{"_id":"@marbec/web-auto-extractor","_rev":"16-57d461c6ef8a048002894259df8203da","name":"@marbec/web-auto-extractor","dist-tags":{"latest":"2.2.1"},"versions":{"2.0.0-beta.1":{"name":"@marbec/web-auto-extractor","version":"2.0.0-beta.1","keywords":["crawler","parser","html parser","schema.org","microdata","rdfa","jsonld","seo"],"license":"MIT","_id":"@marbec/web-auto-extractor@2.0.0-beta.1","maintainers":[{"name":"marbec","email":"mabecker@adobe.com"}],"homepage":"https://github.com/herzog31/web-auto-extractor#readme","bugs":{"url":"https://github.com/herzog31/web-auto-extractor/issues"},"dist":{"shasum":"3654ed73e4f589f1d8b009ef51ec8cab684925b1","tarball":"https://registry.npmjs.org/@marbec/web-auto-extractor/-/web-auto-extractor-2.0.0-beta.1.tgz","fileCount":19,"integrity":"sha512-gyGZrJkYpmmfXF+7yBRgVyQGHF94J3brrIpeH3EdaWD3kJL4DnOUU7yhHQnbrvAsxfMLI6HkyKxvcrLq/3sVyQ==","signatures":[{"sig":"MEUCIQDVTS/8dfRzj5bAcKoQeXb+WCjF8MUZLT1wLbnZPD6iAwIgMQnm5HEcvP9H2VKW1U8oYC+Sw/ykzK5B8+OkLELsP28=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":885447},"main":"dist/index.js","type":"module","engines":{"node":">=18.0.0"},"gitHead":"df30016fffdf4fbad332767089be1618d24c97a5","scripts":{"lint":"eslint .","test":"mocha --recursive","build":"parcel build src/index.js","start":"parcel src/index.js","format":"prettier --single-quote --check .","format:fix":"prettier --single-quote --write .","prepublish":"npm run lint && npm run format && npm run test && npm run build"},"_npmUser":{"name":"marbec","email":"mabecker@adobe.com"},"repository":{"url":"git+https://github.com/herzog31/web-auto-extractor.git","type":"git"},"_npmVersion":"10.2.3","description":"Automatically extracts structured information from webpages","directories":{},"_nodeVersion":"20.10.0","dependencies":{"cheerio":"^1.0.0","htmlparser2":"^3.9.1"},"publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"chai":"^5.2.0","mocha":"^11.1.0","eslint":"^9.22.0","parcel":"^2.14.0","globals":"^16.0.0","prettier":"^3.5.3","@eslint/js":"^9.22.0"},"_npmOperationalInternal":{"tmp":"tmp/web-auto-extractor_2.0.0-beta.1_1742316152114_0.8540330334865216","host":"s3://npm-registry-packages-npm-production"}},"2.0.0-beta.2":{"name":"@marbec/web-auto-extractor","version":"2.0.0-beta.2","keywords":["crawler","parser","html parser","schema.org","microdata","rdfa","jsonld","seo"],"license":"MIT","_id":"@marbec/web-auto-extractor@2.0.0-beta.2","maintainers":[{"name":"marbec","email":"mabecker@adobe.com"}],"homepage":"https://github.com/herzog31/web-auto-extractor#readme","bugs":{"url":"https://github.com/herzog31/web-auto-extractor/issues"},"dist":{"shasum":"8ed9e325d43843b2d7ec00d36a5052287d918d20","tarball":"https://registry.npmjs.org/@marbec/web-auto-extractor/-/web-auto-extractor-2.0.0-beta.2.tgz","fileCount":19,"integrity":"sha512-ZoQIsBCAbeWVriR4p4cp9zfwiTAv70dGg6lnoWs68fmcL+TgMDgoO6FZ5UoMA8k8u9lCid9o39OAn1FOJNMnjg==","signatures":[{"sig":"MEUCIB4stQR7Fd/CUEyQWyILa4Z5K5mGtnGy0J/jl5vWBMIMAiEA+koMV2oyMBGHjqid6xc504DsAWh1bABxY21TKXHtk8Y=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":936364},"main":"dist/index.js","type":"module","engines":{"node":">=18.0.0"},"gitHead":"49745372ffd3a6fb6a6602c79c3fabfd2bf82b6d","scripts":{"lint":"eslint .","test":"mocha --recursive","build":"parcel build src/index.js","start":"parcel src/index.js","format":"prettier --single-quote --check .","format:fix":"prettier --single-quote --write .","prepublish":"npm run lint && npm run format && npm run test && npm run build"},"_npmUser":{"name":"marbec","email":"mabecker@adobe.com"},"repository":{"url":"git+https://github.com/herzog31/web-auto-extractor.git","type":"git"},"_npmVersion":"10.2.3","description":"Automatically extracts structured information from webpages","directories":{},"_nodeVersion":"20.10.0","dependencies":{"cheerio":"^1.0.0","htmlparser2":"^3.9.1"},"publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"chai":"^5.2.0","mocha":"^11.1.0","eslint":"^9.22.0","parcel":"^2.14.0","globals":"^16.0.0","prettier":"^3.5.3","@eslint/js":"^9.22.0"},"_npmOperationalInternal":{"tmp":"tmp/web-auto-extractor_2.0.0-beta.2_1742393287629_0.8557607602770785","host":"s3://npm-registry-packages-npm-production"}},"2.0.0-beta.3":{"name":"@marbec/web-auto-extractor","version":"2.0.0-beta.3","keywords":["crawler","parser","html