From 59b5c73612136edc95488e126ada6b49f77ca730 Mon Sep 17 00:00:00 2001 From: Vitalii Litvinchuk Date: Fri, 19 Jun 2026 14:15:50 +0300 Subject: [PATCH] feat: implement core product scraping infrastructure with Playwright extractors and data formatters --- .gitignore | 9 + package-lock.json | 1129 ++++++++++++++++++++++++++++++++ package.json | 23 + src/extract/extract-product.ts | 20 + src/extract/extractors.ts | 309 +++++++++ src/format/format-product.ts | 14 + src/format/formatters.ts | 83 +++ src/index.ts | 45 ++ src/request/page-loader.ts | 26 + src/types.ts | 51 ++ tsconfig.json | 44 ++ 11 files changed, 1753 insertions(+) create mode 100644 .gitignore create mode 100644 package-lock.json create mode 100644 package.json create mode 100644 src/extract/extract-product.ts create mode 100644 src/extract/extractors.ts create mode 100644 src/format/format-product.ts create mode 100644 src/format/formatters.ts create mode 100644 src/index.ts create mode 100644 src/request/page-loader.ts create mode 100644 src/types.ts create mode 100644 tsconfig.json diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..d4c1b3f --- /dev/null +++ b/.gitignore @@ -0,0 +1,9 @@ +node_modules/ +output/ +dist/ +build/ +.DS_Store +.env +npm-debug.log* +yarn-debug.log* +yarn-error.log* diff --git a/package-lock.json b/package-lock.json new file mode 100644 index 0000000..5d8fc29 --- /dev/null +++ b/package-lock.json @@ -0,0 +1,1129 @@ +{ + "name": "scraper", + "version": "1.0.0", + "lockfileVersion": 3, + "requires": true, + "packages": { + "": { + "name": "scraper", + "version": "1.0.0", + "license": "ISC", + "dependencies": { + "playwright": "^1.50.1", + "playwright-extra": "^4.3.6", + "puppeteer-extra-plugin-stealth": "^2.11.2" + }, + "devDependencies": { + "@types/node": "^22.19.21", + "tsx": "^4.19.3", + "typescript": "^5.8.2" + } + }, + "node_modules/@esbuild/aix-ppc64": { + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/aix-ppc64/-/aix-ppc64-0.28.1.tgz", + "integrity": "sha512-Svl7tq8k/08+p6CXPpRjQ1fKX+1odH/BQbb48fV6fj3CWHhsoIOoY87w1oHXm0qEpkIK3ZfVgp0hed3XBXzXMQ==", + "cpu": [ + "ppc64" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "aix" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/android-arm": { + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/android-arm/-/android-arm-0.28.1.tgz", + "integrity": "sha512-0k2F129Xdio1TdJfzJ8sy1Q47vUD2NnwdhiAf7drUN1EBTfPf4hsFCtmMgu/6m8JSzsBrlmVjudMBQqOfG8usQ==", + "cpu": [ + "arm" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "android" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/android-arm64": { + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/android-arm64/-/android-arm64-0.28.1.tgz", + "integrity": "sha512-34EGEbCIAgosYz6goLcopX6Mo7NyGv9tfwEM2/7Ce2VcVRk568iSvniGWcUXIy7wEDR1wzolcxcriFVrWYcwBg==", + "cpu": [ + "arm64" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "android" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/android-x64": { + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/android-x64/-/android-x64-0.28.1.tgz", + "integrity": "sha512-dbwY7ltSMDWsRatcRpCnES4F+im88OCUgGZjy52shC7GqHRE/cYlxNbB4Z4UpJswpcc4Qxd2oE/ufM0p61IKng==", + "cpu": [ + "x64" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "android" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/darwin-arm64": { + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/darwin-arm64/-/darwin-arm64-0.28.1.tgz", + "integrity": "sha512-TZbWkQY7kvTAXbXUT7uVACR5cMHsDiSz9z7ZKAX/RTq/WJEk3QyRr0wZpNhBDX+/0CtdqUIJlOiodQcta6tY3Q==", + "cpu": [ + "arm64" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "darwin" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/darwin-x64": { + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/darwin-x64/-/darwin-x64-0.28.1.tgz", + "integrity": "sha512-zfdzgK9ACBNZLI/CyHTOx81SyNbM6YXn7rxSgX97VjyiPl9W1i4Ka4fgKECEoFCKGpvBj5qArWIGgQjOwkgskQ==", + "cpu": [ + "x64" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "darwin" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/freebsd-arm64": { + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/freebsd-arm64/-/freebsd-arm64-0.28.1.tgz", + "integrity": "sha512-wG2EA8ENdEI0qhkSZMjfqrdY+ziCYCPMmtZjjIwOmXFjmyzEHn+UUxk5of+SYsjtfs3VpnlC7QLzSI5hY/rOAw==", + "cpu": [ + "arm64" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "freebsd" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/freebsd-x64": { + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/freebsd-x64/-/freebsd-x64-0.28.1.tgz", + "integrity": "sha512-i7dZ9vQgnvSCzi/rYCXNgtF/U+eKZNJBzu3eTQbRgHnM7tNSizLOkRFAl3qzVc/Op/u5YkHHa4pf/3DOYHthLQ==", + "cpu": [ + "x64" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "freebsd" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/linux-arm": { + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/linux-arm/-/linux-arm-0.28.1.tgz", + "integrity": "sha512-qVXBOHQS+d5Y722GwJzJUtOLlX7km3CraOaGormF1pDtPd2C/l1SHRPgjLunLGe51Sh5YYWKMFDyV4SxgMQYTQ==", + "cpu": [ + "arm" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/linux-arm64": { + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/linux-arm64/-/linux-arm64-0.28.1.tgz", + "integrity": "sha512-yHs+0uc8+nvEAfAfxrWQKK5peSNzBc4PegcMO0EJ2hT71uA7vB8Ihg2e77R2P7SG5uYjPbHlLLmve4LLLRCf0g==", + "cpu": [ + "arm64" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/linux-ia32": { + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/linux-ia32/-/linux-ia32-0.28.1.tgz", + "integrity": "sha512-d1z4ZuP0ajrfz/FhGT4vv278rX8KnPPJx8i5+AtK7TYbx9Le9F1hyzurZpkEyjkGa9dUGhQow4C1NmeGvqxN2w==", + "cpu": [ + "ia32" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/linux-loong64": { + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/linux-loong64/-/linux-loong64-0.28.1.tgz", + "integrity": "sha512-M5sRjUVZrkm1OAPR3dlOYzNmN+loZKGVi1VUQGrwuqLcbR6qeAz+famMhjASeH3YVKvZz+zT1jlh/keC3Rj/lg==", + "cpu": [ + "loong64" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/linux-mips64el": { + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/linux-mips64el/-/linux-mips64el-0.28.1.tgz", + "integrity": "sha512-mRObBZeHh2OxcBFPWE/FjylkRgZdYuiTR3vaTozquCGOH14iP9oN4x4Ge81CoIDYQrXmIxpFumJBu5MtZpnQJQ==", + "cpu": [ + "mips64el" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/linux-ppc64": { + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/linux-ppc64/-/linux-ppc64-0.28.1.tgz", + "integrity": "sha512-slScBsMAb3GFDcdrCgLwZtPYRoH2H/youv10QiZyRjmsP48fznoveWytSgCI/R0ZcUgpc0ZhIUEx6LHts8yrfQ==", + "cpu": [ + "ppc64" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/linux-riscv64": { + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/linux-riscv64/-/linux-riscv64-0.28.1.tgz", + "integrity": "sha512-kw0owk1o0GFETUJyW0jc0G4Yzs0BHZn0JDZ8JRT088vjJYX777BAs1fDGxAC+q831qOs2DTC96mNsG2opdfyyQ==", + "cpu": [ + "riscv64" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/linux-s390x": { + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/linux-s390x/-/linux-s390x-0.28.1.tgz", + "integrity": "sha512-/lAIjX8aYFRByhh6L5rYtPEDRqa9de/4V/juOXcta5frjvzXO4/sqEtyytse0g3zZFuWu5cDN0MkLz2qRDD2Ag==", + "cpu": [ + "s390x" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/linux-x64": { + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/linux-x64/-/linux-x64-0.28.1.tgz", + "integrity": "sha512-u/anNYF2mmVOEDwLtnQ1wOr3EZ9sTNGLWrsYGYwHWzGA3Si84IOkHXlbWTD1NB+9/1lcnweYKO54uhxZydNzfA==", + "cpu": [ + "x64" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/netbsd-arm64": { + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/netbsd-arm64/-/netbsd-arm64-0.28.1.tgz", + "integrity": "sha512-oks0DYbLwWMmaakTsCb+zL4E+aHRVLom9IJZOAthMQEPiQmydXHkziYEsGYRx0uNV/IjEKGAV941JzH02pflqw==", + "cpu": [ + "arm64" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "netbsd" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/netbsd-x64": { + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/netbsd-x64/-/netbsd-x64-0.28.1.tgz", + "integrity": "sha512-aeL6lAnN89Hz43Mlh1G8ARasbuoYvSITDEx0tHh5b7jJnHcssqgjy9Yx430GDpmCa6OyrKoS0aNRjKundRizGg==", + "cpu": [ + "x64" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "netbsd" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/openbsd-arm64": { + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/openbsd-arm64/-/openbsd-arm64-0.28.1.tgz", + "integrity": "sha512-MEFJe5C3R8pwXdZ5Y21oo6m7ePiS0d9pWucn99O/wvyJZChoIQKrQDxKrGeW8F5+T0okTHesAmDeiHDTIq0V/Q==", + "cpu": [ + "arm64" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "openbsd" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/openbsd-x64": { + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/openbsd-x64/-/openbsd-x64-0.28.1.tgz", + "integrity": "sha512-i/ZLIOafE0Z8cI/XANJAixoJL/uRAoS2xOA3rb0xN+KK0K177cMAsQYkzHtBrtMXAKuAc7HGgcWiZ/sRC1Nxgw==", + "cpu": [ + "x64" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "openbsd" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/openharmony-arm64": { + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/openharmony-arm64/-/openharmony-arm64-0.28.1.tgz", + "integrity": "sha512-ge+Z7EXFNt2BO1oAMsVpiQ8EwndV9i1xXerAeTIK7AtPs3bKFXQM7nlRxDSIUIMeueR1CNXxqztLzdNeReKBJg==", + "cpu": [ + "arm64" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "openharmony" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/sunos-x64": { + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/sunos-x64/-/sunos-x64-0.28.1.tgz", + "integrity": "sha512-BEjgtECkL3vY+SaSQ6nzVfiALUeFxpawyp8Jmf5PtYhf1Ug40N1h/hxlhts+f1FvSvarEigdxS3BlSMI2PJLcQ==", + "cpu": [ + "x64" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "sunos" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/win32-arm64": { + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/win32-arm64/-/win32-arm64-0.28.1.tgz", + "integrity": "sha512-lCv9eK/H6ZJWbE7bh2nw54CZ9M2nupBxJcTsdk/QQnWkdSjKGuxmmH8/GWrlT1eMmZfn4dGcCjRte397WqfQXA==", + "cpu": [ + "arm64" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "win32" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/win32-ia32": { + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/win32-ia32/-/win32-ia32-0.28.1.tgz", + "integrity": "sha512-zvb/mB2bSCoJOpoCBgYKKpX6YM6mJBlBUVUtVj41DlZJVEB6/0CKlRYxP5wWl1C1ILiCoAU5wZZ4q1P3qeS6Eg==", + "cpu": [ + "ia32" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "win32" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@esbuild/win32-x64": { + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/win32-x64/-/win32-x64-0.28.1.tgz", + "integrity": "sha512-bm4Mowrv+GXMlpWX++EcXw/iLyd1o3+bJkC2DkWXYVvgZCqD/bSj9ctZeAMC3cIxgjRVR2Dufaiu4YPxr5gW1A==", + "cpu": [ + "x64" + ], + "dev": true, + "license": "MIT", + "optional": true, + "os": [ + "win32" + ], + "engines": { + "node": ">=18" + } + }, + "node_modules/@types/debug": { + "version": "4.1.13", + "resolved": "https://registry.npmjs.org/@types/debug/-/debug-4.1.13.tgz", + "integrity": "sha512-KSVgmQmzMwPlmtljOomayoR89W4FynCAi3E8PPs7vmDVPe84hT+vGPKkJfThkmXs0x0jAaa9U8uW8bbfyS2fWw==", + "license": "MIT", + "dependencies": { + "@types/ms": "*" + } + }, + "node_modules/@types/ms": { + "version": "2.1.0", + "resolved": "https://registry.npmjs.org/@types/ms/-/ms-2.1.0.tgz", + "integrity": "sha512-GsCCIZDE/p3i96vtEqx+7dBUGXrc7zeSK3wwPHIaRThS+9OhWIXRqzs4d6k1SVU8g91DrNRWxWUGhp5KXQb2VA==", + "license": "MIT" + }, + "node_modules/@types/node": { + "version": "22.19.21", + "resolved": "https://registry.npmjs.org/@types/node/-/node-22.19.21.tgz", + "integrity": "sha512-VMeFBSCKQKmm2swI2kW51SFusDqekC6q9trBCvJ/JliDchFSuoYYKN7yVNjPthP1HKZcx3U1gI/wTcEBjEFKTA==", + "dev": true, + "license": "MIT", + "dependencies": { + "undici-types": "~6.21.0" + } + }, + "node_modules/arr-union": { + "version": "3.1.0", + "resolved": "https://registry.npmjs.org/arr-union/-/arr-union-3.1.0.tgz", + "integrity": "sha512-sKpyeERZ02v1FeCZT8lrfJq5u6goHCtpTAzPwJYe7c8SPFOboNjNg1vz2L4VTn9T4PQxEx13TbXLmYUcS6Ug7Q==", + "license": "MIT", + "engines": { + "node": ">=0.10.0" + } + }, + "node_modules/balanced-match": { + "version": "1.0.2", + "resolved": "https://registry.npmjs.org/balanced-match/-/balanced-match-1.0.2.tgz", + "integrity": "sha512-3oSeUO0TMV67hN1AmbXsK4yaqU7tjiHlbxRDZOpH0KW9+CeX4bRAaX0Anxt0tx2MrpRpWwQaPwIlISEJhYU5Pw==", + "license": "MIT" + }, + "node_modules/brace-expansion": { + "version": "1.1.15", + "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.15.tgz", + "integrity": "sha512-EwOCDEex4quD37XhqM3omwtMoJjr//isUZz1JopUNWms+4Z2ViyM/k1YIRePpoVNnQhENnxtFjLaxNHrT7xIUg==", + "license": "MIT", + "dependencies": { + "balanced-match": "^1.0.0", + "concat-map": "0.0.1" + } + }, + "node_modules/clone-deep": { + "version": "0.2.4", + "resolved": "https://registry.npmjs.org/clone-deep/-/clone-deep-0.2.4.tgz", + "integrity": "sha512-we+NuQo2DHhSl+DP6jlUiAhyAjBQrYnpOk15rN6c6JSPScjiCLh8IbSU+VTcph6YS3o7mASE8a0+gbZ7ChLpgg==", + "license": "MIT", + "dependencies": { + "for-own": "^0.1.3", + "is-plain-object": "^2.0.1", + "kind-of": "^3.0.2", + "lazy-cache": "^1.0.3", + "shallow-clone": "^0.1.2" + }, + "engines": { + "node": ">=0.10.0" + } + }, + "node_modules/concat-map": { + "version": "0.0.1", + "resolved": "https://registry.npmjs.org/concat-map/-/concat-map-0.0.1.tgz", + "integrity": "sha512-/Srv4dswyQNBfohGpz9o6Yb3Gz3SrUDqBH5rTuhGR7ahtlbYKnVxw2bCFMRljaA7EXHaXZ8wsHdodFvbkhKmqg==", + "license": "MIT" + }, + "node_modules/debug": { + "version": "4.4.3", + "resolved": "https://registry.npmjs.org/debug/-/debug-4.4.3.tgz", + "integrity": "sha512-RGwwWnwQvkVfavKVt22FGLw+xYSdzARwm0ru6DhTVA3umU5hZc28V3kO4stgYryrTlLpuvgI9GiijltAjNbcqA==", + "license": "MIT", + "dependencies": { + "ms": "^2.1.3" + }, + "engines": { + "node": ">=6.0" + }, + "peerDependenciesMeta": { + "supports-color": { + "optional": true + } + } + }, + "node_modules/deepmerge": { + "version": "4.3.1", + "resolved": "https://registry.npmjs.org/deepmerge/-/deepmerge-4.3.1.tgz", + "integrity": "sha512-3sUqbMEc77XqpdNO7FRyRog+eW3ph+GYCbj+rK+uYyRMuwsVy0rMiVtPn+QJlKFvWP/1PYpapqYn0Me2knFn+A==", + "license": "MIT", + "engines": { + "node": ">=0.10.0" + } + }, + "node_modules/esbuild": { + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/esbuild/-/esbuild-0.28.1.tgz", + "integrity": "sha512-HrJrvZv5ayxBzPfwphOoNzkzOIIlifzk0KJrGK2c8R4+LKpMtpYLQeUdjnwjWv/LZlkH2laZk+4w78pi99D4Vw==", + "dev": true, + "hasInstallScript": true, + "license": "MIT", + "bin": { + "esbuild": "bin/esbuild" + }, + "engines": { + "node": ">=18" + }, + "optionalDependencies": { + "@esbuild/aix-ppc64": "0.28.1", + "@esbuild/android-arm": "0.28.1", + "@esbuild/android-arm64": "0.28.1", + "@esbuild/android-x64": "0.28.1", + "@esbuild/darwin-arm64": "0.28.1", + "@esbuild/darwin-x64": "0.28.1", + "@esbuild/freebsd-arm64": "0.28.1", + "@esbuild/freebsd-x64": "0.28.1", + "@esbuild/linux-arm": "0.28.1", + "@esbuild/linux-arm64": "0.28.1", + "@esbuild/linux-ia32": "0.28.1", + "@esbuild/linux-loong64": "0.28.1", + "@esbuild/linux-mips64el": "0.28.1", + "@esbuild/linux-ppc64": "0.28.1", + "@esbuild/linux-riscv64": "0.28.1", + "@esbuild/linux-s390x": "0.28.1", + "@esbuild/linux-x64": "0.28.1", + "@esbuild/netbsd-arm64": "0.28.1", + "@esbuild/netbsd-x64": "0.28.1", + "@esbuild/openbsd-arm64": "0.28.1", + "@esbuild/openbsd-x64": "0.28.1", + "@esbuild/openharmony-arm64": "0.28.1", + "@esbuild/sunos-x64": "0.28.1", + "@esbuild/win32-arm64": "0.28.1", + "@esbuild/win32-ia32": "0.28.1", + "@esbuild/win32-x64": "0.28.1" + } + }, + "node_modules/for-in": { + "version": "1.0.2", + "resolved": "https://registry.npmjs.org/for-in/-/for-in-1.0.2.tgz", + "integrity": "sha512-7EwmXrOjyL+ChxMhmG5lnW9MPt1aIeZEwKhQzoBUdTV0N3zuwWDZYVJatDvZ2OyzPUvdIAZDsCetk3coyMfcnQ==", + "license": "MIT", + "engines": { + "node": ">=0.10.0" + } + }, + "node_modules/for-own": { + "version": "0.1.5", + "resolved": "https://registry.npmjs.org/for-own/-/for-own-0.1.5.tgz", + "integrity": "sha512-SKmowqGTJoPzLO1T0BBJpkfp3EMacCMOuH40hOUbrbzElVktk4DioXVM99QkLCyKoiuOmyjgcWMpVz2xjE7LZw==", + "license": "MIT", + "dependencies": { + "for-in": "^1.0.1" + }, + "engines": { + "node": ">=0.10.0" + } + }, + "node_modules/fs-extra": { + "version": "10.1.0", + "resolved": "https://registry.npmjs.org/fs-extra/-/fs-extra-10.1.0.tgz", + "integrity": "sha512-oRXApq54ETRj4eMiFzGnHWGy+zo5raudjuxN0b8H7s/RU2oW0Wvsx9O0ACRN/kRq9E8Vu/ReskGB5o3ji+FzHQ==", + "license": "MIT", + "dependencies": { + "graceful-fs": "^4.2.0", + "jsonfile": "^6.0.1", + "universalify": "^2.0.0" + }, + "engines": { + "node": ">=12" + } + }, + "node_modules/fs.realpath": { + "version": "1.0.0", + "resolved": "https://registry.npmjs.org/fs.realpath/-/fs.realpath-1.0.0.tgz", + "integrity": "sha512-OO0pH2lK6a0hZnAdau5ItzHPI6pUlvI7jMVnxUQRtw4owF2wk8lOSabtGDCTP4Ggrg2MbGnWO9X8K1t4+fGMDw==", + "license": "ISC" + }, + "node_modules/fsevents": { + "version": "2.3.2", + "resolved": "https://registry.npmjs.org/fsevents/-/fsevents-2.3.2.tgz", + "integrity": "sha512-xiqMQR4xAeHTuB9uWm+fFRcIOgKBMiOBP+eXiyT7jsgVCq1bkVygt00oASowB7EdtpOHaaPgKt812P9ab+DDKA==", + "hasInstallScript": true, + "license": "MIT", + "optional": true, + "os": [ + "darwin" + ], + "engines": { + "node": "^8.16.0 || ^10.6.0 || >=11.0.0" + } + }, + "node_modules/glob": { + "version": "7.2.3", + "resolved": "https://registry.npmjs.org/glob/-/glob-7.2.3.tgz", + "integrity": "sha512-nFR0zLpU2YCaRxwoCJvL6UvCH2JFyFVIvwTLsIf21AuHlMskA1hhTdk+LlYJtOlYt9v6dvszD2BGRqBL+iQK9Q==", + "deprecated": "Old versions of glob are not supported, and contain widely publicized security vulnerabilities, which have been fixed in the current version. Please update. Support for old versions may be purchased (at exorbitant rates) by contacting i@izs.me", + "license": "ISC", + "dependencies": { + "fs.realpath": "^1.0.0", + "inflight": "^1.0.4", + "inherits": "2", + "minimatch": "^3.1.1", + "once": "^1.3.0", + "path-is-absolute": "^1.0.0" + }, + "engines": { + "node": "*" + }, + "funding": { + "url": "https://github.com/sponsors/isaacs" + } + }, + "node_modules/graceful-fs": { + "version": "4.2.11", + "resolved": "https://registry.npmjs.org/graceful-fs/-/graceful-fs-4.2.11.tgz", + "integrity": "sha512-RbJ5/jmFcNNCcDV5o9eTnBLJ/HszWV0P73bc+Ff4nS/rJj+YaS6IGyiOL0VoBYX+l1Wrl3k63h/KrH+nhJ0XvQ==", + "license": "ISC" + }, + "node_modules/inflight": { + "version": "1.0.6", + "resolved": "https://registry.npmjs.org/inflight/-/inflight-1.0.6.tgz", + "integrity": "sha512-k92I/b08q4wvFscXCLvqfsHCrjrF7yiXsQuIVvVE7N82W3+aqpzuUdBbfhWcy/FZR3/4IgflMgKLOsvPDrGCJA==", + "deprecated": "This module is not supported, and leaks memory. Do not use it. Check out lru-cache if you want a good and tested way to coalesce async requests by a key value, which is much more comprehensive and