util-buffer-from": "^2.2.0", "tslib": "^2.6.2" } }, "sha512-R8Rdn8Hy72KKcebgLiv8jQcQkXoLMOGGv5uI1/k0l+snqkOzQ1R0ChUBCxWMlBsFMekWjq0wRudIweFs7sKT5A=="], + "@puppeteer/browsers/semver": ["semver@7.7.2", "", { "bin": { "semver": "bin/semver.js" } }, "sha512-RF0Fw+rO5AMf9MAyaRXI4AV0Ulj5lMHqVxxdSgiVbixSCXoEmmX/jk0CuJw4+3SqroYO9VoUh+HcuJivvtJemA=="], + "@types/node-fetch/@types/node": ["@types/node@18.19.110", "", { "dependencies": { "undici-types": "~5.26.4" } }, "sha512-WW2o4gTmREtSnqKty9nhqF/vA0GKd0V/rbC0OyjSk9Bz6bzlsXKT+i7WDdS/a0z74rfT2PO4dArVCSnapNLA5Q=="], "bun-types/@types/node": ["@types/node@18.19.110", "", { "dependencies": { "undici-types": "~5.26.4" } }, "sha512-WW2o4gTmREtSnqKty9nhqF/vA0GKd0V/rbC0OyjSk9Bz6bzlsXKT+i7WDdS/a0z74rfT2PO4dArVCSnapNLA5Q=="], @@ -617,14 +782,28 @@ "htmlparser2/entities": ["entities@4.5.0", "", {}, "sha512-V0hjH4dGPh9Ao5p0MoRY6BVqtwCjhz6vI5LT8AJ55H+4g9/4vbHx1I54fS0XuclLhDHArPQCiMjDxjaL8fPxhw=="], + "http-proxy-agent/agent-base": ["agent-base@7.1.3", "", {}, "sha512-jRR5wdylq8CkOe6hei19GGZnxM6rBGwFl3Bg0YItGDimvjGtAvdZk4Pu6Cl4u4Igsws4a1fd1Vq3ezrhn4KmFw=="], + "http-response-object/@types/node": ["@types/node@10.17.60", "", {}, "sha512-F0KIgDJfy2nA3zMLmWGKxcH2ZVEtCZXHHdOQs2gSaQ27+lNeEfGxzkIw90aXswATX7AZ33tahPbzy6KAfUreVw=="], "openai/@types/node": ["@types/node@18.19.110", "", { "dependencies": { "undici-types": "~5.26.4" } }, "sha512-WW2o4gTmREtSnqKty9nhqF/vA0GKd0V/rbC0OyjSk9Bz6bzlsXKT+i7WDdS/a0z74rfT2PO4dArVCSnapNLA5Q=="], + "pac-proxy-agent/agent-base": ["agent-base@7.1.3", "", {}, "sha512-jRR5wdylq8CkOe6hei19GGZnxM6rBGwFl3Bg0YItGDimvjGtAvdZk4Pu6Cl4u4Igsws4a1fd1Vq3ezrhn4KmFw=="], + + "pac-proxy-agent/https-proxy-agent": ["https-proxy-agent@7.0.6", "", { "dependencies": { "agent-base": "^7.1.2", "debug": "4" } }, "sha512-vK9P5/iUfdl95AI+JVyUuIcVtd4ofvtrOr3HNtM2yxC9bnMbEdp3x01OhQNnjb8IJYi38VlTE3mBXwcfvywuSw=="], + "parse5/entities": ["entities@6.0.0", "", {}, "sha512-aKstq2TDOndCn4diEyp9Uq/Flu2i1GlLkc6XIDQSDMuaFE3OPW5OphLCyQ5SpSJZTb4reN+kTcYru5yIfXoRPw=="], + "proxy-agent/agent-base": ["agent-base@7.1.3", "", {}, "sha512-jRR5wdylq8CkOe6hei19GGZnxM6rBGwFl3Bg0YItGDimvjGtAvdZk4Pu6Cl4u4Igsws4a1fd1Vq3ezrhn4KmFw=="], + + "proxy-agent/https-proxy-agent": ["https-proxy-agent@7.0.6", "", { "dependencies": { "agent-base": "^7.1.2", "debug": "4" } }, "sha512-vK9P5/iUfdl95AI+JVyUuIcVtd4ofvtrOr3HNtM2yxC9bnMbEdp3x01OhQNnjb8IJYi38VlTE3mBXwcfvywuSw=="], + + "proxy-agent/lru-cache": ["lru-cache@7.18.3", "", {}, "sha512-jumlc0BIUrS3qJGgIkWZsyfAM7NCWiBcCDhnd+3NNM5KbBmLTgHVfWBcg6W+rLUsIpzpERPsvwUP7CckAQSOoA=="], + "rss-parser/xml2js": ["xml2js@0.5.0", "", { "dependencies": { "sax": ">=0.6.0", "xmlbuilder": "~11.0.0" } }, "sha512-drPFnkQJik/O+uPKpqSgr22mpuFHqKdbS835iAQrUC73L2F5WkboIRd63ai/2Yg6I1jzifPFKH2NTK+cfglkIA=="], + "socks-proxy-agent/agent-base": ["agent-base@7.1.3", "", {}, "sha512-jRR5wdylq8CkOe6hei19GGZnxM6rBGwFl3Bg0YItGDimvjGtAvdZk4Pu6Cl4u4Igsws4a1fd1Vq3ezrhn4KmFw=="], + "@aws-crypto/sha256-browser/@smithy/util-utf8/@smithy/util-buffer-from": ["@smithy/util-buffer-from@2.2.0", "", { "dependencies": { "@smithy/is-array-buffer": "^2.2.0", "tslib": "^2.6.2" } }, "sha512-IJdWBbTcMQ6DA0gdNhh/BwrLkDR+ADW5Kr1aZmd4k3DIF6ezMV4R2NIAmT08wQJ3yUK82thHWmC/TnK/wpMMIA=="], "@aws-crypto/util/@smithy/util-utf8/@smithy/util-buffer-from": ["@smithy/util-buffer-from@2.2.0", "", { "dependencies": { "@smithy/is-array-buffer": "^2.2.0", "tslib": "^2.6.2" } }, "sha512-IJdWBbTcMQ6DA0gdNhh/BwrLkDR+ADW5Kr1aZmd4k3DIF6ezMV4R2NIAmT08wQJ3yUK82thHWmC/TnK/wpMMIA=="], diff --git a/package.json b/package.json index b7ae6c1..a3f1d7d 100644 --- a/package.json +++ b/package.json @@ -23,6 +23,7 @@ "ffmpeg-static": "^5.2.0", "hono": "^4.7.11", "openai": "^4.104.0", + "puppeteer": "^24.10.0", "react": "^19.1.0", "react-dom": "^19.1.0", "react-helmet-async": "^2.0.5", diff --git a/scripts/fetch_and_generate.ts b/scripts/fetch_and_generate.ts index 8ce9fa9..09bf690 100644 --- a/scripts/fetch_and_generate.ts +++ b/scripts/fetch_and_generate.ts @@ -2,7 +2,7 @@ import crypto from "crypto"; import fs from "fs/promises"; import Parser from "rss-parser"; import { config } from "../services/config.js"; -import { enhanceArticleContent } from "../services/content-extractor.js"; +import { enhanceArticleContent, closeBrowser } from "../services/content-extractor.js"; import { getFeedById, getFeedByUrl, @@ -425,6 +425,9 @@ async function processRetryQueue(abortSignal?: AbortSignal): Promise { closeError, ); } + + // Close Puppeteer browser on exit + await closeBrowser(); } } diff --git a/server.ts b/server.ts index ca1b6f7..3c2e831 100644 --- a/server.ts +++ b/server.ts @@ -3,6 +3,7 @@ import { serve } from "@hono/node-server"; import { Hono } from "hono"; import { batchScheduler } from "./services/batch-scheduler.js"; import { config, validateConfig } from "./services/config.js"; +import { closeBrowser } from "./services/content-extractor.js"; // Validate configuration on startup try { @@ -572,6 +573,19 @@ app.get("*", serveIndex); // Batch processing - now using batch scheduler console.log("πŸ”„ Batch scheduler initialized and ready"); +// Graceful shutdown +process.on('SIGINT', async () => { + console.log('\nπŸ›‘ Received SIGINT. Graceful shutdown...'); + await closeBrowser(); + process.exit(0); +}); + +process.on('SIGTERM', async () => { + console.log('\nπŸ›‘ Received SIGTERM. Graceful shutdown...'); + await closeBrowser(); + process.exit(0); +}); + // ァーバー衷動 serve( { diff --git a/services/content-extractor.ts b/services/content-extractor.ts index e4f1080..437c1b7 100644 --- a/services/content-extractor.ts +++ b/services/content-extractor.ts @@ -1,4 +1,4 @@ -import * as cheerio from "cheerio"; +import puppeteer, { type Browser } from "puppeteer"; export interface ExtractedContent { title?: string; @@ -8,126 +8,194 @@ export interface ExtractedContent { error?: string; } +// Singleton browser instance for reuse +let sharedBrowser: Browser | null = null; + +async function getBrowser(): Promise { + if (!sharedBrowser || !sharedBrowser.isConnected()) { + sharedBrowser = await puppeteer.launch({ + headless: true, + args: [ + "--no-sandbox", + "--disable-setuid-sandbox", + "--disable-dev-shm-usage", + "--disable-accelerated-2d-canvas", + "--no-first-run", + "--no-zygote", + "--disable-gpu", + "--disable-web-security", + "--disable-features=VizDisplayCompositor", + ], + }); + } + return sharedBrowser; +} + +export async function closeBrowser(): Promise { + if (sharedBrowser && sharedBrowser.isConnected()) { + await sharedBrowser.close(); + sharedBrowser = null; + } +} + export async function extractArticleContent( url: string, ): Promise { + let page = null; try { - // Fetch the HTML content - const response = await fetch(url, { - headers: { - "User-Agent": - "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36", - Accept: - "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8", - "Accept-Language": "ja,en-US;q=0.7,en;q=0.3", - "Accept-Encoding": "gzip, deflate", - Connection: "keep-alive", - "Upgrade-Insecure-Requests": "1", - }, - signal: AbortSignal.timeout(30000), // 30 second timeout + const browser = await getBrowser(); + page = await browser.newPage(); + + // Set user agent and viewport + await page.setUserAgent( + "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36", + ); + await page.setViewport({ width: 1280, height: 720 }); + + // Set navigation timeout + page.setDefaultNavigationTimeout(30000); + page.setDefaultTimeout(30000); + + // Navigate to the page + const response = await page.goto(url, { + waitUntil: "networkidle2", + timeout: 30000, }); - if (!response.ok) { - throw new Error(`HTTP ${response.status}: ${response.statusText}`); + if (!response || !response.ok()) { + throw new Error(`HTTP ${response?.status()}: Failed to load page`); } - const html = await response.text(); - const $ = cheerio.load(html); + // Wait for potential dynamic content + await new Promise(resolve => setTimeout(resolve, 2000)); - // Remove unwanted elements - $( - "script, style, nav, header, footer, aside, .advertisement, .ads, .sidebar, .menu, .navigation, .social-share, .comments", - ).remove(); + // Extract content using page.evaluate + const extractedData = await page.evaluate(() => { + // Remove unwanted elements + const unwantedSelectors = [ + "script", + "style", + "nav", + "header", + "footer", + "aside", + ".advertisement", + ".ads", + ".sidebar", + ".menu", + ".navigation", + ".social-share", + ".comments", + ".cookie-banner", + ".popup", + ".modal", + ]; - let content = ""; - let title = ""; - let description = ""; + unwantedSelectors.forEach((selector) => { + const elements = document.querySelectorAll(selector); + elements.forEach((el) => el.remove()); + }); - // Extract title - title = - $("title").text().trim() || - $("h1").first().text().trim() || - $('meta[property="og:title"]').attr("content") || - ""; + let content = ""; + let title = ""; + let description = ""; - // Extract description - description = - $('meta[name="description"]').attr("content") || - $('meta[property="og:description"]').attr("content") || - ""; + // Extract title + const titleElement = document.querySelector("title"); + const h1Element = document.querySelector("h1"); + const ogTitleMeta = document.querySelector('meta[property="og:title"]'); - // Try multiple content extraction strategies - const contentSelectors = [ - // Common article selectors - "article", - '[role="main"]', - ".article-content", - ".post-content", - ".entry-content", - ".content", - ".main-content", - ".article-body", - ".post-body", - ".story-body", - ".news-content", + title = + titleElement?.textContent?.trim() || + h1Element?.textContent?.trim() || + ogTitleMeta?.getAttribute("content") || + ""; - // Japanese news site specific selectors - ".article", - ".news-article", - ".post", - ".entry", - "#content", - "#main", - ".main", + // Extract description + const descriptionMeta = document.querySelector('meta[name="description"]'); + const ogDescriptionMeta = document.querySelector( + 'meta[property="og:description"]', + ); - // Fallback to common containers - ".container", - "#container", - "main", - "body", - ]; + description = + descriptionMeta?.getAttribute("content") || + ogDescriptionMeta?.getAttribute("content") || + ""; - for (const selector of contentSelectors) { - const element = $(selector); - if (element.length > 0) { - // Get text content and clean it up - let extractedText = element.text().trim(); + // Try multiple content extraction strategies + const contentSelectors = [ + // Common article selectors + "article", + '[role="main"]', + ".article-content", + ".post-content", + ".entry-content", + ".content", + ".main-content", + ".article-body", + ".post-body", + ".story-body", + ".news-content", - // Remove extra whitespace and normalize - extractedText = extractedText - .replace(/\s+/g, " ") - .replace(/\n\s*\n/g, "\n") - .trim(); + // Japanese news site specific selectors + ".article", + ".news-article", + ".post", + ".entry", + "#content", + "#main", + ".main", - // Only use if we found substantial content - if (extractedText.length > 200) { - content = extractedText; - break; + // Fallback to common containers + ".container", + "#container", + "main", + "body", + ]; + + for (const selector of contentSelectors) { + const element = document.querySelector(selector); + if (element) { + // Get text content and clean it up + let extractedText = element.textContent?.trim() || ""; + + // Remove extra whitespace and normalize + extractedText = extractedText + .replace(/\s+/g, " ") + .replace(/\n\s*\n/g, "\n") + .trim(); + + // Only use if we found substantial content + if (extractedText.length > 200) { + content = extractedText; + break; + } } } - } - // If still no content, try paragraph extraction - if (!content) { - const paragraphs = $("p") - .map((_, el) => $(el).text().trim()) - .get(); - content = paragraphs - .filter((p) => p.length > 50) // Filter out short paragraphs - .join("\n\n"); - } + // If still no content, try paragraph extraction + if (!content) { + const paragraphs = Array.from(document.querySelectorAll("p")) + .map((p) => p.textContent?.trim() || "") + .filter((p) => p.length > 50); // Filter out short paragraphs + content = paragraphs.join("\n\n"); + } - // Final fallback: use body text - if (!content || content.length < 100) { - content = $("body").text().replace(/\s+/g, " ").trim(); - } + // Final fallback: use body text + if (!content || content.length < 100) { + const bodyText = document.body?.textContent || ""; + content = bodyText.replace(/\s+/g, " ").trim(); + } + + return { title, content, description }; + }); // Validate extracted content - if (!content || content.length < 50) { + if (!extractedData.content || extractedData.content.length < 50) { return { - title, + title: extractedData.title, content: "", - description, + description: extractedData.description, success: false, error: "Insufficient content extracted", }; @@ -135,14 +203,15 @@ export async function extractArticleContent( // Limit content length to avoid token limits const maxLength = 5000; + let content = extractedData.content; if (content.length > maxLength) { content = content.substring(0, maxLength) + "..."; } return { - title, + title: extractedData.title, content, - description, + description: extractedData.description, success: true, }; } catch (error) { @@ -153,6 +222,10 @@ export async function extractArticleContent( success: false, error: error instanceof Error ? error.message : "Unknown error occurred", }; + } finally { + if (page) { + await page.close(); + } } }