parser","schema.org","microdata","rdfa","jsonld","seo"],"license":"MIT","_id":"@marbec/web-auto-extractor@2.0.0-beta.3","maintainers":[{"name":"marbec","email":"mabecker@adobe.com"}],"homepage":"https://github.com/herzog31/web-auto-extractor#readme","bugs":{"url":"https://github.com/herzog31/web-auto-extractor/issues"},"dist":{"shasum":"149a0ac219f484885ba52058063c523b4fac2dcf","tarball":"https://registry.npmjs.org/@marbec/web-auto-extractor/-/web-auto-extractor-2.0.0-beta.3.tgz","fileCount":19,"integrity":"sha512-Ic4dYAbDfXpqYGVwHlsT9ezccJ/VYPDFxFRWnDF2Ag0/moNH7BvUx7GtuvSughihNT5JQ43RvyBGwH0E9h2yzg==","signatures":[{"sig":"MEQCIBBDcOpcBeDEUmWrIXi8e96p9ihyNPvETBsILv9QvDNzAiAxCF+ZwmRXD3D78RXMV0ICSMEPKozTFKtUGWnu7EjWUw==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":938155},"main":"dist/index.js","type":"module","engines":{"node":">=18.0.0"},"gitHead":"379081f9ed4ab8eccdd44370cf4a3cb261a81c37","scripts":{"lint":"eslint .","test":"mocha --recursive","build":"parcel build src/index.js","start":"parcel src/index.js","format":"prettier --single-quote --check .","format:fix":"prettier --single-quote --write .","prepublish":"npm run lint && npm run format && npm run test && npm run build"},"_npmUser":{"name":"marbec","email":"mabecker@adobe.com"},"repository":{"url":"git+https://github.com/herzog31/web-auto-extractor.git","type":"git"},"_npmVersion":"10.2.3","description":"Automatically extracts structured information from webpages","directories":{},"_nodeVersion":"20.10.0","dependencies":{"cheerio":"^1.0.0","parse5-sax-parser":"^7.0.0"},"publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"chai":"^5.2.0","mocha":"^11.1.0","eslint":"^9.22.0","parcel":"^2.14.0","globals":"^16.0.0","prettier":"^3.5.3","@eslint/js":"^9.22.0"},"_npmOperationalInternal":{"tmp":"tmp/web-auto-extractor_2.0.0-beta.3_1743586890697_0.2711538712449828","host":"s3://npm-registry-packages-npm-production"}},"2.0.0-beta.4":{"name":"@marbec/web-auto-extractor","version":"2.0.0-beta.4","keywords":["crawler","parser","html parser","schema.org","microdata","rdfa","jsonld","seo"],"license":"MIT","_id":"@marbec/web-auto-extractor@2.0.0-beta.4","maintainers":[{"name":"marbec","email":"mabecker@adobe.com"}],"homepage":"https://github.com/herzog31/web-auto-extractor#readme","bugs":{"url":"https://github.com/herzog31/web-auto-extractor/issues"},"dist":{"shasum":"4e08af38bbc10678b0352df16576fbadacb3bce0","tarball":"https://registry.npmjs.org/@marbec/web-auto-extractor/-/web-auto-extractor-2.0.0-beta.4.tgz","fileCount":19,"integrity":"sha512-pLW9Y5oT0103DdXq7OOR+4zIr1Sw2AHUQl9Trc7KYK+X5ozubLzpolBKXR+UlDCfEpYpx0OxJ98K9UmfwpIFDQ==","signatures":[{"sig":"MEYCIQDeiEb3x/pMivd3c0sYw8bKW1nkD8zBSmHvGqW/rX3J0wIhAIg4Z1OTA1YKalqb4GzRnCMfelss0o+L2Ovrp5WJNrgu","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":978791},"main":"dist/index.js","type":"module","engines":{"node":">=18.0.0"},"gitHead":"0a1a15a67855e74d253783c44cced6f09f8cc727","scripts":{"lint":"eslint .","test":"mocha --recursive","build":"parcel build src/index.js","start":"parcel src/index.js","format":"prettier --single-quote --check .","format:fix":"prettier --single-quote --write .","prepublish":"npm run lint && npm run format && npm run test && npm run build"},"_npmUser":{"name":"marbec","email":"mabecker@adobe.com"},"repository":{"url":"git+https://github.com/herzog31/web-auto-extractor.git","type":"git"},"_npmVersion":"10.9.2","description":"Automatically extracts structured information from webpages","directories":{},"_nodeVersion":"22.13.1","dependencies":{"cheerio":"^1.0.0","parse5-sax-parser":"^7.0.0"},"publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"chai":"^5.2.0","mocha":"^11.1.0","eslint":"^9.22.0","parcel":"^2.14.0","globals":"^16.0.0","prettier":"^3.5.3","@eslint/js":"^9.22.0"},"_npmOperationalInternal":{"tmp":"tmp/web-auto-extractor_2.0.0-beta.4_1743596896964_0.6730392404129795","host":"s3://npm-registry-packages-npm-production"}},"2.0.0-beta.5":{"name":"@marbec/web-auto-extractor","version":"2.0.0-beta.5","keywords":["crawler","parser","html parser","schema.org","microdata","rdfa","jsonld","seo"],"license":"MIT","_id":"@marbec/web-auto-extractor@2.0.0-beta.5","maintainers":[{"name":"marbec","email":"mabecker@adobe.com"}],"homepage":"https://github.com/herzog31/web-auto-extractor#readme","bugs":{"url":"https://github.com/herzog31/web-auto-extractor/issues"},"dist":{"shasum":"ddbb946e1473cb977e31f7d0f55a7b2bda8a27ef","tarball":"https://registry.npmjs.org/@marbec/web-auto-extractor/-/web-auto-extractor-2.0.0-beta.5.tgz","fileCount":15,"integrity":"sha512-Jm5GzYPnaPpZlM/Ul9if12Mm3jHXMzHtOf77L3apEcyXmJ2PfSH/UGBL5ubxZv67jyLe9N4qJ0P4iDgfJ4ZWOw==","signatures":[{"sig":"MEQCIErY9OHSTrpfXiKUuO1efhDl61KXU8WM9mI2OI/gnoM1AiB1LH82CZft+8edffdIOXPsi/A+aROmB3am2kPc9WSu7w==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":948300},"main":"dist/index.js","type":"module","engines":{"node":">=18.0.0"},"gitHead":"477e0ebeee1798b176868b68797ccfbeec8d8ea0","scripts":{"lint":"eslint .","test":"mocha --recursive","build":"parcel build src/index.js","start":"parcel src/index.js","format":"prettier --single-quote --check .","format:fix":"prettier --single-quote --write .","prepublish":"npm run lint && npm run format && npm run test && npm run build"},"_npmUser":{"name":"marbec","email":"mabecker@adobe.com"},"repository":{"url":"git+https://github.com/herzog31/web-auto-extractor.git","type":"git"},"_npmVersion":"10.9.2","description":"Automatically extracts structured information from webpages","directories":{},"_nodeVersion":"22.13.1","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"chai":"^5.2.0","mocha":"^11.1.0","eslint":"^9.22.0","parcel":"^2.14.0","globals":"^16.0.0","prettier":"^3.5.3","@eslint/js":"^9.22.0"},"_npmOperationalInternal":{"tmp":"tmp/web-auto-extractor_2.0.0-beta.5_1744101669229_0.5609670937722901","host":"s3://npm-registry-packages-npm-production"}},"2.0.0-beta.6":{"name":"@marbec/web-auto-extractor","version":"2.0.0-beta.6","keywords":["crawler","parser","html parser","schema.org","microdata","rdfa","jsonld","seo"],"license":"MIT","_id":"@marbec/web-auto-extractor@2.0.0-beta.6","maintainers":[{"name":"marbec","email":"mabecker@adobe.com"}],"homepage":"https://github.com/herzog31/web-auto-extractor#readme","bugs":{"url":"https://github.com/herzog31/web-auto-extractor/issues"},"dist":{"shasum":"0e22f10fe06dfb866f0c9d51e8ee66c0a334df31","tarball":"https://registry.npmjs.org/@marbec/web-auto-extractor/-/web-auto-extractor-2.0.0-beta.6.tgz","fileCount":15,"integrity":"sha512-+3RBOdGQXKoiZ4bJ8dvsBDXTinX8o1zgluPqJ+Zh1VyR0DQhpUovWYznak+e1tiqjbjB2rZUY+PzADZXOmy7WQ==","signatures":[{"sig":"MEYCIQCSjdnD2dQdPDvd2Hj6YsdBHyW3vhz3AzVmk27bC1zDyQIhAOcYhtxLQYJ0T+AVhPHkOelhFgxxS5MRxtQnXNwl62YY","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1081548},"main":"dist/index.js","type":"module","engines":{"node":">=18.0.0"},"gitHead":"2c7687c581a2b60f13d1f58d838d30c8c854c735","scripts":{"lint":"eslint .","test":"mocha --recursive","build":"parcel build src/index.js","start":"parcel src/index.js","format":"prettier --single-quote --check .","format:fix":"prettier --single-quote --write .","prepublish":"npm run lint && npm run format && npm run test && npm run build"},"_npmUser":{"name":"marbec","email":"mabecker@adobe.com"},"repository":{"url":"git+https://github.com/herzog31/web-auto-extractor.git","type":"git"},"_npmVersion":"10.2.3","description":"Automatically extracts structured information from webpages","directories":{},"_nodeVersion":"20.10.0","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"chai":"^5.2.0","mocha":"^11.1.0","eslint":"^9.22.0","parcel":"^2.14.0","globals":"^16.0.0","prettier":"^3.5.3","@eslint/js":"^9.22.0"},"_npmOperationalInternal":{"tmp":"tmp/web-auto-extractor_2.0.0-beta.6_1744125978637_0.40627231121265117","host":"s3://npm-registry-packages-npm-production"}},"2.0.0-beta.7":{"name":"@marbec/web-auto-extractor","version":"2.0.0-beta.7","keywords":["crawler","parser","html parser","schema.org","microdata","rdfa","jsonld","seo"],"license":"MIT","_id":"@marbec/web-auto-extractor@2.0.0-beta.7","maintainers":[{"name":"marbec","email":"mabecker@adobe.com"}],"homepage":"https://github.com/herzog31/web-auto-extractor#readme","bugs":{"url":"https://github.com/herzog31/web-auto-extractor/issues"},"dist":{"shasum":"48dabb8f0f3a6a92a7d0cb845145465c664ccb1b","tarball":"https://registry.npmjs.org/@marbec/web-auto-extractor/-/web-auto-extractor-2.0.0-beta.7.tgz","fileCount":15,"integrity":"sha512-U+pkulW4n0k14sNVpTZHj5GyJCUI0prM9w1U3xxP9BrX2mpoRm3//HdqIyZq+tMyUYRxmObkY4m4PIaFuQohbw==","signatures":[{"sig":"MEUCIQDdJ4QvyYshJTC1XjrMZTBQzCgQ7cL68k00TEgJrBnYvQIgCDdK+UeRhM2rRkoLkeq7p54hJ+kGk9xKUlPtLrr3574=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1133549},"main":"dist/index.js","type":"module","engines":{"node":">=18.0.0"},"gitHead":"fea65c3eab88361c725528c3a52149daecc27765","scripts":{"lint":"eslint .","test":"mocha --recursive","build":"parcel build src/index.js","start":"parcel src/index.js","format":"prettier --single-quote --check .","format:fix":"prettier --single-quote --write .","prepublish":"npm run lint && npm run format && npm run test && npm run build"},"_npmUser":{"name":"marbec","email":"mabecker@adobe.com"},"repository":{"url":"git+https://github.com/herzog31/web-auto-extractor.git","type":"git"},"_npmVersion":"10.2.3","description":"Automatically