powerful.", + "license": "ISC", + "dependencies": { + "once": "^1.3.0", + "wrappy": "1" + } + }, + "node_modules/inherits": { + "version": "2.0.4", + "resolved": "https://registry.npmjs.org/inherits/-/inherits-2.0.4.tgz", + "integrity": "sha512-k/vGaX4/Yla3WzyMCvTQOXYeIHvqOKtnqBduzTHpzpQZzAskKMhZ2K+EnBiSM9zGSoIFeMpXKxa4dYeZIQqewQ==", + "license": "ISC" + }, + "node_modules/is-buffer": { + "version": "1.1.6", + "resolved": "https://registry.npmjs.org/is-buffer/-/is-buffer-1.1.6.tgz", + "integrity": "sha512-NcdALwpXkTm5Zvvbk7owOUSvVvBKDgKP5/ewfXEznmQFfs4ZRmanOeKBTjRVjka3QFoN6XJ+9F3USqfHqTaU5w==", + "license": "MIT" + }, + "node_modules/is-extendable": { + "version": "0.1.1", + "resolved": "https://registry.npmjs.org/is-extendable/-/is-extendable-0.1.1.tgz", + "integrity": "sha512-5BMULNob1vgFX6EjQw5izWDxrecWK9AM72rugNr0TFldMOi0fj6Jk+zeKIt0xGj4cEfQIJth4w3OKWOJ4f+AFw==", + "license": "MIT", + "engines": { + "node": ">=0.10.0" + } + }, + "node_modules/is-plain-object": { + "version": "2.0.4", + "resolved": "https://registry.npmjs.org/is-plain-object/-/is-plain-object-2.0.4.tgz", + "integrity": "sha512-h5PpgXkWitc38BBMYawTYMWJHFZJVnBquFE57xFpjB8pJFiF6gZ+bU+WyI/yqXiFR5mdLsgYNaPe8uao6Uv9Og==", + "license": "MIT", + "dependencies": { + "isobject": "^3.0.1" + }, + "engines": { + "node": ">=0.10.0" + } + }, + "node_modules/isobject": { + "version": "3.0.1", + "resolved": "https://registry.npmjs.org/isobject/-/isobject-3.0.1.tgz", + "integrity": "sha512-WhB9zCku7EGTj/HQQRz5aUQEUeoQZH2bWcltRErOpymJ4boYE6wL9Tbr23krRPSZ+C5zqNSrSw+Cc7sZZ4b7vg==", + "license": "MIT", + "engines": { + "node": ">=0.10.0" + } + }, + "node_modules/jsonfile": { + "version": "6.2.1", + "resolved": "https://registry.npmjs.org/jsonfile/-/jsonfile-6.2.1.tgz", + "integrity": "sha512-zwOTdL3rFQ/lRdBnntKVOX6k5cKJwEc1HdilT71BWEu7J41gXIB2MRp+vxduPSwZJPWBxEzv4yH1wYLJGUHX4Q==", + "license": "MIT", + "dependencies": { + "universalify": "^2.0.0" + }, + "optionalDependencies": { + "graceful-fs": "^4.1.6" + } + }, + "node_modules/kind-of": { + "version": "3.2.2", + "resolved": "https://registry.npmjs.org/kind-of/-/kind-of-3.2.2.tgz", + "integrity": "sha512-NOW9QQXMoZGg/oqnVNoNTTIFEIid1627WCffUBJEdMxYApq7mNE7CpzucIPc+ZQg25Phej7IJSmX3hO+oblOtQ==", + "license": "MIT", + "dependencies": { + "is-buffer": "^1.1.5" + }, + "engines": { + "node": ">=0.10.0" + } + }, + "node_modules/lazy-cache": { + "version": "1.0.4", + "resolved": "https://registry.npmjs.org/lazy-cache/-/lazy-cache-1.0.4.tgz", + "integrity": "sha512-RE2g0b5VGZsOCFOCgP7omTRYFqydmZkBwl5oNnQ1lDYC57uyO9KqNnNVxT7COSHTxrRCWVcAVOcbjk+tvh/rgQ==", + "license": "MIT", + "engines": { + "node": ">=0.10.0" + } + }, + "node_modules/merge-deep": { + "version": "3.0.3", + "resolved": "https://registry.npmjs.org/merge-deep/-/merge-deep-3.0.3.tgz", + "integrity": "sha512-qtmzAS6t6grwEkNrunqTBdn0qKwFgNWvlxUbAV8es9M7Ot1EbyApytCnvE0jALPa46ZpKDUo527kKiaWplmlFA==", + "license": "MIT", + "dependencies": { + "arr-union": "^3.1.0", + "clone-deep": "^0.2.4", + "kind-of": "^3.0.2" + }, + "engines": { + "node": ">=0.10.0" + } + }, + "node_modules/minimatch": { + "version": "3.1.5", + "resolved": "https://registry.npmjs.org/minimatch/-/minimatch-3.1.5.tgz", + "integrity": "sha512-VgjWUsnnT6n+NUk6eZq77zeFdpW2LWDzP6zFGrCbHXiYNul5Dzqk2HHQ5uFH2DNW5Xbp8+jVzaeNt94ssEEl4w==", + "license": "ISC", + "dependencies": { + "brace-expansion": "^1.1.7" + }, + "engines": { + "node": "*" + } + }, + "node_modules/mixin-object": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/mixin-object/-/mixin-object-2.0.1.tgz", + "integrity": "sha512-ALGF1Jt9ouehcaXaHhn6t1yGWRqGaHkPFndtFVHfZXOvkIZ/yoGaSi0AHVTafb3ZBGg4dr/bDwnaEKqCXzchMA==", + "license": "MIT", + "dependencies": { + "for-in": "^0.1.3", + "is-extendable": "^0.1.1" + }, + "engines": { + "node": ">=0.10.0" + } + }, + "node_modules/mixin-object/node_modules/for-in": { + "version": "0.1.8", + "resolved": "https://registry.npmjs.org/for-in/-/for-in-0.1.8.tgz", + "integrity": "sha512-F0to7vbBSHP8E3l6dCjxNOLuSFAACIxFy3UehTUlG7svlXi37HHsDkyVcHo0Pq8QwrE+pXvWSVX3ZT1T9wAZ9g==", + "license": "MIT", + "engines": { + "node": ">=0.10.0" + } + }, + "node_modules/ms": { + "version": "2.1.3", + "resolved": "https://registry.npmjs.org/ms/-/ms-2.1.3.tgz", + "integrity": "sha512-6FlzubTLZG3J2a/NVCAleEhjzq5oxgHyaCU9yYXvcLsvoVaHJq/s5xXI6/XXP6tz7R9xAOtHnSO/tXtF3WRTlA==", + "license": "MIT" + }, + "node_modules/once": { + "version": "1.4.0", + "resolved": "https://registry.npmjs.org/once/-/once-1.4.0.tgz", + "integrity": "sha512-lNaJgI+2Q5URQBkccEKHTQOPaXdUxnZZElQTZY0MFUAuaEqe1E+Nyvgdz/aIyNi6Z9MzO5dv1H8n58/GELp3+w==", + "license": "ISC", + "dependencies": { + "wrappy": "1" + } + }, + "node_modules/path-is-absolute": { + "version": "1.0.1", + "resolved": "https://registry.npmjs.org/path-is-absolute/-/path-is-absolute-1.0.1.tgz", + "integrity": "sha512-AVbw3UJ2e9bq64vSaS9Am0fje1Pa8pbGqTTsmXfaIiMpnr5DlDhfJOuLj9Sf95ZPVDAUerDfEk88MPmPe7UCQg==", + "license": "MIT", + "engines": { + "node": ">=0.10.0" + } + }, + "node_modules/playwright": { + "version": "1.61.0", + "resolved": "https://registry.npmjs.org/playwright/-/playwright-1.61.0.tgz", + "integrity": "sha512-Z+7BeeqQPRRzklHsVFP4KTGIyMxKUmfeRA4WisM6G3/XW6nwGeX6fX9qYaDa+CiUqpOkb2f6X3nar05R3kSuJQ==", + "license": "Apache-2.0", + "peer": true, + "dependencies": { + "playwright-core": "1.61.0" + }, + "bin": { + "playwright": "cli.js" + }, + "engines": { + "node": ">=18" + }, + "optionalDependencies": { + "fsevents": "2.3.2" + } + }, + "node_modules/playwright-core": { + "version": "1.61.0", + "resolved": "https://registry.npmjs.org/playwright-core/-/playwright-core-1.61.0.tgz", + "integrity": "sha512-caX7TrY3Ml6egyDX0WUcTHDxodl/b51y5wJOdCEA36QviK/s2g081hvmGs8eaE3DWb6NYZQ6BjO/QkNRPenoPA==", + "license": "Apache-2.0", + "bin": { + "playwright-core": "cli.js" + }, + "engines": { + "node": ">=18" + } + }, + "node_modules/playwright-extra": { + "version": "4.3.6", + "resolved": "https://registry.npmjs.org/playwright-extra/-/playwright-extra-4.3.6.tgz", + "integrity": "sha512-q2rVtcE8V8K3vPVF1zny4pvwZveHLH8KBuVU2MoE3Jw4OKVoBWsHI9CH9zPydovHHOCDxjGN2Vg+2m644q3ijA==", + "license": "MIT", + "peer": true, + "dependencies": { + "debug": "^4.3.4" + }, + "engines": { + "node": ">=12" + }, + "peerDependencies": { + "playwright": "*", + "playwright-core": "*" + }, + "peerDependenciesMeta": { + "playwright": { + "optional": true + }, + "playwright-core": { + "optional": true + } + } + }, + "node_modules/puppeteer-extra-plugin": { + "version": "3.2.3", + "resolved": "https://registry.npmjs.org/puppeteer-extra-plugin/-/puppeteer-extra-plugin-3.2.3.tgz", + "integrity": "sha512-6RNy0e6pH8vaS3akPIKGg28xcryKscczt4wIl0ePciZENGE2yoaQJNd17UiEbdmh5/6WW6dPcfRWT9lxBwCi2Q==", + "license": "MIT", + "dependencies": { + "@types/debug": "^4.1.0", + "debug": "^4.1.1", + "merge-deep": "^3.0.1" + }, + "engines": { + "node": ">=9.11.2" + }, + "peerDependencies": { + "playwright-extra": "*", + "puppeteer-extra": "*" + }, + "peerDependenciesMeta": { + "playwright-extra": { + "optional": true + }, + "puppeteer-extra": { + "optional": true + } + } + }, + "node_modules/puppeteer-extra-plugin-stealth": { + "version": "2.11.2", + "resolved": "https://registry.npmjs.org/puppeteer-extra-plugin-stealth/-/puppeteer-extra-plugin-stealth-2.11.2.tgz", + "integrity": "sha512-bUemM5XmTj9i2ZerBzsk2AN5is0wHMNE6K0hXBzBXOzP5m5G3Wl0RHhiqKeHToe/uIH8AoZiGhc1tCkLZQPKTQ==", + "license": "MIT", + "dependencies": { + "debug": "^4.1.1", + "puppeteer-extra-plugin": "^3.2.3", + "puppeteer-extra-plugin-user-preferences": "^2.4.1" + }, + "engines": { + "node": ">=8" + }, + "peerDependencies": { + "playwright-extra": "*", + "puppeteer-extra": "*" + }, + "peerDependenciesMeta": { + "playwright-extra": { + "optional": true + }, + "puppeteer-extra": { + "optional": true + } + } + }, + "node_modules/puppeteer-extra-plugin-user-data-dir": { + "version": "2.4.1", + "resolved": "https://registry.npmjs.org/puppeteer-extra-plugin-user-data-dir/-/puppeteer-extra-plugin-user-data-dir-2.4.1.tgz", + "integrity": "sha512-kH1GnCcqEDoBXO7epAse4TBPJh9tEpVEK/vkedKfjOVOhZAvLkHGc9swMs5ChrJbRnf8Hdpug6TJlEuimXNQ+g==", + "license": "MIT", + "dependencies": { + "debug": "^4.1.1", + "fs-extra": "^10.0.0", + "puppeteer-extra-plugin": "^3.2.3", + "rimraf": "^3.0.2" + }, + "engines": { + "node": ">=8" + }, + "peerDependencies": { + "playwright-extra": "*", + "puppeteer-extra": "*" + }, + "peerDependenciesMeta": { + "playwright-extra": { + "optional": true + }, + "puppeteer-extra": { + "optional": true + } + } + }, + "node_modules/puppeteer-extra-plugin-user-preferences": { + "version": "2.4.1", + "resolved": "https://registry.npmjs.org/puppeteer-extra-plugin-user-preferences/-/puppeteer-extra-plugin-user-preferences-2.4.1.tgz", + "integrity": "sha512-i1oAZxRbc1bk8MZufKCruCEC3CCafO9RKMkkodZltI4OqibLFXF3tj6HZ4LZ9C5vCXZjYcDWazgtY69mnmrQ9A==", + "license": "MIT", + "dependencies": { + "debug": "^4.1.1", + "deepmerge": "^4.2.2", + "puppeteer-extra-plugin": "^3.2.3", + "puppeteer-extra-plugin-user-data-dir": "^2.4.1" + }, + "engines": { + "node": ">=8" + }, + "peerDependencies": { + "playwright-extra": "*", + "puppeteer-extra": "*" + }, + "peerDependenciesMeta": { + "playwright-extra": { + "optional": true + }, + "puppeteer-extra": { + "optional": true + } + } + }, + "node_modules/rimraf": { + "version": "3.0.2", + "resolved": "https://registry.npmjs.org/rimraf/-/rimraf-3.0.2.tgz", + "integrity": "sha512-JZkJMZkAGFFPP2YqXZXPbMlMBgsxzE8ILs4lMIX/2o0L9UBw9O/Y3o6wFw/i9YLapcUJWwqbi3kdxIPdC62TIA==", + "deprecated": "Rimraf versions prior to v4 are no longer supported", + "license": "ISC", + "dependencies": { + "glob": "^7.1.3" + }, + "bin": { + "rimraf": "bin.js" + }, + "funding": { + "url": "https://github.com/sponsors/isaacs" + } + }, + "node_modules/shallow-clone": { + "version": "0.1.2", + "resolved": "https://registry.npmjs.org/shallow-clone/-/shallow-clone-0.1.2.tgz", + "integrity": "sha512-J1zdXCky5GmNnuauESROVu31MQSnLoYvlyEn6j2Ztk6Q5EHFIhxkMhYcv6vuDzl2XEzoRr856QwzMgWM/TmZgw==", + "license": "MIT", + "dependencies": { + "is-extendable": "^0.1.1", + "kind-of": "^2.0.1", + "lazy-cache": "^0.2.3", + "mixin-object": "^2.0.1" + }, + "engines": { + "node": ">=0.10.0" + } + }, + "node_modules/shallow-clone/node_modules/kind-of": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/kind-of/-/kind-of-2.0.1.tgz", + "integrity": "sha512-0u8i1NZ/mg0b+W3MGGw5I7+6Eib2nx72S/QvXa0hYjEkjTknYmEYQJwGu3mLC0BrhtJjtQafTkyRUQ75Kx0LVg==", + "license": "MIT", + "dependencies": { + "is-buffer": "^1.0.2" + }, + "engines": { + "node": ">=0.10.0" + } + }, + "node_modules/shallow-clone/node_modules/lazy-cache": { + "version": "0.2.7", + "resolved": "https://registry.npmjs.org/lazy-cache/-/lazy-cache-0.2.7.tgz", + "integrity": "sha512-gkX52wvU/R8DVMMt78ATVPFMJqfW8FPz1GZ1sVHBVQHmu/WvhIWE4cE1GBzhJNFicDeYhnwp6Rl35BcAIM3YOQ==", + "license": "MIT", + "engines": { + "node": ">=0.10.0" + } + }, + "node_modules/tsx": { + "version": "4.22.4", + "resolved": "https://registry.npmjs.org/tsx/-/tsx-4.22.4.tgz", + "integrity": "sha512-X8EX+XV4QR5xCsrgxaED954zTDfY8KqlDtskKEL0cHhyS/P8b4IFOvGDQpsC9Q1XnLq915wEfwwY/zzskCtmhg==", + "dev": true, + "license": "MIT", + "dependencies": { + "esbuild": "~0.28.0" + }, + "bin": { + "tsx": "dist/cli.mjs" + }, + "engines": { + "node": ">=18.0.0" + }, + "optionalDependencies": { + "fsevents": "~2.3.3" + } + }, + "node_modules/tsx/node_modules/fsevents": { + "version": "2.3.3", + "resolved": "https://registry.npmjs.org/fsevents/-/fsevents-2.3.3.tgz", + "integrity": "sha512-5xoDfX+fL7faATnagmWPpbFtwh/R77WmMMqqHGS65C3vvB0YHrgF+B1YmZ3441tMj5n63k0212XNoJwzlhffQw==", + "dev": true, + "hasInstallScript": true, + "license": "MIT", + "optional": true, + "os": [ + "darwin" + ], + "engines": { + "node": "^8.16.0 || ^10.6.0 || >=11.0.0" + } + }, + "node_modules/typescript": { + "version": "5.9.3", + "resolved": "https://registry.npmjs.org/typescript/-/typescript-5.9.3.tgz", + "integrity": "sha512-jl1vZzPDinLr9eUt3J/t7V6FgNEw9QjvBPdysz9KfQDD41fQrC2Y4vKQdiaUpFT4bXlb1RHhLpp8wtm6M5TgSw==", + "dev": true, + "license": "Apache-2.0", + "bin": { + "tsc": "bin/tsc", + "tsserver": "bin/tsserver" + }, + "engines": { + "node": ">=14.17" + } + }, + "node_modules/undici-types": { + "version": "6.21.0", + "resolved": "https://registry.npmjs.org/undici-types/-/undici-types-6.21.0.tgz", + "integrity": "sha512-iwDZqg0QAGrg9Rav5H4n0M64c3mkR59cJ6wQp+7C4nI0gsmExaedaYLNO44eT4AtBBwjbTiGPMlt2Md0T9H9JQ==", + "dev": true, + "license": "MIT" + }, + "node_modules/universalify": { + "version": "2.0.1", + "resolved": "https://registry.npmjs.org/universalify/-/universalify-2.0.1.tgz", + "integrity": "sha512-gptHNQghINnc/vTGIk0SOFGFNXw7JVrlRUtConJRlvaw6DuX0wO5Jeko9sWrMBhh+PsYAZ7oXAiOnf/UKogyiw==", + "license": "MIT", + "engines": { + "node": ">= 10.0.0" + } + }, + "node_modules/wrappy": { + "version": "1.0.2", + "resolved": "https://registry.npmjs.org/wrappy/-/wrappy-1.0.2.tgz", + "integrity": "sha512-l4Sp/DRseor9wL6EvV2+TuQn63dMkPjZ/sp9XkghTEbV9KlPS1xUsZ3u7/IQO4wxtcFB4bgpQPRcR3QCvezPcQ==", + "license": "ISC" + } + } +} diff --git a/package.json b/package.json new file mode 100644 index 0000000..c09e171 --- /dev/null +++ b/package.json @@ -0,0 +1,23 @@ +{ + "name": "scraper", + "version": "1.0.0", + "description": "", + "main": "index.js", + "scripts": { + "scrape": "npx tsx src/index.ts" + }, + "keywords": [], + "author": "", + "license": "ISC", + "type": "module", + "dependencies": { + "playwright": "^1.50.1", + "playwright-extra": "^4.3.6", + "puppeteer-extra-plugin-stealth": "^2.11.2" + }, + "devDependencies": { + "@types/node": "^22.19.21", + "tsx": "^4.19.3", + "typescript": "^5.8.2" + } +} diff --git a/src/extract/extract-product.ts b/src/extract/extract-product.ts new file mode 100644 index 0000000..0979060 --- /dev/null +++ b/src/extract/extract-product.ts @@ -0,0 +1,20 @@ +import type { Page } from "playwright"; +import type { RawProduct, Product } from "../types.js"; +import { extractors } from "./extractors.js"; + +export const extractProduct = async (page: Page): Promise => { + const raw: Partial = {}; + + const keys = Object.keys(extractors) as Array; + + for (const key of keys) { + try { + raw[key] = await extractors[key](page); + } catch (error) { + console.error(`Error extracting field "${key}":`, error); + raw[key] = null; + } + } + + return raw as RawProduct; +}; diff --git a/src/extract/extractors.ts b/src/extract/extractors.ts new file mode 100644 index 0000000..94be92d --- /dev/null +++ b/src/extract/extractors.ts @@ -0,0 +1,309 @@ +import type { Page } from "playwright"; +import type { ExtractorMap, SpecEntry, JsonObject, JsonValue } from "../types.js"; + +async function getJsonLd(page: Page): Promise { + return page.evaluate(() => { + const scripts = Array.from(document.querySelectorAll('script[type="application/ld+json"]')); + return scripts.map(s => { + try { + const parsed = JSON.parse(s.textContent || "{}"); + return typeof parsed === 'object' && parsed !== null ? parsed : {}; + } catch { + return {}; + } + }); + }); +} + +async function findJsonLdType(page: Page, typeStr: string): Promise { + const jsonLds = await getJsonLd(page); + for (const item of jsonLds) { + const typeObj = item["@type"]; + if (typeObj === typeStr || (Array.isArray(typeObj) && typeObj.includes(typeStr))) { + return item; + } + const graphObj = item["@graph"]; + if (graphObj && Array.isArray(graphObj)) { + const found = graphObj.find((g: JsonValue) => g && typeof g === 'object' && !Array.isArray(g) && g["@type"] === typeStr); + if (found) return found as JsonObject; + } + } + return null; +} + +export const extractors: ExtractorMap = { + url: async (page) => { + return page.url(); + }, + + item_id: async (page) => { + const productData = await findJsonLdType(page, "Product"); + if (productData?.sku) return String(productData.sku); + if (productData?.productID) return String(productData.productID); + + // Try finding data attributes or hidden inputs + return page.evaluate(() => { + const skuEl = document.querySelector('[data-product-sku], [data-sku], input[name="product_id"]'); + if (skuEl) { + return skuEl.getAttribute('data-product-sku') || skuEl.getAttribute('data-sku') || (skuEl as HTMLInputElement).value; + } + return null; + }); + }, + + title: async (page) => { + const productData = await findJsonLdType(page, "Product"); + if (productData?.name) return String(productData.name); + + return page.evaluate(() => { + const imgAlt = document.querySelector('.product-detail-thumb-bto, .main-image img'); + if (imgAlt && imgAlt.getAttribute('alt')) return imgAlt.getAttribute('alt')?.trim(); + + const titleStr = document.title; + if (titleStr) { + const dashPart = titleStr.split(' - ')[0] || titleStr; + const pipePart = dashPart.split(' | ')[0] || dashPart; + return pipePart.trim(); + } + + const h1s = Array.from(document.querySelectorAll('h1')); + const validH1 = h1s.find(el => { + const text = el.textContent?.toLowerCase() || ''; + return !text.includes('cookie') && !text.includes('choice') && !text.includes('consent'); + }); + if (validH1) return validH1.textContent?.trim(); + + return null; + }); + }, + + brand: async (page) => { + const productData = await findJsonLdType(page, "Product"); + if (productData?.brand && typeof productData.brand === 'object' && !Array.isArray(productData.brand)) { + const brandName = (productData.brand as JsonObject).name; + if (brandName) return String(brandName); + } + + return page.evaluate(() => { + const brandEl = document.querySelector('[itemprop="brand"]'); + if (brandEl) return brandEl.textContent?.trim() || brandEl.getAttribute('content'); + + const siteName = document.querySelector('meta[property="og:site_name"]'); + if (siteName) { + const content = siteName.getAttribute('content'); + if (content) return (content.split('-')[0] || content).trim(); + } + return null; + }); + }, + + product_category: async (page) => { + return page.evaluate(() => { + const breadcrumbs = Array.from(document.querySelectorAll('.breadcrumb li, .breadcrumbs li, [aria-label="breadcrumb"] li, [itemtype="http://schema.org/BreadcrumbList"] li, .path-item')); + if (breadcrumbs.length > 0) { + const texts = breadcrumbs.map(b => b.textContent?.replace(/\s+/g, ' ').trim()).filter(Boolean); + const filtered = texts.filter(t => t && t.toLowerCase() !== 'home'); + if (filtered.length > 0) return filtered.join(' > '); + } + return null; + }); + }, + + category_tree: async (page) => { + return page.evaluate(() => { + const items = Array.from(document.querySelectorAll('.breadcrumb a, .breadcrumbs a, [aria-label="breadcrumb"] a, [itemprop="itemListElement"] a')); + if (items.length > 0) { + const tree = items.map(el => { + const name = el.textContent?.trim() || ''; + const url = (el as HTMLAnchorElement).href || null; + return { name, url }; + }).filter(item => item.name && item.name.toLowerCase() !== 'home'); + return tree; + } + return []; + }); + }, + + description: async (page) => { + const productData = await findJsonLdType(page, "Product"); + if (productData?.description) return String(productData.description); + + return page.evaluate(() => { + const descEl = document.querySelector('.product-description, #description, [itemprop="description"]'); + if (descEl) return descEl.textContent?.trim(); + const metaDesc = document.querySelector('meta[name="description"], meta[property="og:description"]'); + if (metaDesc) return metaDesc.getAttribute('content'); + return null; + }); + }, + + price: async (page) => { + const productData = await findJsonLdType(page, "Product"); + if (productData?.offers) { + if (Array.isArray(productData.offers)) { + const offer = productData.offers[0] as JsonObject; + if (offer?.price) return String(offer.price); + } else if (typeof productData.offers === 'object') { + const offer = productData.offers as JsonObject; + if (offer.price) return String(offer.price); + } + } + + return page.evaluate(() => { + const priceEl = document.querySelector('.prices-new, .price-new, [itemprop="price"], .product-price, .current-price, .regular-price'); + if (priceEl) return priceEl.textContent?.trim(); + return null; + }); + }, + + sale_price: async (page) => { + return page.evaluate(() => { + const hasOldPrice = document.querySelector('.prices-old, .price-old, .price-was'); + if (hasOldPrice) { + const saleEl = document.querySelector('.prices-new, .price-new'); + if (saleEl) return saleEl.textContent?.trim(); + } + return null; + }); + }, + + availability: async (page) => { + const productData = await findJsonLdType(page, "Product"); + let offerUrl: unknown = null; + + if (productData?.offers) { + if (Array.isArray(productData.offers)) { + const offer = productData.offers[0] as JsonObject; + offerUrl = offer?.availability; + } else if (typeof productData.offers === 'object') { + const offer = productData.offers as JsonObject; + offerUrl = offer.availability; + } + } + + if (offerUrl) { + return String(offerUrl).split('/').pop() || String(offerUrl); + } + + return page.evaluate(() => { + const btn = document.querySelector('#button-cart, .add-to-cart, [data-action="add-to-cart"], button.btn-cart'); + if (btn) return btn.textContent?.trim() || "Add to Cart"; + + const stockEl = document.querySelector('.stock, .availability, [itemprop="availability"]'); + if (stockEl) return stockEl.textContent?.trim() || stockEl.getAttribute('href')?.split('/').pop(); + return null; + }); + }, + + image_url: async (page) => { + const productData = await findJsonLdType(page, "Product"); + if (productData?.image) { + if (typeof productData.image === 'string') return productData.image; + if (Array.isArray(productData.image)) return String(productData.image[0]); + if (typeof productData.image === 'object') { + const url = (productData.image as JsonObject).url; + if (url) return String(url); + } + } + + return page.evaluate(() => { + const img = document.querySelector('.product-detail-thumb-bto, .product-image img, .main-image img, [property="og:image"], img[itemprop="image"]'); + if (img) { + if (img.tagName.toLowerCase() === 'meta') return img.getAttribute('content'); + return img.getAttribute('popup_img') || (img as HTMLImageElement).src || img.getAttribute('data-src') || img.getAttribute('src'); + } + return null; + }); + }, + + additional_image_urls: async (page) => { + return page.evaluate(() => { + const imgs = Array.from(document.querySelectorAll('.product-detail-thumb-bto, .gallery img, .thumbnails img, .product-thumbnails img')); + return imgs.map(img => { + return img.getAttribute('popup_img') || (img as HTMLImageElement).src || img.getAttribute('data-src') || img.getAttribute('src') || ''; + }).filter(Boolean); + }); + }, + + specs: async (page) => { + return page.evaluate(() => { + const specs: SpecEntry[] = []; + const rows = Array.from(document.querySelectorAll('.spec-table tr, .specifications tr, table tr, .tech-specs li')); + + for (const row of rows) { + const th = row.querySelector('th'); + const td = row.querySelector('td'); + if (th && td) { + specs.push({ + name: th.textContent?.trim() || '', + value: td.textContent?.trim() || null + }); + continue; + } + + const label = row.querySelector('.label, .spec-name, dt'); + const value = row.querySelector('.value, .spec-value, dd'); + if (label && value) { + specs.push({ + name: label.textContent?.trim() || '', + value: value.textContent?.trim() || null + }); + } + } + return specs.filter(s => s.name); + }); + }, + + star_rating: async (page) => { + const productData = await findJsonLdType(page, "Product"); + if (productData?.aggregateRating && typeof productData.aggregateRating === 'object' && !Array.isArray(productData.aggregateRating)) { + const val = (productData.aggregateRating as JsonObject).ratingValue; + if (val) return String(val); + } + + return page.evaluate(() => { + const ratingEl = document.querySelector('.rating-value, [itemprop="ratingValue"], .stars'); + if (ratingEl) return ratingEl.textContent?.trim() || ratingEl.getAttribute('content'); + return null; + }); + }, + + review_count: async (page) => { + const productData = await findJsonLdType(page, "Product"); + if (productData?.aggregateRating && typeof productData.aggregateRating === 'object' && !Array.isArray(productData.aggregateRating)) { + const val = (productData.aggregateRating as JsonObject).reviewCount; + if (val) return String(val); + } + + return page.evaluate(() => { + const countEl = document.querySelector('.review-count, [itemprop="reviewCount"]'); + if (countEl) return countEl.textContent?.trim() || countEl.getAttribute('content'); + return null; + }); + }, + + gtin: async (page) => { + const productData = await findJsonLdType(page, "Product"); + if (productData?.gtin13) return String(productData.gtin13); + if (productData?.gtin) return String(productData.gtin); + + return page.evaluate(() => { + const el = document.querySelector('[itemprop="gtin13"], [itemprop="gtin"]'); + return el ? (el.textContent?.trim() || el.getAttribute('content')) : null; + }); + }, + + mpn: async (page) => { + const productData = await findJsonLdType(page, "Product"); + if (productData?.mpn) return String(productData.mpn); + + return page.evaluate(() => { + const el = document.querySelector('[itemprop="mpn"]'); + return el ? (el.textContent?.trim() || el.getAttribute('content')) : null; + }); + }, + + scraped_at: async () => { + return new Date().toISOString(); + } +}; diff --git a/src/format/format-product.ts b/src/format/format-product.ts new file mode 100644 index 0000000..ba1dc35 --- /dev/null +++ b/src/format/format-product.ts @@ -0,0 +1,14 @@ +import type { RawProduct, Product } from "../types.js"; +import { formatters } from "./formatters.js"; + +export const formatProduct = (raw: RawProduct): Product => { + const product: Partial = {}; + + const keys = Object.keys(formatters) as Array; + + for (const key of keys) { + (product as Record)[key] = formatters[key](raw[key]); + } + + return product as Product; +}; diff --git a/src/format/formatters.ts b/src/format/formatters.ts new file mode 100644 index 0000000..a61aad1 --- /dev/null +++ b/src/format/formatters.ts @@ -0,0 +1,83 @@ +import type { FormatterMap, Availability, CategoryEntry, SpecEntry } from "../types.js"; + +const availabilityMap: Record = { + "add to cart": "in_stock", + "in stock": "in_stock", + "instock": "in_stock", + "out of stock": "out_of_stock", + "outofstock": "out_of_stock", + "sold out": "out_of_stock", + "pre-order": "pre_order", + "pre order": "pre_order", + "preorder": "pre_order" +}; + +const parseNumber = (val: unknown): number | null => { + if (typeof val === "number") return val; + if (typeof val !== "string") return null; + const cleaned = val.replace(/[^\d.