diff --git a/package-lock.json b/package-lock.json index ba3dd65..5400adf 100644 --- a/package-lock.json +++ b/package-lock.json @@ -10,9 +10,9 @@ "license": "Apache-2.0", "dependencies": { "cheerio": "^1.0.0", + "jsdom": "^24.1.3", "jsonrepair": "^3.12.0", "turndown": "^7.2.0", - "xmldom": "^0.6.0", "xpath": "^0.0.34", "zod": "^3.24.3" }, @@ -23,7 +23,6 @@ "@types/jest": "^29.5.12", "@types/node": "^22.15.3", "@types/turndown": "^5.0.5", - "@types/xmldom": "^0.1.34", "dotenv": "^16.3.1", "jest": "^29.7.0", "playwright": "^1.58.2", @@ -39,6 +38,25 @@ "@langchain/core": ">=1.1.31" } }, + "node_modules/@asamuzakjp/css-color": { + "version": "3.2.0", + "resolved": "https://registry.npmjs.org/@asamuzakjp/css-color/-/css-color-3.2.0.tgz", + "integrity": "sha512-K1A6z8tS3XsmCMM86xoWdn7Fkdn9m6RSVtocUrJYIwZnFVkng/PvkEoWtOWmP+Scc6saYWHWZYbndEEXxl24jw==", + "license": "MIT", + "dependencies": { + "@csstools/css-calc": "^2.1.3", + "@csstools/css-color-parser": "^3.0.9", + "@csstools/css-parser-algorithms": "^3.0.4", + "@csstools/css-tokenizer": "^3.0.3", + "lru-cache": "^10.4.3" + } + }, + "node_modules/@asamuzakjp/css-color/node_modules/lru-cache": { + "version": "10.4.3", + "resolved": "https://registry.npmjs.org/lru-cache/-/lru-cache-10.4.3.tgz", + "integrity": "sha512-JNAzZcXrCt42VGLuYz0zfAzDfAvJWW6AfYlDBQyDV5DClI2m5sAmK+OIO7s59XfsRsWHp02jAJrRadPRGTt6SQ==", + "license": "ISC" + }, "node_modules/@babel/code-frame": { "version": "7.29.0", "resolved": "https://registry.npmjs.org/@babel/code-frame/-/code-frame-7.29.0.tgz", @@ -566,6 +584,116 @@ "@jridgewell/sourcemap-codec": "^1.4.10" } }, + "node_modules/@csstools/color-helpers": { + "version": "5.1.0", + "resolved": "https://registry.npmjs.org/@csstools/color-helpers/-/color-helpers-5.1.0.tgz", + "integrity": "sha512-S11EXWJyy0Mz5SYvRmY8nJYTFFd1LCNV+7cXyAgQtOOuzb4EsgfqDufL+9esx72/eLhsRdGZwaldu/h+E4t4BA==", + "funding": [ + { + "type": "github", + "url": "https://github.com/sponsors/csstools" + }, + { + "type": "opencollective", + "url": "https://opencollective.com/csstools" + } + ], + "license": "MIT-0", + "engines": { + "node": ">=18" + } + }, + "node_modules/@csstools/css-calc": { + "version": "2.1.4", + "resolved": "https://registry.npmjs.org/@csstools/css-calc/-/css-calc-2.1.4.tgz", + "integrity": "sha512-3N8oaj+0juUw/1H3YwmDDJXCgTB1gKU6Hc/bB502u9zR0q2vd786XJH9QfrKIEgFlZmhZiq6epXl4rHqhzsIgQ==", + "funding": [ + { + "type": "github", + "url": "https://github.com/sponsors/csstools" + }, + { + "type": "opencollective", + "url": "https://opencollective.com/csstools" + } + ], + "license": "MIT", + "engines": { + "node": ">=18" + }, + "peerDependencies": { + "@csstools/css-parser-algorithms": "^3.0.5", + "@csstools/css-tokenizer": "^3.0.4" + } + }, + "node_modules/@csstools/css-color-parser": { + "version": "3.1.0", + "resolved": "https://registry.npmjs.org/@csstools/css-color-parser/-/css-color-parser-3.1.0.tgz", + "integrity": "sha512-nbtKwh3a6xNVIp/VRuXV64yTKnb1IjTAEEh3irzS+HkKjAOYLTGNb9pmVNntZ8iVBHcWDA2Dof0QtPgFI1BaTA==", + "funding": [ + { + "type": "github", + "url": "https://github.com/sponsors/csstools" + }, + { + "type": "opencollective", + "url": "https://opencollective.com/csstools" + } + ], + "license": "MIT", + "dependencies": { + "@csstools/color-helpers": "^5.1.0", + "@csstools/css-calc": "^2.1.4" + }, + "engines": { + "node": ">=18" + }, + "peerDependencies": { + "@csstools/css-parser-algorithms": "^3.0.5", + "@csstools/css-tokenizer": "^3.0.4" + } + }, + "node_modules/@csstools/css-parser-algorithms": { + "version": "3.0.5", + "resolved": "https://registry.npmjs.org/@csstools/css-parser-algorithms/-/css-parser-algorithms-3.0.5.tgz", + "integrity": "sha512-DaDeUkXZKjdGhgYaHNJTV9pV7Y9B3b644jCLs9Upc3VeNGg6LWARAT6O+Q+/COo+2gg/bM5rhpMAtf70WqfBdQ==", + "funding": [ + { + "type": "github", + "url": "https://github.com/sponsors/csstools" + }, + { + "type": "opencollective", + "url": "https://opencollective.com/csstools" + } + ], + "license": "MIT", + "engines": { + "node": ">=18" + }, + "peerDependencies": { + "@csstools/css-tokenizer": "^3.0.4" + } + }, + "node_modules/@csstools/css-tokenizer": { + "version": "3.0.4", + "resolved": "https://registry.npmjs.org/@csstools/css-tokenizer/-/css-tokenizer-3.0.4.tgz", + "integrity": "sha512-Vd/9EVDiu6PPJt9yAh6roZP6El1xHrdvIVGjyBsHR0RYwNHgL7FJPyIIW4fANJNG6FtyZfvlRPpFI4ZM/lubvw==", + "funding": [ + { + "type": "github", + "url": "https://github.com/sponsors/csstools" + }, + { + "type": "opencollective", + "url": "https://opencollective.com/csstools" + } + ], + "license": "MIT", + "engines": { + "node": ">=18" + } + }, "node_modules/@google/generative-ai": { "version": "0.24.1", "resolved": "https://registry.npmjs.org/@google/generative-ai/-/generative-ai-0.24.1.tgz", @@ -1319,13 +1447,6 @@ "dev": true, "license": "MIT" }, - "node_modules/@types/xmldom": { - "version": "0.1.34", - "resolved": "https://registry.npmjs.org/@types/xmldom/-/xmldom-0.1.34.tgz", - "integrity": "sha512-7eZFfxI9XHYjJJuugddV6N5YNeXgQE1lArWOcd1eCOKWb/FGs5SIjacSYuEJuwhsGS3gy4RuZ5EUIcqYscuPDA==", - "dev": true, - "license": "MIT" - }, "node_modules/@types/yargs": { "version": "17.0.35", "resolved": "https://registry.npmjs.org/@types/yargs/-/yargs-17.0.35.tgz", @@ -1369,6 +1490,15 @@ "node": ">=0.4.0" } }, + "node_modules/agent-base": { + "version": "7.1.4", + "resolved": "https://registry.npmjs.org/agent-base/-/agent-base-7.1.4.tgz", + "integrity": "sha512-MnA+YT8fwfJPgBx3m60MNqakm30XOkyIoH1y6huTQvC0PwZG7ki8NacLBcrPbNoo8vEZy7Jpuk7+jMO+CUovTQ==", + "license": "MIT", + "engines": { + "node": ">= 14" + } + }, "node_modules/ansi-escapes": { "version": "4.3.2", "resolved": "https://registry.npmjs.org/ansi-escapes/-/ansi-escapes-4.3.2.tgz", @@ -1439,6 +1569,12 @@ "sprintf-js": "~1.0.2" } }, + "node_modules/asynckit": { + "version": "0.4.0", + "resolved": "https://registry.npmjs.org/asynckit/-/asynckit-0.4.0.tgz", + "integrity": "sha512-Oei9OH4tRh0YqU3GxhX79dM/mwVgvbZJaSNaRk+bshkj0S5cfHcgYakreBjrHwatXKbz+IoIdYLxrKim2MjW0Q==", + "license": "MIT" + }, "node_modules/babel-jest": { "version": "29.7.0", "resolved": "https://registry.npmjs.org/babel-jest/-/babel-jest-29.7.0.tgz", @@ -1690,6 +1826,19 @@ "dev": true, "license": "MIT" }, + "node_modules/call-bind-apply-helpers": { + "version": "1.0.2", + "resolved": "https://registry.npmjs.org/call-bind-apply-helpers/-/call-bind-apply-helpers-1.0.2.tgz", + "integrity": "sha512-Sp1ablJ0ivDkSzjcaJdxEunN5/XvksFJ2sMBFfq6x0ryhQV/2b/KwFe21cMpmHtPOSij8K99/wSfoEuTObmuMQ==", + "license": "MIT", + "dependencies": { + "es-errors": "^1.3.0", + "function-bind": "^1.1.2" + }, + "engines": { + "node": ">= 0.4" + } + }, "node_modules/callsites": { "version": "3.1.0", "resolved": "https://registry.npmjs.org/callsites/-/callsites-3.1.0.tgz", @@ -1895,6 +2044,18 @@ "dev": true, "license": "MIT" }, + "node_modules/combined-stream": { + "version": "1.0.8", + "resolved": "https://registry.npmjs.org/combined-stream/-/combined-stream-1.0.8.tgz", + "integrity": "sha512-FQN4MRfuJeHf7cBbBMJFXhKSDq+2kAArBlmRBvcvFE5BB1HZKXtSFASDhdlz9zOYwxh8lDdnvmMOe/+5cdoEdg==", + "license": "MIT", + "dependencies": { + "delayed-stream": "~1.0.0" + }, + "engines": { + "node": ">= 0.8" + } + }, "node_modules/concat-map": { "version": "0.0.1", "resolved": "https://registry.npmjs.org/concat-map/-/concat-map-0.0.1.tgz", @@ -1991,11 +2152,42 @@ "url": "https://github.com/sponsors/fb55" } }, + "node_modules/cssstyle": { + "version": "4.6.0", + "resolved": "https://registry.npmjs.org/cssstyle/-/cssstyle-4.6.0.tgz", + "integrity": "sha512-2z+rWdzbbSZv6/rhtvzvqeZQHrBaqgogqt85sqFNbabZOuFbCVFb8kPeEtZjiKkbrm395irpNKiYeFeLiQnFPg==", + "license": "MIT", + "dependencies": { + "@asamuzakjp/css-color": "^3.2.0", + "rrweb-cssom": "^0.8.0" + }, + "engines": { + "node": ">=18" + } + }, + "node_modules/cssstyle/node_modules/rrweb-cssom": { + "version": "0.8.0", + "resolved": "https://registry.npmjs.org/rrweb-cssom/-/rrweb-cssom-0.8.0.tgz", + "integrity": "sha512-guoltQEx+9aMf2gDZ0s62EcV8lsXR+0w8915TC3ITdn2YueuNjdAYh/levpU9nFaoChh9RUS5ZdQMrKfVEN9tw==", + "license": "MIT" + }, + "node_modules/data-urls": { + "version": "5.0.0", + "resolved": "https://registry.npmjs.org/data-urls/-/data-urls-5.0.0.tgz", + "integrity": "sha512-ZYP5VBHshaDAiVZxjbRVcFJpc+4xGgT0bK3vzy1HLN8jTO975HEbuYzZJcHoQEY5K1a0z8YayJkyVETa08eNTg==", + "license": "MIT", + "dependencies": { + "whatwg-mimetype": "^4.0.0", + "whatwg-url": "^14.0.0" + }, + "engines": { + "node": ">=18" + } + }, "node_modules/debug": { "version": "4.4.3", "resolved": "https://registry.npmjs.org/debug/-/debug-4.4.3.tgz", "integrity": "sha512-RGwwWnwQvkVfavKVt22FGLw+xYSdzARwm0ru6DhTVA3umU5hZc28V3kO4stgYryrTlLpuvgI9GiijltAjNbcqA==", - "dev": true, "license": "MIT", "dependencies": { "ms": "^2.1.3" @@ -2019,6 +2211,12 @@ "node": ">=0.10.0" } }, + "node_modules/decimal.js": { + "version": "10.6.0", + "resolved": "https://registry.npmjs.org/decimal.js/-/decimal.js-10.6.0.tgz", + "integrity": "sha512-YpgQiITW3JXGntzdUmyUR1V812Hn8T1YVXhCu+wO3OpS4eU9l4YdD3qjyiKdV6mvV29zapkMeD390UVEf2lkUg==", + "license": "MIT" + }, "node_modules/dedent": { "version": "1.7.2", "resolved": "https://registry.npmjs.org/dedent/-/dedent-1.7.2.tgz", @@ -2044,6 +2242,15 @@ "node": ">=0.10.0" } }, + "node_modules/delayed-stream": { + "version": "1.0.0", + "resolved": "https://registry.npmjs.org/delayed-stream/-/delayed-stream-1.0.0.tgz", + "integrity": "sha512-ZySD7Nf91aLB0RxL4KGrKHBXl7Eds1DAmEdcoVawXnLD7SDhpNgtuII2aAkg7a7QS41jxPSZ17p4VdGnMHk3MQ==", + "license": "MIT", + "engines": { + "node": ">=0.4.0" + } + }, "node_modules/detect-newline": { "version": "3.1.0", "resolved": "https://registry.npmjs.org/detect-newline/-/detect-newline-3.1.0.tgz", @@ -2142,6 +2349,20 @@ "url": "https://dotenvx.com" } }, + "node_modules/dunder-proto": { + "version": "1.0.1", + "resolved": "https://registry.npmjs.org/dunder-proto/-/dunder-proto-1.0.1.tgz", + "integrity": "sha512-KIN/nDJBQRcXw0MLVhZE9iQHmG68qAVIBg9CqmUYjmQIhgij9U5MFvrqkUL5FbtyyzZuOeOt0zdeRe4UY7ct+A==", + "license": "MIT", + "dependencies": { + "call-bind-apply-helpers": "^1.0.1", + "es-errors": "^1.3.0", + "gopd": "^1.2.0" + }, + "engines": { + "node": ">= 0.4" + } + }, "node_modules/eastasianwidth": { "version": "0.2.0", "resolved": "https://registry.npmjs.org/eastasianwidth/-/eastasianwidth-0.2.0.tgz", @@ -2211,6 +2432,51 @@ "is-arrayish": "^0.2.1" } }, + "node_modules/es-define-property": { + "version": "1.0.1", + "resolved": "https://registry.npmjs.org/es-define-property/-/es-define-property-1.0.1.tgz", + "integrity": "sha512-e3nRfgfUZ4rNGL232gUgX06QNyyez04KdjFrF+LTRoOXmrOgFKDg4BCdsjW8EnT69eqdYGmRpJwiPVYNrCaW3g==", + "license": "MIT", + "engines": { + "node": ">= 0.4" + } + }, + "node_modules/es-errors": { + "version": "1.3.0", + "resolved": "https://registry.npmjs.org/es-errors/-/es-errors-1.3.0.tgz", + "integrity": "sha512-Zf5H2Kxt2xjTvbJvP2ZWLEICxA6j+hAmMzIlypy4xcBg1vKVnx89Wy0GbS+kf5cwCVFFzdCFh2XSCFNULS6csw==", + "license": "MIT", + "engines": { + "node": ">= 0.4" + } + }, + "node_modules/es-object-atoms": { + "version": "1.1.1", + "resolved": "https://registry.npmjs.org/es-object-atoms/-/es-object-atoms-1.1.1.tgz", + "integrity": "sha512-FGgH2h8zKNim9ljj7dankFPcICIK9Cp5bm+c2gQSYePhpaG5+esrLODihIorn+Pe6FGJzWhXQotPv73jTaldXA==", + "license": "MIT", + "dependencies": { + "es-errors": "^1.3.0" + }, + "engines": { + "node": ">= 0.4" + } + }, + "node_modules/es-set-tostringtag": { + "version": "2.1.0", + "resolved": "https://registry.npmjs.org/es-set-tostringtag/-/es-set-tostringtag-2.1.0.tgz", + "integrity": "sha512-j6vWzfrGVfyXxge+O0x5sh6cvxAog0a/4Rdd2K36zCMV5eJ+/+tOAngRO8cODMNWbVRdVlmGZQL2YS3yR8bIUA==", + "license": "MIT", + "dependencies": { + "es-errors": "^1.3.0", + "get-intrinsic": "^1.2.6", + "has-tostringtag": "^1.0.2", + "hasown": "^2.0.2" + }, + "engines": { + "node": ">= 0.4" + } + }, "node_modules/escalade": { "version": "3.2.0", "resolved": "https://registry.npmjs.org/escalade/-/escalade-3.2.0.tgz", @@ -2376,6 +2642,22 @@ "url": "https://github.com/sponsors/isaacs" } }, + "node_modules/form-data": { + "version": "4.0.5", + "resolved": "https://registry.npmjs.org/form-data/-/form-data-4.0.5.tgz", + "integrity": "sha512-8RipRLol37bNs2bhoV67fiTEvdTrbMUYcFTiy3+wuuOnUog2QBHCZWXDRijWQfAkhBj2Uf5UnVaiWwA5vdd82w==", + "license": "MIT", + "dependencies": { + "asynckit": "^0.4.0", + "combined-stream": "^1.0.8", + "es-set-tostringtag": "^2.1.0", + "hasown": "^2.0.2", + "mime-types": "^2.1.12" + }, + "engines": { + "node": ">= 