extracts structured information from webpages","directories":{},"_nodeVersion":"20.10.0","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"chai":"^5.2.0","mocha":"^11.1.0","eslint":"^9.22.0","parcel":"^2.14.0","globals":"^16.0.0","prettier":"^3.5.3","@eslint/js":"^9.22.0"},"_npmOperationalInternal":{"tmp":"tmp/web-auto-extractor_2.0.0-beta.7_1744377212294_0.1597496239030045","host":"s3://npm-registry-packages-npm-production"}},"2.0.0-beta.8":{"name":"@marbec/web-auto-extractor","version":"2.0.0-beta.8","keywords":["crawler","parser","html parser","schema.org","microdata","rdfa","jsonld","seo"],"license":"MIT","_id":"@marbec/web-auto-extractor@2.0.0-beta.8","maintainers":[{"name":"marbec","email":"mabecker@adobe.com"}],"homepage":"https://github.com/herzog31/web-auto-extractor#readme","bugs":{"url":"https://github.com/herzog31/web-auto-extractor/issues"},"dist":{"shasum":"e562909af6e9f57c7cb7a18c1770e9e8f8d483c0","tarball":"https://registry.npmjs.org/@marbec/web-auto-extractor/-/web-auto-extractor-2.0.0-beta.8.tgz","fileCount":15,"integrity":"sha512-ROoAWRzwJpawsUhJ07YNgwzS4M5wAhM6ODW/0BmAg9PR5R5u/heAZXRb/GFKfBfpbk1xWVPp+Ou/mATWgjwkQg==","signatures":[{"sig":"MEUCIQC7dVcxVFON2xCKY5CRGkr/GtCJbyduVEsFrAOqsP0OjAIgG9rk2zqF8Iygx6PG/tgSSiKGHIcv/UpdVZFuyssOYdc=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":522692},"main":"dist/index.js","type":"module","engines":{"node":">=18.0.0"},"gitHead":"68a57879e50aa53a7f869d10bdf044bd8538109f","scripts":{"lint":"eslint .","test":"mocha --recursive","build":"parcel build src/index.js","start":"parcel src/index.js","format":"prettier --single-quote --check .","format:fix":"prettier --single-quote --write .","prepublish":"npm run lint && npm run format && npm run test && npm run build"},"_npmUser":{"name":"marbec","email":"mabecker@adobe.com"},"repository":{"url":"git+https://github.com/herzog31/web-auto-extractor.git","type":"git"},"_npmVersion":"10.2.3","description":"Automatically extracts structured information from webpages","directories":{},"_nodeVersion":"20.10.0","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"chai":"^5.2.0","mocha":"^11.1.0","eslint":"^9.22.0","parcel":"^2.14.0","globals":"^16.0.0","prettier":"^3.5.3","@eslint/js":"^9.22.0"},"_npmOperationalInternal":{"tmp":"tmp/web-auto-extractor_2.0.0-beta.8_1744634158066_0.09979334669557227","host":"s3://npm-registry-packages-npm-production"}},"2.0.0-beta.9":{"name":"@marbec/web-auto-extractor","version":"2.0.0-beta.9","keywords":["crawler","parser","html parser","schema.org","microdata","rdfa","jsonld","seo"],"license":"MIT","_id":"@marbec/web-auto-extractor@2.0.0-beta.9","maintainers":[{"name":"marbec","email":"mabecker@adobe.com"}],"homepage":"https://github.com/herzog31/web-auto-extractor#readme","bugs":{"url":"https://github.com/herzog31/web-auto-extractor/issues"},"dist":{"shasum":"387e5db5d5598a150c6cb66f3624336e75356d87","tarball":"https://registry.npmjs.org/@marbec/web-auto-extractor/-/web-auto-extractor-2.0.0-beta.9.tgz","fileCount":15,"integrity":"sha512-qsGznMfyOCLhntf68EmOc+uQP/E3RWHwbbeIcgIGMZk88iBmfWwwFe21AtKEIk4dJai1o+nV+GcNeW/xifgMBw==","signatures":[{"sig":"MEYCIQCesUdvCeh5K06+/7p5k2RLd+rlLyIv+6vaZahVkoLTIwIhAMN3dsYb/RGUoxiHWJHfIy2QpZ1UDSN32ue25BtjtGo4","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":522795},"main":"dist/index.js","type":"module","engines":{"node":">=18.0.0"},"gitHead":"e4a67519081208afb797e3396f90b82beca32bef","scripts":{"lint":"eslint .","test":"mocha --recursive","build":"parcel build src/index.js","start":"parcel src/index.js","format":"prettier --single-quote --check .","format:fix":"prettier --single-quote --write .","prepublish":"npm run lint && npm run format && npm run test && npm run build"},"_npmUser":{"name":"marbec","email":"mabecker@adobe.com"},"repository":{"url":"git+https://github.com/herzog31/web-auto-extractor.git","type":"git"},"_npmVersion":"10.2.3","description":"Automatically extracts structured information from webpages","directories":{},"_nodeVersion":"20.10.0","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"chai":"^5.2.0","mocha":"^11.1.0","eslint":"^9.22.0","parcel":"^2.14.0","globals":"^16.0.0","prettier":"^3.5.3","@eslint/js":"^9.22.0"},"_npmOperationalInternal":{"tmp":"tmp/web-auto-extractor_2.0.0-beta.9_1744636149061_0.755292860938445","host":"s3://npm-registry-packages-npm-production"}},"2.0.0-beta.10":{"name":"@marbec/web-auto-extractor","version":"2.0.0-beta.10","keywords":["crawler","parser","html