-]/g, ""); + const parsed = parseFloat(cleaned); + return isNaN(parsed) ? null : parsed; +}; + +const parseString = (val: unknown): string | null => { + if (typeof val === "string") { + const trimmed = val.trim(); + return trimmed.length > 0 ? trimmed : null; + } + return null; +}; + +export const formatters: FormatterMap = { + url: (val) => parseString(val) || "", + + item_id: parseString, + + title: parseString, + + brand: parseString, + + product_category: parseString, + + category_tree: (val) => { + if (!Array.isArray(val)) return []; + return val as CategoryEntry[]; + }, + + description: parseString, + + price: parseNumber, + + sale_price: parseNumber, + + availability: (val) => { + const str = parseString(val); + if (!str) return null; + const lower = str.toLowerCase(); + return availabilityMap[lower] ?? null; + }, + + image_url: parseString, + + additional_image_urls: (val) => { + if (!Array.isArray(val)) return []; + // Deduplicate array + const urls = val.map(parseString).filter(Boolean) as string[]; + return Array.from(new Set(urls)); + }, + + specs: (val) => { + if (!Array.isArray(val)) return []; + return val as SpecEntry[]; + }, + + star_rating: parseNumber, + + review_count: parseNumber, + + gtin: parseString, + + mpn: parseString, + + scraped_at: (val) => parseString(val) || new Date().toISOString() +}; diff --git a/src/index.ts b/src/index.ts new file mode 100644 index 0000000..b2bade6 --- /dev/null +++ b/src/index.ts @@ -0,0 +1,45 @@ +import { writeFileSync, mkdirSync } from "node:fs"; +import { dirname } from "node:path"; +import { loadPage } from "./request/page-loader.js"; +import { extractProduct } from "./extract/extract-product.js"; +import { formatProduct } from "./format/format-product.js"; + +const DEFAULT_URL = "https://us-store.msi.com/Motherboards/Intel-Platform-Motherboard/INTEL-Z890/MAG-Z890-TOMAHAWK-WIFI"; +const TARGET_URL = process.argv[2] || DEFAULT_URL; +const OUTPUT_FILE = "output/product.json"; + +async function main() { + console.log(`Starting scraper for URL: ${TARGET_URL}`); + + let browser; + try { + const loaderResult = await loadPage(TARGET_URL); + browser = loaderResult.browser; + const page = loaderResult.page; + + console.log("Page loaded. Extracting data..."); + const rawData = await extractProduct(page); + + console.log("Data extracted. Formatting..."); + const product = formatProduct(rawData); + + console.log("Formatting complete. Saving output..."); + mkdirSync(dirname(OUTPUT_FILE), { recursive: true }); + writeFileSync(OUTPUT_FILE, JSON.stringify(product, null, 2), "utf8"); + + const html = await page.content(); + writeFileSync("output/page.html", html, "utf8"); + + console.log(`Success! Data saved to ${OUTPUT_FILE}`); + } catch (error) { + console.error("Scraping failed:", error); + process.exit(1); + } finally { + if (browser) { + await browser.close(); + console.log("Browser closed."); + } + } +} + +main(); diff --git a/src/request/page-loader.ts b/src/request/page-loader.ts new file mode 100644 index 0000000..e1063ff --- /dev/null +++ b/src/request/page-loader.ts @@ -0,0 +1,26 @@ +import { chromium } from "playwright-extra"; +import stealth from "puppeteer-extra-plugin-stealth"; +import type { Browser, Page } from "playwright"; + +chromium.use(stealth()); + +export const loadPage = async (url: string): Promise<{ page: Page; browser: Browser }> => { + const browser = await chromium.launch({ headless: true }); + const context = await browser.newContext({ + userAgent: "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/121.0.0.0 Safari/537.36", + viewport: { width: 1920, height: 1080 } + }); + + const page = await context.newPage(); + + await page.goto(url, { waitUntil: "domcontentloaded" }); + await page.waitForTimeout(3000); + + try { + await page.waitForSelector("h1", { timeout: 10000 }); + } catch (error) { + console.warn("Warning: Could not find

element within timeout."); + } + + return { page, browser }; +}; diff --git a/src/types.ts b/src/types.ts new file mode 100644 index 0000000..f4e3ca6 --- /dev/null +++ b/src/types.ts @@ -0,0 +1,51 @@ +import type { Page } from "playwright"; + +export type JsonPrimitive = string | number | boolean | null; +export type JsonValue = JsonPrimitive | JsonObject | JsonArray; +export interface JsonObject { + [key: string]: JsonValue; +} +export interface JsonArray extends Array {} + +export type Availability = "in_stock" | "out_of_stock" | "pre_order"; + +export type CategoryEntry = { + name: string; + url: string | null; +}; + +export type SpecEntry = { + name: string; + value: string | null; +}; + +export type Product = { + url: string; + item_id: string | null; + title: string | null; + brand: string | null; + product_category: string | null; + category_tree: CategoryEntry[]; + description: string | null; + price: number | null; + sale_price: number | null; + availability: Availability | null; + image_url: string | null; + additional_image_urls: string[]; + specs: SpecEntry[]; + star_rating: number | null; + review_count: number | null; + gtin: string | null; + mpn: string | null; + scraped_at: string; +}; + +export type RawProduct = { + [K in keyof Product]: unknown; +}; + +export type Extractor = (page: Page) => Promise; +export type Formatter = (raw: unknown) => unknown; + +export type ExtractorMap = Record; +export type FormatterMap = Record; diff --git a/tsconfig.json b/tsconfig.json new file mode 100644 index 0000000..a4e1431 --- /dev/null +++ b/tsconfig.json @@ -0,0 +1,44 @@ +{ + // Visit https://aka.ms/tsconfig to read more about this file + "compilerOptions": { + // File Layout + // "rootDir": "./src", + // "outDir": "./dist", + + // Environment Settings + // See also https://aka.ms/tsconfig/module + "module": "nodenext", + "target": "esnext", + "types": ["node"], + // For nodejs: + // "lib": ["esnext"], + // "types": ["node"], + // and npm install -D @types/node + + // Other Outputs + "sourceMap": true, + "declaration": true, + "declarationMap": true, + + // Stricter Typechecking Options + "noUncheckedIndexedAccess": true, + "exactOptionalPropertyTypes": true, + + // Style Options + // "noImplicitReturns": true, + // "noImplicitOverride": true, + // "noUnusedLocals": true, + // "noUnusedParameters": true, + // "noFallthroughCasesInSwitch": true, + // "noPropertyAccessFromIndexSignature": true, + + // Recommended Options + "strict": true, + "jsx": "react-jsx", + "verbatimModuleSyntax": true, + "isolatedModules": true, + "noUncheckedSideEffectImports": true, + "moduleDetection": "force", + "skipLibCheck": true, + } +}