6" + } + }, "node_modules/fs.realpath": { "version": "1.0.0", "resolved": "https://registry.npmjs.org/fs.realpath/-/fs.realpath-1.0.0.tgz", @@ -2402,7 +2684,6 @@ "version": "1.1.2", "resolved": "https://registry.npmjs.org/function-bind/-/function-bind-1.1.2.tgz", "integrity": "sha512-7XHNxH7qX9xG5mIwxkhumTox/MIRNcOgDrxWsMt2pAr23WHp6MrRlN7FBSFpCpr+oVO0F744iUgR82nJMfG2SA==", - "dev": true, "license": "MIT", "funding": { "url": "https://github.com/sponsors/ljharb" @@ -2428,6 +2709,30 @@ "node": "6.* || 8.* || >= 10.*" } }, + "node_modules/get-intrinsic": { + "version": "1.3.0", + "resolved": "https://registry.npmjs.org/get-intrinsic/-/get-intrinsic-1.3.0.tgz", + "integrity": "sha512-9fSjSaos/fRIVIp+xSJlE6lfwhES7LNtKaCBIamHsjr2na1BiABJPo0mOjjz8GJDURarmCPGqaiVg5mfjb98CQ==", + "license": "MIT", + "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" + }, + "engines": { + "node": ">= 0.4" + }, + "funding": { + "url": "https://github.com/sponsors/ljharb" + } + }, "node_modules/get-package-type": { "version": "0.1.0", "resolved": "https://registry.npmjs.org/get-package-type/-/get-package-type-0.1.0.tgz", @@ -2438,6 +2743,19 @@ "node": ">=8.0.0" } }, + "node_modules/get-proto": { + "version": "1.0.1", + "resolved": "https://registry.npmjs.org/get-proto/-/get-proto-1.0.1.tgz", + "integrity": "sha512-sTSfBjoXBp89JvIKIefqw7U2CCebsc74kiY6awiGogKtoSGbgjYE/G/+l9sF3MWFPNc9IcoOC4ODfKHfxFmp0g==", + "license": "MIT", + "dependencies": { + "dunder-proto": "^1.0.1", + "es-object-atoms": "^1.0.0" + }, + "engines": { + "node": ">= 0.4" + } + }, "node_modules/get-stream": { "version": "6.0.1", "resolved": "https://registry.npmjs.org/get-stream/-/get-stream-6.0.1.tgz", @@ -2473,6 +2791,18 @@ "url": "https://github.com/sponsors/isaacs" } }, + "node_modules/gopd": { + "version": "1.2.0", + "resolved": "https://registry.npmjs.org/gopd/-/gopd-1.2.0.tgz", + "integrity": "sha512-ZUKRh6/kUFoAiTAtTYPZJ3hw9wNxx+BIBOijnlG9PnrJsCcSjs1wyyD6vJpaYtgnzDrKYRSqf3OO6Rfa93xsRg==", + "license": "MIT", + "engines": { + "node": ">= 0.4" + }, + "funding": { + "url": "https://github.com/sponsors/ljharb" + } + }, "node_modules/graceful-fs": { "version": "4.2.11", "resolved": "https://registry.npmjs.org/graceful-fs/-/graceful-fs-4.2.11.tgz", @@ -2512,11 +2842,37 @@ "node": ">=8" } }, + "node_modules/has-symbols": { + "version": "1.1.0", + "resolved": "https://registry.npmjs.org/has-symbols/-/has-symbols-1.1.0.tgz", + "integrity": "sha512-1cDNdwJ2Jaohmb3sg4OmKaMBwuC48sYni5HUw2DvsC8LjGTLK9h+eb1X6RyuOHe4hT0ULCW68iomhjUoKUqlPQ==", + "license": "MIT", + "engines": { + "node": ">= 0.4" + }, + "funding": { + "url": "https://github.com/sponsors/ljharb" + } + }, + "node_modules/has-tostringtag": { + "version": "1.0.2", + "resolved": "https://registry.npmjs.org/has-tostringtag/-/has-tostringtag-1.0.2.tgz", + "integrity": "sha512-NqADB8VjPFLM2V0VvHUewwwsw0ZWBaIdgo+ieHtK3hasLz4qeCRjYcqfB6AQrBggRKppKF8L52/VqdVsO47Dlw==", + "license": "MIT", + "dependencies": { + "has-symbols": "^1.0.3" + }, + "engines": { + "node": ">= 0.4" + }, + "funding": { + "url": "https://github.com/sponsors/ljharb" + } + }, "node_modules/hasown": { "version": "2.0.2", "resolved": "https://registry.npmjs.org/hasown/-/hasown-2.0.2.tgz", "integrity": "sha512-0hJU9SCPvmMzIBdZFqNPXWa6dqh7WdH0cII9y+CyS8rG3nL48Bclra9HmKhVVUHyPWNH5Y7xDwAB7bfgSjkUMQ==", - "dev": true, "license": "MIT", "dependencies": { "function-bind": "^1.1.2" @@ -2525,6 +2881,18 @@ "node": ">= 0.4" } }, + "node_modules/html-encoding-sniffer": { + "version": "4.0.0", + "resolved": "https://registry.npmjs.org/html-encoding-sniffer/-/html-encoding-sniffer-4.0.0.tgz", + "integrity": "sha512-Y22oTqIU4uuPgEemfz7NDJz6OeKf12Lsu+QC+s3BVpda64lTiMYCyGwg5ki4vFxkMwQdeZDl2adZoqUgdFuTgQ==", + "license": "MIT", + "dependencies": { + "whatwg-encoding": "^3.1.1" + }, + "engines": { + "node": ">=18" + } + }, "node_modules/html-escaper": { "version": "2.0.2", "resolved": "https://registry.npmjs.org/html-escaper/-/html-escaper-2.0.2.tgz", @@ -2563,6 +2931,32 @@ "url": "https://github.com/fb55/entities?sponsor=1" } }, + "node_modules/http-proxy-agent": { + "version": "7.0.2", + "resolved": "https://registry.npmjs.org/http-proxy-agent/-/http-proxy-agent-7.0.2.tgz", + "integrity": "sha512-T1gkAiYYDWYx3V5Bmyu7HcfcvL7mUrTWiM6yOfa3PIphViJ/gFPbvidQ+veqSOHci/PxBcDabeUNCzpOODJZig==", + "license": "MIT", + "dependencies": { + "agent-base": "^7.1.0", + "debug": "^4.3.4" + }, + "engines": { + "node": ">= 14" + } + }, + "node_modules/https-proxy-agent": { + "version": "7.0.6", + "resolved": "https://registry.npmjs.org/https-proxy-agent/-/https-proxy-agent-7.0.6.tgz", + "integrity": "sha512-vK9P5/iUfdl95AI+JVyUuIcVtd4ofvtrOr3HNtM2yxC9bnMbEdp3x01OhQNnjb8IJYi38VlTE3mBXwcfvywuSw==", + "license": "MIT", + "dependencies": { + "agent-base": "^7.1.2", + "debug": "4" + }, + "engines": { + "node": ">= 14" + } + }, "node_modules/human-signals": { "version": "2.1.0", "resolved": "https://registry.npmjs.org/human-signals/-/human-signals-2.1.0.tgz", @@ -2687,6 +3081,12 @@ "node": ">=0.12.0" } }, + "node_modules/is-potential-custom-element-name": { + "version": "1.0.1", + "resolved": "https://registry.npmjs.org/is-potential-custom-element-name/-/is-potential-custom-element-name-1.0.1.tgz", + "integrity": "sha512-bCYeRA2rVibKZd+s2625gGnGF/t7DSqDs4dP7CrLA1m7jKWz6pps0LpYLJN8Q64HtmPKJ1hrN3nzPNKFEKOUiQ==", + "license": "MIT" + }, "node_modules/is-stream": { "version": "2.0.1", "resolved": "https://registry.npmjs.org/is-stream/-/is-stream-2.0.1.tgz", @@ -3421,6 +3821,46 @@ "js-yaml": "bin/js-yaml.js" } }, + "node_modules/jsdom": { + "version": "24.1.3", + "resolved": "https://registry.npmjs.org/jsdom/-/jsdom-24.1.3.tgz", + "integrity": "sha512-MyL55p3Ut3cXbeBEG7Hcv0mVM8pp8PBNWxRqchZnSfAiES1v1mRnMeFfaHWIPULpwsYfvO+ZmMZz5tGCnjzDUQ==", + "license": "MIT", + "dependencies": { + "cssstyle": "^4.0.1", + "data-urls": "^5.0.0", + "decimal.js": "^10.4.3", + "form-data": "^4.0.0", + "html-encoding-sniffer": "^4.0.0", + "http-proxy-agent": "^7.0.2", + "https-proxy-agent": "^7.0.5", + "is-potential-custom-element-name": "^1.0.1", + "nwsapi": "^2.2.12", + "parse5": "^7.1.2", + "rrweb-cssom": "^0.7.1", + "saxes": "^6.0.0", + "symbol-tree": "^3.2.4", + "tough-cookie": "^4.1.4", + "w3c-xmlserializer": "^5.0.0", + "webidl-conversions": "^7.0.0", + "whatwg-encoding": "^3.1.1", + "whatwg-mimetype": "^4.0.0", + "whatwg-url": "^14.0.0", + "ws": "^8.18.0", + "xml-name-validator": "^5.0.0" + }, + "engines": { + "node": ">=18" + }, + "peerDependencies": { + "canvas": "^2.11.2" + }, + "peerDependenciesMeta": { + "canvas": { + "optional": true + } + } + }, "node_modules/jsesc": { "version": "3.1.0", "resolved": "https://registry.npmjs.org/jsesc/-/jsesc-3.1.0.tgz", @@ -3645,6 +4085,15 @@ "tmpl": "1.0.5" } }, + "node_modules/math-intrinsics": { + "version": "1.1.0", + "resolved": "https://registry.npmjs.org/math-intrinsics/-/math-intrinsics-1.1.0.tgz", + "integrity": "sha512-/IXtbwEk5HTPyEwyKX6hGkYXxM9nbj64B+ilVJnC/R6B0pH5G4V3b0pVbL7DBj4tkhBAppbQUlf6F6Xl9LHu1g==", + "license": "MIT", + "engines": { + "node": ">= 0.4" + } + }, "node_modules/merge-stream": { "version": "2.0.0", "resolved": "https://registry.npmjs.org/merge-stream/-/merge-stream-2.0.0.tgz", @@ -3666,6 +4115,27 @@ "node": ">=8.6" } }, + "node_modules/mime-db": { + "version": "1.52.0", + "resolved": "https://registry.npmjs.org/mime-db/-/mime-db-1.52.0.tgz", + "integrity": "sha512-sPU4uV7dYlvtWJxwwxHD0PuihVNiE7TyAbQ5SWxDCB9mUYvOgroQOwYQQOKPJ8CIbE+1ETVlOoK1UC2nU3gYvg==", + "license": "MIT", + "engines": { + "node": ">= 0.6" + } + }, + "node_modules/mime-types": { + "version": "2.1.35", + "resolved": "https://registry.npmjs.org/mime-types/-/mime-types-2.1.35.tgz", + "integrity": "sha512-ZDY+bPm5zTTF+YpCrAU9nK0UgICYPT0QtT1NZWFv4s++TNkcgVaT0g6+4R2uI4MjQjzysHB1zxuWL50hzaeXiw==", + "license": "MIT", + "dependencies": { + "mime-db": "1.52.0" + }, + "engines": { + "node": ">= 0.6" + } + }, "node_modules/mimic-fn": { "version": "2.1.0", "resolved": "https://registry.npmjs.org/mimic-fn/-/mimic-fn-2.1.0.tgz", @@ -3713,7 +4183,6 @@ "version": "2.1.3", "resolved": "https://registry.npmjs.org/ms/-/ms-2.1.3.tgz", "integrity": "sha512-6FlzubTLZG3J2a/NVCAleEhjzq5oxgHyaCU9yYXvcLsvoVaHJq/s5xXI6/XXP6tz7R9xAOtHnSO/tXtF3WRTlA==", - "dev": true, "license": "MIT" }, "node_modules/mustache": { @@ -3789,6 +4258,12 @@ "url": "https://github.com/fb55/nth-check?sponsor=1" } }, + "node_modules/nwsapi": { + "version": "2.2.23", + "resolved": "https://registry.npmjs.org/nwsapi/-/nwsapi-2.2.23.tgz", + "integrity": "sha512-7wfH4sLbt4M0gCDzGE6vzQBo0bfTKjU7Sfpqy/7gs1qBfYz2vEJH6vXcBKpO3+6Yu1telwd0t9HpyOoLEQQbIQ==", + "license": "MIT" + }, "node_modules/once": { "version": "1.4.0", "resolved": "https://registry.npmjs.org/once/-/once-1.4.0.tgz", @@ -4187,6 +4662,27 @@ "node": ">= 6" } }, + "node_modules/psl": { + "version": "1.15.0", + "resolved": "https://registry.npmjs.org/psl/-/psl-1.15.0.tgz", + "integrity": "sha512-JZd3gMVBAVQkSs6HdNZo9Sdo0LNcQeMNP3CozBJb3JYC/QUYZTnKxP+f8oWRX4rHP5EurWxqAHTSwUCjlNKa1w==", + "license": "MIT", + "dependencies": { + "punycode": "^2.3.1" + }, + "funding": { + "url": "https://github.com/sponsors/lupomontero" + } + }, + "node_modules/punycode": { + "version": "2.3.1", + "resolved": "https://registry.npmjs.org/punycode/-/punycode-2.3.1.tgz", + "integrity": "sha512-vYt7UD1U9Wg6138shLtLOvdAu+8DsC/ilFtEVHcH+wydcSpNE20AfSOduf6MkRFahL5FY7X1oU7nKVZFtfq8Fg==", + "license": "MIT", + "engines": { + "node": ">=6" + } + }, "node_modules/pure-rand": { "version": "6.1.0", "resolved": "https://registry.npmjs.org/pure-rand/-/pure-rand-6.1.0.tgz", @@ -4204,6 +4700,12 @@ ], "license": "MIT" }, + "node_modules/querystringify": { + "version": "2.2.0", + "resolved": "https://registry.npmjs.org/querystringify/-/querystringify-2.2.0.tgz", + "integrity": "sha512-FIqgj2EUvTa7R50u0rGsyTftzjYmv/a3hO345bZNrqabNqjtgiDMgmo4mkUjd+nzU5oF3dClKqFIPUKybUyqoQ==", + "license": "MIT" + }, "node_modules/react-is": { "version": "18.3.1", "resolved": "https://registry.npmjs.org/react-is/-/react-is-18.3.1.tgz", @@ -4221,6 +4723,12 @@ "node": ">=0.10.0" } }, + "node_modules/requires-port": { + "version": "1.0.0", + "resolved": "https://registry.npmjs.org/requires-port/-/requires-port-1.0.0.tgz", + "integrity": "sha512-KigOCHcocU3XODJxsu8i/j8T9tzT4adHiecwORRQ0ZZFcp7ahwXuRU1m+yuO90C5ZUyGeGfocHDI14M3L3yDAQ==", + "license": "MIT" + }, "node_modules/resolve": { "version": "1.22.11", "resolved": "https://registry.npmjs.org/resolve/-/resolve-1.22.11.tgz", @@ -4339,12 +4847,30 @@ "url": "https://github.com/sponsors/isaacs" } }, + "node_modules/rrweb-cssom": { + "version": "0.7.1", + "resolved": "https://registry.npmjs.org/rrweb-cssom/-/rrweb-cssom-0.7.1.tgz", + "integrity": "sha512-TrEMa7JGdVm0UThDJSx7ddw5nVm3UJS9o9CCIZ72B1vSyEZoziDqBYP3XIoi/12lKrJR8rE3jeFHMok2F/Mnsg==", + "license": "MIT" + }, "node_modules/safer-buffer": { "version": "2.1.2", "resolved": "https://registry.npmjs.org/safer-buffer/-/safer-buffer-2.1.2.tgz", "integrity": "sha512-YZo3K82SD7Riyi0E1EQPojLz7kpepnSQI9IyPbHHg1XXXevb5dJI7tpyN2ADxGcQbHG7vcyRHk0cbwqcQriUtg==", "license": "MIT" }, + "node_modules/saxes": { + "version": "6.0.0", + "resolved": "https://registry.npmjs.org/saxes/-/saxes-6.0.0.tgz", + "integrity": "sha512-xAg7SOnEhrm5zI3puOOKyy1OMcMlIJZYNJY7xLBwSze0UjhPLnWfj2GF2EpT0jmzaJKIWKHLsaSSajf35bcYnA==", + "license": "ISC", + "dependencies": { + "xmlchars": "^2.2.0" + }, + "engines": { + "node": ">=v12.22.7" + } + }, "node_modules/semver": { "version": "6.3.1", "resolved": "https://registry.npmjs.org/semver/-/semver-6.3.1.tgz", @@ -4581,6 +5107,12 @@ "url": "https://github.com/sponsors/ljharb" } }, + "node_modules/symbol-tree": { + "version": "3.2.4", + "resolved": "https://registry.npmjs.org/symbol-tree/-/symbol-tree-3.2.4.tgz", + "integrity": "sha512-9QNk5KwDF+Bvz+PyObkmSYjI5ksVUYtjW7AU22r2NKcfLJcXp96hkDWU3+XndOsUb+AQ9QhfzfCT2O+CNWT5Tw==", + "license": "MIT" + }, "node_modules/test-exclude": { "version": "6.0.0", "resolved": "https://registry.npmjs.org/test-exclude/-/test-exclude-6.0.0.tgz", @@ -4616,6 +5148,33 @@ "node": ">=8.0" } }, + "node_modules/tough-cookie": { + "version": "4.1.4", + "resolved": "https://registry.npmjs.org/tough-cookie/-/tough-cookie-4.1.4.tgz", + "integrity": "sha512-Loo5UUvLD9ScZ6jh8beX1T6sO1w2/MpCRpEP7V280GKMVUQ0Jzar2U3UJPsrdbziLEMMhu3Ujnq//rhiFuIeag==", + "license": "BSD-3-Clause", + "dependencies": { + "psl": "^1.1.33", + "punycode": "^2.1.1", + "universalify": "^0.2.0", + "url-parse": "^1.5.3" + }, + "engines": { + "node": ">=6" + } + }, + "node_modules/tr46": { + "version": "5.1.1", + "resolved": "https://registry.npmjs.org/tr46/-/tr46-5.1.1.tgz", + "integrity": "sha512-hdF5ZgjTqgAntKkklYw0R03MG2x/bSzTtkxmIRw/sTNV8YXsCJ1tfLAX23lhxhHJlEf3CRCOCGGWw3vI3GaSPw==", + "license": "MIT", + "dependencies": { + "punycode": "^2.3.1" + }, + "engines": { + "node": ">=18" + } + }, "node_modules/ts-jest": { "version": "29.4.6", "resolved": "https://registry.npmjs.org/ts-jest/-/ts-jest-29.4.6.tgz", @@ -4815,6 +5374,15 @@ "dev": true, "license": "MIT" }, + "node_modules/universalify": { + "version": "0.2.0", + "resolved": "https://registry.npmjs.org/universalify/-/universalify-0.2.0.tgz", + "integrity": "sha512-CJ1QgKmNg3CwvAv/kOFmtnEN05f0D/cn9QntgNOQlQF9dgvVTHj3t+8JPdjqawCHk7V/KA+fbUqzZ9XWhcqPUg==", + "license": "MIT", + "engines": { + "node": ">= 4.0.0" + } + }, "node_modules/update-browserslist-db": { "version": "1.2.3", "resolved": "https://registry.npmjs.org/update-browserslist-db/-/update-browserslist-db-1.2.3.tgz", @@ -4846,6 +5414,16 @@ "browserslist": ">= 4.21.0" } }, + "node_modules/url-parse": { + "version": "1.5.10", + "resolved": "https://registry.npmjs.org/url-parse/-/url-parse-1.5.10.tgz", + "integrity": "sha512-WypcfiRhfeUP9vvF0j6rw0J3hrWrw6iZv3+22h6iRMJ/8z1Tj6XfLP4DsUix5MhMPnXpiHDoKyoZ/bdCkwBCiQ==", + "license": "MIT", + "dependencies": { + "querystringify": "^2.1.1", + "requires-port": "^1.0.0" + } + }, "node_modules/uuid": { "version": "11.1.0", "resolved": "https://registry.npmjs.org/uuid/-/uuid-11.1.0.tgz", @@ -4882,6 +5460,18 @@ "node": ">=10.12.0" } }, + "node_modules/w3c-xmlserializer": { + "version": "5.0.0", + "resolved": "https://registry.npmjs.org/w3c-xmlserializer/-/w3c-xmlserializer-5.0.0.tgz", + "integrity": "sha512-o8qghlI8NZHU1lLPrpi2+Uq7abh4GGPpYANlalzWxyWteJOCsr/P+oPBA49TOLu5FTZO4d3F9MnWJfiMo4BkmA==", + "license": "MIT", + "dependencies": { + "xml-name-validator": "^5.0.0" + }, + "engines": { + "node": ">=18" + } + }, "node_modules/walker": { "version": "1.0.8", "resolved": "https://registry.npmjs.org/walker/-/walker-1.0.8.tgz", @@ -4892,6 +5482,15 @@ "makeerror": "1.0.12" } }, + "node_modules/webidl-conversions": { + "version": "7.0.0", + "resolved": "https://registry.npmjs.org/webidl-conversions/-/webidl-conversions-7.0.0.tgz", + "integrity": "sha512-VwddBukDzu71offAQR975unBIGqfKZpM+8ZX6ySk8nYhVoo5CYaZyzt3YBvYtRtO+aoGlqxPg/B87NGVZ/fu6g==", + "license": "BSD-2-Clause", + "engines": { + "node": ">=12" + } + }, "node_modules/whatwg-encoding": { "version": "3.1.1", "resolved": "https://registry.npmjs.org/whatwg-encoding/-/whatwg-encoding-3.1.1.tgz", @@ -4914,6 +5513,19 @@ "node": ">=18" } }, + "node_modules/whatwg-url": { + "version": "14.2.0", + "resolved": "https://registry.npmjs.org/whatwg-url/-/whatwg-url-14.2.0.tgz", + "integrity": "sha512-De72GdQZzNTUBBChsXueQUnPKDkg/5A5zp7pFDuQAj5UFoENpiACU0wlCvzpAGnTkj++ihpKwKyYewn/XNUbKw==", + "license": "MIT", + "dependencies": { + "tr46": "^5.1.0", + "webidl-conversions": "^7.0.0" + }, + "engines": { + "node": ">=18" + } + }, "node_modules/which": { "version": "2.0.2", "resolved": "https://registry.npmjs.org/which/-/which-2.0.2.tgz", @@ -5027,15 +5639,42 @@ "node": "^12.13.0 || ^14.15.0 || >=16.0.0" } }, - "node_modules/xmldom": { - "version": "0.6.0", - "resolved": "https://registry.npmjs.org/xmldom/-/xmldom-0.6.0.tgz", - "integrity": "sha512-iAcin401y58LckRZ0TkI4k0VSM1Qg0KGSc3i8rU+xrxe19A/BN1zHyVSJY7uoutVlaTSzYyk/v5AmkewAP7jtg==", + "node_modules/ws": { + "version": "8.20.0", + "resolved": "https://registry.npmjs.org/ws/-/ws-8.20.0.tgz", + "integrity": "sha512-sAt8BhgNbzCtgGbt2OxmpuryO63ZoDk/sqaB/znQm94T4fCEsy/yV+7CdC1kJhOU9lboAEU7R3kquuycDoibVA==", "license": "MIT", "engines": { "node": ">=10.0.0" + }, + "peerDependencies": { + "bufferutil": "^4.0.1", + "utf-8-validate": ">=5.0.2" + }, + "peerDependenciesMeta": { + "bufferutil": { + "optional": true + }, + "utf-8-validate": { + "optional": true + } } }, + "node_modules/xml-name-validator": { + "version": "5.0.0", + "resolved": "https://registry.npmjs.org/xml-name-validator/-/xml-name-validator-5.0.0.tgz", + "integrity": "sha512-EvGK8EJ3DhaHfbRlETOWAS5pO9MZITeauHKJyb8wyajUfQUenkIg2MvLDTZ4T/TgIcm3HU0TFBgWWboAZ30UHg==", + "license": "Apache-2.0", + "engines": { + "node": ">=18" + } + }, + "node_modules/xmlchars": { + "version": "2.2.0", + "resolved": "https://registry.npmjs.org/xmlchars/-/xmlchars-2.2.0.tgz", + "integrity": "sha512-JZnDKK8B0RCDw84FNdDAIpZK+JuJw+s7Lz8nksI7SIuU3UXJJslUthsi+uWBUYOwPFwW7W7PRLRfUKpxjtjFCw==", + "license": "MIT" + }, "node_modules/xpath": { "version": "0.0.34", "resolved": "https://registry.npmjs.org/xpath/-/xpath-0.0.34.tgz", diff --git a/package.json b/package.json index 1cd0691..fbcbb6b 100644 --- a/package.json +++ b/package.json @@ -59,9 +59,9 @@ }, "dependencies": { "cheerio": "^1.0.0", + "jsdom": "^24.1.3", "jsonrepair": "^3.12.0", "turndown": "^7.2.0", - "xmldom": "^0.6.0", "xpath": "^0.0.34", "zod": "^3.24.3" }, @@ -72,10 +72,9 @@ "@types/jest": "^29.5.12", "@types/node": "^22.15.3", "@types/turndown": "^5.0.5", - "@types/xmldom": "^0.1.34", "dotenv": "^16.3.1", - "playwright": "^1.58.2", "jest": "^29.7.0", + "playwright": "^1.58.2", "rimraf": "^5.0.10", "ts-jest": "^29.1.2", "ts-node": "^10.9.2", diff --git a/src/converters.ts b/src/converters.ts index 4c4c68c..b33541d 100644 --- a/src/converters.ts +++ b/src/converters.ts @@ -1,10 +1,7 @@ import TurndownService from "turndown"; import { HTMLExtractionOptions } from "./types"; -import { DOMParser, XMLSerializer } from "xmldom"; -import { isNodeLike } from "xpath"; import * as url from "url"; -var xpath = require("xpath"); const cheerio = require("cheerio"); /** @@ -42,23 +39,29 @@ function cleanUrl(urlString: string): string { */ function extractMainHtml(html: string): string { try { - const bodyDoc = new DOMParser().parseFromString(html, "text/html"); + const { JSDOM } = require("jsdom"); + const dom = new JSDOM(html); + const doc = dom.window.document; [...OVERALL_DISCARD_XPATH, ...PRECISION_DISCARD_XPATH].forEach((xPath) => { - const result = xpath.parse(xPath).select({ node: bodyDoc, isHtml: true }); - - // Ensure result is an array before calling forEach - const nodes = Array.isArray(result) ? result : [result]; + const result = doc.evaluate( + xPath, + doc, + null, + dom.window.XPathResult.ORDERED_NODE_SNAPSHOT_TYPE, + null, + ); - nodes.forEach((node) => { - if (isNodeLike(node) && node.parentNode) { + for (let i = result.snapshotLength - 1; i >= 0; i--) { + const node = result.snapshotItem(i); + if (node?.parentNode) { node.parentNode.removeChild(node); } - }); + } }); - const refinedHtml = new XMLSerializer().serializeToString(bodyDoc); - return refinedHtml == "" ? html : refinedHtml; + const refinedHtml = doc.body?.innerHTML ?? ""; + return refinedHtml === "" ? html : refinedHtml; } catch (error) { console.error("error extracting main html", error); return ""; @@ -71,7 +74,7 @@ function extractMainHtml(html: string): string { export function htmlToMarkdown( html: string, options?: HTMLExtractionOptions, - sourceUrl?: string + sourceUrl?: string, ): string { // First clean up the html const tidiedHtml = tidyHtml(html, options?.includeImages ?? false); @@ -126,8 +129,8 @@ export function htmlToMarkdown( filter: function (node: any, options: any) { return Boolean( options.linkStyle === "inlined" && - node.nodeName === "A" && - node.getAttribute("href") + node.nodeName === "A" && + node.getAttribute("href"), ); }, @@ -145,7 +148,7 @@ export function htmlToMarkdown( } catch (error) { console.warn( `Failed to resolve URL ${href} against ${sourceUrl}:`, - error + error, ); } } @@ -180,7 +183,7 @@ export function htmlToMarkdown( } catch (error) { console.warn( `Failed to resolve URL ${src} against ${sourceUrl}:`, - error + error, ); } }