parser","schema.org","microdata","rdfa","jsonld","seo"],"license":"MIT","_id":"@marbec/web-auto-extractor@2.0.0-beta.10","maintainers":[{"name":"marbec","email":"mabecker@adobe.com"}],"homepage":"https://github.com/herzog31/web-auto-extractor#readme","bugs":{"url":"https://github.com/herzog31/web-auto-extractor/issues"},"dist":{"shasum":"8733e44205c43502e38abb162282dd64e9c7c072","tarball":"https://registry.npmjs.org/@marbec/web-auto-extractor/-/web-auto-extractor-2.0.0-beta.10.tgz","fileCount":15,"integrity":"sha512-SWQI7oAbvb/wTOlTKvm3nFP8JM/w3M3APnjK3LHBQqFd4nMk0JPpsLByDYv+5/Kn57nwin47LBsQNhf4xOSvlg==","signatures":[{"sig":"MEYCIQCbiO12W7PrVi/4BSL5AdlXywZZ52raicaveEuUd7wdNAIhAO016/LlGXwnU+wI6eXbpMuifGD18/XZk0ZGpoM5dPzf","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":557344},"main":"dist/index.js","type":"module","engines":{"node":">=18.0.0"},"gitHead":"b53e636979fc70a015c5478c7f3932afbfcd1e56","scripts":{"lint":"eslint .","test":"mocha --recursive","build":"parcel build src/index.js","start":"parcel src/index.js","format":"prettier --single-quote --check .","format:fix":"prettier --single-quote --write .","prepublish":"npm run lint && npm run format && npm run test && npm run build"},"_npmUser":{"name":"marbec","email":"mabecker@adobe.com"},"repository":{"url":"git+https://github.com/herzog31/web-auto-extractor.git","type":"git"},"_npmVersion":"10.2.3","description":"Automatically extracts structured information from webpages","directories":{},"_nodeVersion":"20.10.0","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"chai":"^5.2.0","mocha":"^11.1.0","eslint":"^9.22.0","parcel":"^2.14.0","globals":"^16.0.0","prettier":"^3.5.3","@eslint/js":"^9.22.0"},"_npmOperationalInternal":{"tmp":"tmp/web-auto-extractor_2.0.0-beta.10_1744724323447_0.5975273490059985","host":"s3://npm-registry-packages-npm-production"}},"2.0.0-beta.11":{"name":"@marbec/web-auto-extractor","version":"2.0.0-beta.11","keywords":["crawler","parser","html parser","schema.org","microdata","rdfa","jsonld","seo"],"license":"MIT","_id":"@marbec/web-auto-extractor@2.0.0-beta.11","maintainers":[{"name":"marbec","email":"mabecker@adobe.com"}],"homepage":"https://github.com/herzog31/web-auto-extractor#readme","bugs":{"url":"https://github.com/herzog31/web-auto-extractor/issues"},"dist":{"shasum":"8f1f1800f333450f80d5eae64fee88052efa6728","tarball":"https://registry.npmjs.org/@marbec/web-auto-extractor/-/web-auto-extractor-2.0.0-beta.11.tgz","fileCount":15,"integrity":"sha512-WOHiMsHvLxHkscZORpgDeOP4Z5ssKlagchwW7f7caPRCMVoaezowo8H702ahLGDCFXLEqfNsaKHHw1VXt+wRZw==","signatures":[{"sig":"MEQCIAQruvETGSHM1dmLowrc7CORTLZ+bLp55hvg1686ikaJAiAWKoXF2jcweuOKCkQO8OdHeYHO4VgDy7KHVyjsgncxEg==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":542555},"main":"dist/index.js","type":"module","engines":{"node":">=18.0.0"},"gitHead":"79488c5ef7452101b7611a6f64d014d2942e0109","scripts":{"lint":"eslint .","test":"mocha --recursive","build":"parcel build src/index.js","start":"parcel src/index.js","format":"prettier --single-quote --check .","format:fix":"prettier --single-quote --write .","prepublish":"npm run lint && npm run format && npm run test && npm run build"},"_npmUser":{"name":"marbec","email":"mabecker@adobe.com"},"repository":{"url":"git+https://github.com/herzog31/web-auto-extractor.git","type":"git"},"_npmVersion":"10.2.3","description":"Automatically extracts structured information from webpages","directories":{},"_nodeVersion":"20.10.0","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"chai":"^5.2.0","mocha":"^11.1.0","eslint":"^9.22.0","parcel":"^2.14.0","globals":"^16.0.0","prettier":"^3.5.3","@eslint/js":"^9.22.0"},"_npmOperationalInternal":{"tmp":"tmp/web-auto-extractor_2.0.0-beta.11_1744797160351_0.868089568934755","host":"s3://npm-registry-packages-npm-production"}},"2.0.0-beta.12":{"name":"@marbec/web-auto-extractor","version":"2.0.0-beta.12","keywords":["crawler","parser","html parser","schema.org","microdata","rdfa","jsonld","seo"],"license":"MIT","_id":"@marbec/web-auto-extractor@2.0.0-beta.12","maintainers":[{"name":"marbec","email":"mabecker@adobe.com"}],"homepage":"https://github.com/herzog31/web-auto-extractor#readme","bugs":{"url":"https://github.com/herzog31/web-auto-extractor/issues"},"dist":{"shasum":"131b5ad32a36e5596efe6a8bf49e468dcb57e1e6","tarball":"https://registry.npmjs.org/@marbec/web-auto-extractor/-/web-auto-extractor-2.0.0-beta.12.tgz","fileCount":27,"integrity":"sha512-7m4K2ipmgc379chTwDXMFaTfHQMKKleQ2hA199cI6NknM6uJVRR31gpAbM9ltFvQeMk+Mf1hg0T3xKkf8kGedA==","signatures":[{"sig":"MEUCIChvy2tccmvjWF1xu3ul6JUAdpRDpsRbWPbfJEmr4irbAiEA85l4Rse2gM8oS7MtdrDs2p+2a6XbWNQJk6GkdMzE0x8=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1983887},"main":"dist/index.js","type":"module","engines":{"node":">=18.0.0"},"gitHead":"7c3bbe1a5b01512f42eee7a50ece12238b8ccdd1","scripts":{"lint":"eslint .","test":"c8 mocha --recursive","build":"parcel build src/index.js","start":"parcel src/index.js","format":"prettier --single-quote --check .","format:fix":"prettier --single-quote --write .","prepublish":"npm run lint && npm run format && npm run test && npm run build"},"_npmUser":{"name":"marbec","email":"mabecker@adobe.com"},"repository":{"url":"git+https://github.com/herzog31/web-auto-extractor.git","type":"git"},"_npmVersion":"10.2.3","description":"Automatically extracts structured information from webpages","directories":{},"_nodeVersion":"20.10.0","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"c8":"^9.1.0","chai":"^5.2.0","mocha":"^11.1.0","eslint":"^9.22.0","parcel":"^2.14.0","globals":"^16.0.0","prettier":"^3.5.3","@eslint/js":"^9.22.0"},"_npmOperationalInternal":{"tmp":"tmp/web-auto-extractor_2.0.0-beta.12_1745495120329_0.1120812291883535","host":"s3://npm-registry-packages-npm-production"}},"2.1.0":{"name":"@marbec/web-auto-extractor","version":"2.1.0","keywords":["crawler","parser","html parser","schema.org","microdata","rdfa","jsonld","seo"],"license":"MIT","_id":"@marbec/web-auto-extractor@2.1.0","maintainers":[{"name":"marbec","email":"mabecker@adobe.com"}],"homepage":"https://github.com/herzog31/web-auto-extractor#readme","bugs":{"url":"https://github.com/herzog31/web-auto-extractor/issues"},"dist":{"shasum":"1bc11089fa5ea7b6d2766d2bde08218025a1d741","tarball":"https://registry.npmjs.org/@marbec/web-auto-extractor/-/web-auto-extractor-2.1.0.tgz","fileCount":7,"integrity":"sha512-ejlljv4MKIB/vnBwHkPe3FG2sR+2ELBIY9uP/juM1L4F4EHCQR5h8KGgEZaypELi2Tm0qWvdp6jGMgMJXIg5vw==","signatures":[{"sig":"MEUCIQD4b0Lyz+lHMRvcccsS3CX8WVoapoo356m53u7BnKoLPwIgVdbWJe3L4dFQjj9wpkpjuYYRXrzLSTGUPkRqQDXNL7w=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":72488},"main":"dist/index.js","type":"module","engines":{"node":">=18.0.0"},"gitHead":"f3e8f30403f160bf4698f09c0aea7160ebff18be","scripts":{"lint":"eslint .","test":"c8 mocha --recursive","build":"parcel build src/index.js","start":"parcel src/index.js","format":"prettier --single-quote --check .","format:fix":"prettier --single-quote --write .","prepublish":"npm run lint && npm run format && npm run test && npm run build","semantic-release":"semantic-release","semantic-release-dry":"semantic-release --dry-run --no-ci --branches $CI_BRANCH"},"_npmUser":{"name":"marbec","actor":{"name":"marbec","type":"user","email":"mabecker@adobe.com"},"email":"mabecker@adobe.com"},"repository":{"url":"git+https://github.com/herzog31/web-auto-extractor.git","type":"git"},"_npmVersion":"10.9.2","description":"Automatically extracts structured information from webpages","directories":{},"_nodeVersion":"18.20.8","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"c8":"^9.1.0","chai":"^5.2.0","mocha":"^11.1.0","eslint":"^9.22.0","parcel":"^2.14.0","globals":"^16.0.0","prettier":"^3.5.3","@eslint/js":"^9.22.0","semantic-release":"^22.0.7","@semantic-release/git":"^10.0.1","@semantic-release/npm":"^11.0.2","@semantic-release/github":"^9.2.6","@semantic-release/changelog":"^6.0.3"},"_npmOperationalInternal":{"tmp":"tmp/web-auto-extractor_2.1.0_1751379267021_0.12722393159337564","host":"s3://npm-registry-packages-npm-production"}},"2.1.1":{"name":"@marbec/web-auto-extractor","version":"2.1.1","keywords":["crawler","parser","html parser","schema.org","microdata","rdfa","jsonld","seo"],"license":"MIT","_id":"@marbec/web-auto-extractor@2.1.1","maintainers":[{"name":"marbec","email":"mabecker@adobe.com"}],"homepage":"https://github.com/herzog31/web-auto-extractor#readme","bugs":{"url":"https://github.com/herzog31/web-auto-extractor/issues"},"dist":{"shasum":"a76381253e7451ccd95f72e479ec5b572c8cba35","tarball":"https://registry.npmjs.org/@marbec/web-auto-extractor/-/web-auto-extractor-2.1.1.tgz","fileCount":7,"integrity":"sha512-8pexZjLxxGx9b5kjRvi/vdNk77GcIkH8+BoETNTunEaupc1EsHf/qHXkS8tPHwkUaVI2+gDwLZiVRbcyNxk05w==","signatures":[{"sig":"MEUCIQDK4GIz5ClVuBZ6vrlWnbu3Ehu3XdBD97/13VTIhX6aXwIgdBp3vFZBJpuiWDALCQ7SE/M75aGfzxNYOE5Gpr5IlxM=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":75681},"main":"dist/index.js","type":"module","engines":{"node":">=18.0.0"},"gitHead":"af9101f88f5e005ac57142988274ef3a225e7372","scripts":{"lint":"eslint .","test":"c8 mocha --recursive","build":"parcel build src/index.js","start":"parcel src/index.js","format":"prettier --single-quote --check .","format:fix":"prettier --single-quote --write .","prepublish":"npm run lint && npm run format && npm run test && npm run build","semantic-release":"semantic-release","semantic-release-dry":"semantic-release --dry-run --no-ci --branches $CI_BRANCH"},"_npmUser":{"name":"marbec","email":"mabecker@adobe.com"},"repository":{"url":"git+https://github.com/herzog31/web-auto-extractor.git","type":"git"},"_npmVersion":"10.9.2","description":"Automatically extracts structured information from webpages","directories":{},"_nodeVersion":"18.20.8","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"c8":"^9.1.0","chai":"^5.2.0","mocha":"^11.1.0","eslint":"^9.22.0","parcel":"^2.14.0","globals":"^16.0.0","prettier":"^3.5.3","@eslint/js":"^9.22.0","semantic-release":"^22.0.7","@semantic-release/git":"^10.0.1","@semantic-release/npm":"^11.0.2","@semantic-release/github":"^9.2.6","@semantic-release/changelog":"^6.0.3"},"_npmOperationalInternal":{"tmp":"tmp/web-auto-extractor_2.1.1_1752744347900_0.4196478637130947","host":"s3://npm-registry-packages-npm-production"}},"2.2.0":{"name":"@marbec/web-auto-extractor","version":"2.2.0","keywords":["crawler","parser","html parser","schema.org","microdata","rdfa","jsonld","seo"],"license":"MIT","_id":"@marbec/web-auto-extractor@2.2.0","maintainers":[{"name":"marbec","email":"mabecker@adobe.com"}],"homepage":"https://github.com/herzog31/web-auto-extractor#readme","bugs":{"url":"https://github.com/herzog31/web-auto-extractor/issues"},"dist":{"shasum":"3dcf09dfb2bc9f53e247286183de5ae2ad8e8eb4","tarball":"https://registry.npmjs.org/@marbec/web-auto-extractor/-/web-auto-extractor-2.2.0.tgz","fileCount":7,"integrity":"sha512-JhMMoO5bAwvEYzixgdAq8lTciHfYpYycqdjqEFVvVKGLiE3SPJbeZQLiZKTfDSxWbm7wutAbq5oESj/42JaS+Q==","signatures":[{"sig":"MEYCIQCxgCOFxUeZKX4T+onapZfFDbnYOwCDRquk5qGIuCZsogIhAM70qh6F+QTNPUbRayKBjvK8OJZgt1GMe12r8EyXlHDR","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":87434},"main":"dist/index.js","type":"module","engines":{"node":">=18.0.0"},"gitHead":"2978b57543ab8461cb388076d006c1436fdc3762","scripts":{"lint":"eslint .","test":"c8 mocha --recursive","build":"parcel build src/index.js","start":"parcel src/index.js","format":"prettier --single-quote --check .","format:fix":"prettier --single-quote --write .","prepublish":"npm run lint && npm run format && npm run test && npm run build","semantic-release":"semantic-release","semantic-release-dry":"semantic-release --dry-run --no-ci --branches $CI_BRANCH"},"_npmUser":{"name":"marbec","email":"mabecker@adobe.com"},"repository":{"url":"git+https://github.com/herzog31/web-auto-extractor.git","type":"git"},"_npmVersion":"10.9.2","description":"Automatically extracts structured information from webpages","directories":{},"_nodeVersion":"18.20.8","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"c8":"^9.1.0","chai":"^5.2.0","mocha":"^11.1.0","eslint":"^9.22.0","parcel":"^2.14.0","globals":"^16.0.0","prettier":"^3.5.3","@eslint/js":"^9.22.0","semantic-release":"^22.0.7","@semantic-release/git":"^10.0.1","@semantic-release/npm":"^11.0.2","@semantic-release/github":"^9.2.6","@semantic-release/changelog":"^6.0.3"},"_npmOperationalInternal":{"tmp":"tmp/web-auto-extractor_2.2.0_1753953890919_0.13360509733652393","host":"s3://npm-registry-packages-npm-production"}},"2.2.1":{"name":"@marbec/web-auto-extractor","version":"2.2.1","publishConfig":{"access":"public"},"description":"Automatically extracts structured information from webpages","main":"dist/index.js","scripts":{"start":"parcel src/index.js","build":"parcel build src/index.js","test":"c8 mocha --recursive","lint":"eslint .","format":"prettier --single-quote --check .","format:fix":"prettier --single-quote --write .","prepublish":"npm run lint && npm run format && npm run test && npm run build","semantic-release":"semantic-release","semantic-release-dry":"semantic-release --dry-run --no-ci --branches $CI_BRANCH"},"engines":{"node":">=18.0.0"},"license":"MIT","devDependencies":{"@eslint/js":"^9.22.0","@semantic-release/changelog":"^6.0.3","@semantic-release/git":"^10.0.1","@semantic-release/github":"^11.0.0","@semantic-release/npm":"^12.0.0","c8":"^10.0.0","chai":"^6.0.0","eslint":"^9.22.0","globals":"^16.0.0","mocha":"^11.1.0","parcel":"^2.14.0","prettier":"^3.5.3","semantic-release":"^24.0.0"},"keywords":["crawler","parser","html parser","schema.org","microdata","rdfa","jsonld","seo"],"repository":{"type":"git","url":"git+https://github.com/herzog31/web-auto-extractor.git"},"bugs":{"url":"https://github.com/herzog31/web-auto-extractor/issues"},"type":"module","_id":"@marbec/web-auto-extractor@2.2.1","gitHead":"d02dca75053c135149e4441a3270c12988e55c98","homepage":"https://github.com/herzog31/web-auto-extractor#readme","_nodeVersion":"22.19.0","_npmVersion":"10.9.3","dist":{"integrity":"sha512-xfUFMFH9+XoW/0vOknCcGtHSQMpwuzN/udMB1ZM8lHGOPxMlgPj0mAbpCQxdxlZ/BcgRKprVK4FZOL1+O7EO0A==","shasum":"4775c13ae174b1924a02b023d522202dca0cde00","tarball":"https://registry.npmjs.org/@marbec/web-auto-extractor/-/web-auto-extractor-2.2.1.tgz","fileCount":8,"unpackedSize":94295,"signatures":[{"keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U","sig":"MEYCIQDe0AmPzZArNJAKNlokJJiUyDuhjvemL+GP+EDlXyGkAAIhALMTlRP+wXzVsnMSSCudFJ4PgNmtyglN9RJzSdj8pctP"}]},"_npmUser":{"name":"marbec","email":"mabecker@adobe.com"},"directories":{},"maintainers":[{"name":"marbec","email":"mabecker@adobe.com"}],"_npmOperationalInternal":{"host":"s3://npm-registry-packages-npm-production","tmp":"tmp/web-auto-extractor_2.2.1_1758721364716_0.14589117631404847"},"_hasShrinkwrap":false}},"time":{"created":"2025-03-18T16:42:32.000Z","modified":"2025-09-24T13:42:45.056Z","2.0.0-beta.1":"2025-03-18T16:42:32.331Z","2.0.0-beta.2":"2025-03-19T14:08:07.805Z","2.0.0-beta.3":"2025-04-02T09:41:30.874Z","2.0.0-beta.4":"2025-04-02T12:28:17.150Z","2.0.0-beta.5":"2025-04-08T08:41:09.540Z","2.0.0-beta.6":"2025-04-08T15:26:18.862Z","2.0.0-beta.7":"2025-04-11T13:13:32.542Z","2.0.0-beta.8":"2025-04-14T12:35:58.273Z","2.0.0-beta.9":"2025-04-14T13:09:09.234Z","2.0.0-beta.10":"2025-04-15T13:38:43.609Z","2.0.0-beta.11":"2025-04-16T09:52:40.574Z","2.0.0-beta.12":"2025-04-24T11:45:20.542Z","2.1.0":"2025-07-01T14:14:27.224Z","2.1.1":"2025-07-17T09:25:48.067Z","2.2.0":"2025-07-31T09:24:51.122Z","2.2.1":"2025-09-24T13:42:44.885Z"},"bugs":{"url":"https://github.com/herzog31/web-auto-extractor/issues"},"license":"MIT","homepage":"https://github.com/herzog31/web-auto-extractor#readme","keywords":["crawler","parser","html parser","schema.org","microdata","rdfa","jsonld","seo"],"repository":{"type":"git","url":"git+https://github.com/herzog31/web-auto-extractor.git"},"description":"Automatically extracts structured information from webpages","maintainers":[{"name":"marbec","email":"mabecker@adobe.com"}],"readme":"# Web Auto Extractor 2.0\n\n\n[](https://github.com/herzog31/web-auto-extractor/actions/workflows/ci.yml)\n[](https://www.npmjs.com/package/@marbec/web-auto-extractor)\n\n\n> This project is a fork of [indix/web-auto-extractor](https://github.com/indix/web-auto-extractor).\n\nParse semantically structured information from any HTML webpage.\n\n**Supported formats:**\n\n- Encodings that support [Schema.org](http://schema.org/) vocabularies:\n - Microdata\n - RDFa-lite\n - JSON-LD\n- Meta tags\n- Heading tags\n\nPopularly, many websites mark up their webpages with Schema.org vocabularies for better SEO. This library helps you parse that information to JSON.\n\n## Installation\n\n`npm i --save @marbec/web-auto-extractor`\n\n## [Usage](#usage)\n\n```js\nimport WebAutoExtractor from '@marbec/web-auto-extractor';\n\nconst parsed = new WebAutoExtractor({\n // Add location information to the root elements in the parsed data.\n // Location is stored as start,end offset values in the @location property.\n addLocation: false,\n\n // Embed the source HTML in the root elements in the parsed data using the @source property.\n // This property is either a boolean to embed sources for all data types or an array of data types to embed sources for.\n embedSource: false,\n\n // Skip headings with empty or whitespace-only text content.\n // When true, headings like or
will be excluded from results.\n skipEmptyHeadings: false,\n\n // Skip headings that are inside layout elements (header, footer, nav, aside).\n // When true, headings within these semantic layout containers will be excluded from results.\n // The isLayoutElement field is only included when this option is false.\n skipLayoutElements: false,\n}).parse(sampleHTML);\n\n// Output format\n/* {\n \"metatags\": {},\n \"microdata\": {},\n \"rdfa\": {},\n \"jsonld\": {},\n \"headings\": {}\n} */\n```\n\n### Browser\n\nYou can run the parser directly in the browser on any website using the following commands:\n\n```js\nconst { default: WebAutoExtractor } = await import(\n 'https://unpkg.com/@marbec/web-auto-extractor@latest/dist/index.js'\n);\nnew WebAutoExtractor().parse(document.documentElement.outerHTML);\n```\n\n### Examples\n\nSee test cases for sample in- and outputs.\n","readmeFilename":"README.md"}