├── .gitattributes ├── .github └── ISSUE_TEMPLATE │ └── protocol.md ├── .gitignore ├── README.md ├── _config.yml ├── _data ├── refs.yml └── warc_fields.yml ├── _includes ├── _about.md ├── _issues.md └── _toc.md ├── _layouts ├── default.html └── plaintext.txt ├── assets ├── bootstrap │ ├── css │ │ ├── bootstrap-theme.css │ │ ├── bootstrap-theme.css.map │ │ ├── bootstrap-theme.min.css │ │ ├── bootstrap.css │ │ ├── bootstrap.css.map │ │ └── bootstrap.min.css │ ├── fonts │ │ ├── glyphicons-halflings-regular.eot │ │ ├── glyphicons-halflings-regular.svg │ │ ├── glyphicons-halflings-regular.ttf │ │ ├── glyphicons-halflings-regular.woff │ │ └── glyphicons-halflings-regular.woff2 │ └── js │ │ ├── bootstrap.js │ │ ├── bootstrap.min.js │ │ └── npm.js ├── fonts │ ├── glyphicons-halflings-regular.eot │ ├── glyphicons-halflings-regular.svg │ ├── glyphicons-halflings-regular.ttf │ └── glyphicons-halflings-regular.woff ├── javascripts │ └── scale.fix.js └── stylesheets │ ├── pygment_trac.css │ └── styles.css ├── guidelines ├── cdx-non-get-requests │ └── index.md ├── warc-fields │ └── index.md └── warc-implementation-guidelines │ └── index.md ├── index.md ├── primers └── web-archive-formats │ ├── cdx.unsorted.out │ ├── hello-world.txt │ ├── hello-world.warc │ ├── hello-world.warc.cdx │ ├── hello-world.warc.gz │ └── index.md └── specifications ├── cdx-format ├── cdx-2006 │ └── index.md └── cdx-2015 │ └── index.md ├── warc-deduplication ├── recording-arbitrary-duplicates-1.0.md └── samples │ ├── 20130729-heritrix-original.warc.gz │ ├── 20130729-heritrix-revisit-with-http-headers.warc.gz │ ├── 20141124-heritrix-server-not-modified.warc.gz │ ├── 20141129-heritrix-original.warc.gz │ └── 20141129-heritrix-revisit-with-http-headers-and-new-warc-headers.warc.gz ├── warc-format ├── meetings │ └── 2015-05-01-IIPC-GA-WARC-Meeting-Minutes.md ├── warc-1.0 │ ├── The_WARC_Format.md │ ├── WARC_ISO_28500_version1_latestdraft.doc │ ├── WARC_ISO_28500_version1_latestdraft.pdf │ └── index.md ├── warc-1.1-annotated │ └── index.md └── warc-1.1 │ └── index.md ├── warc-rendered-targets └── warc-rendered-targets-1.0.md └── warc-zstd └── index.md /.gitattributes: -------------------------------------------------------------------------------- 1 | *.warc -text 2 | -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/protocol.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/.github/ISSUE_TEMPLATE/protocol.md -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | _site/ 2 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/README.md -------------------------------------------------------------------------------- /_config.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/_config.yml -------------------------------------------------------------------------------- /_data/refs.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/_data/refs.yml -------------------------------------------------------------------------------- /_data/warc_fields.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/_data/warc_fields.yml -------------------------------------------------------------------------------- /_includes/_about.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/_includes/_about.md -------------------------------------------------------------------------------- /_includes/_issues.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/_includes/_issues.md -------------------------------------------------------------------------------- /_includes/_toc.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/_includes/_toc.md -------------------------------------------------------------------------------- /_layouts/default.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/_layouts/default.html -------------------------------------------------------------------------------- /_layouts/plaintext.txt: -------------------------------------------------------------------------------- 1 | {{ content }} 2 | -------------------------------------------------------------------------------- /assets/bootstrap/css/bootstrap-theme.css: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/assets/bootstrap/css/bootstrap-theme.css -------------------------------------------------------------------------------- /assets/bootstrap/css/bootstrap-theme.css.map: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/assets/bootstrap/css/bootstrap-theme.css.map -------------------------------------------------------------------------------- /assets/bootstrap/css/bootstrap-theme.min.css: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/assets/bootstrap/css/bootstrap-theme.min.css -------------------------------------------------------------------------------- /assets/bootstrap/css/bootstrap.css: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/assets/bootstrap/css/bootstrap.css -------------------------------------------------------------------------------- /assets/bootstrap/css/bootstrap.css.map: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/assets/bootstrap/css/bootstrap.css.map -------------------------------------------------------------------------------- /assets/bootstrap/css/bootstrap.min.css: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/assets/bootstrap/css/bootstrap.min.css -------------------------------------------------------------------------------- /assets/bootstrap/fonts/glyphicons-halflings-regular.eot: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/assets/bootstrap/fonts/glyphicons-halflings-regular.eot -------------------------------------------------------------------------------- /assets/bootstrap/fonts/glyphicons-halflings-regular.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/assets/bootstrap/fonts/glyphicons-halflings-regular.svg -------------------------------------------------------------------------------- /assets/bootstrap/fonts/glyphicons-halflings-regular.ttf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/assets/bootstrap/fonts/glyphicons-halflings-regular.ttf -------------------------------------------------------------------------------- /assets/bootstrap/fonts/glyphicons-halflings-regular.woff: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/assets/bootstrap/fonts/glyphicons-halflings-regular.woff -------------------------------------------------------------------------------- /assets/bootstrap/fonts/glyphicons-halflings-regular.woff2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/assets/bootstrap/fonts/glyphicons-halflings-regular.woff2 -------------------------------------------------------------------------------- /assets/bootstrap/js/bootstrap.js: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/assets/bootstrap/js/bootstrap.js -------------------------------------------------------------------------------- /assets/bootstrap/js/bootstrap.min.js: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/assets/bootstrap/js/bootstrap.min.js -------------------------------------------------------------------------------- /assets/bootstrap/js/npm.js: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/assets/bootstrap/js/npm.js -------------------------------------------------------------------------------- /assets/fonts/glyphicons-halflings-regular.eot: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/assets/fonts/glyphicons-halflings-regular.eot -------------------------------------------------------------------------------- /assets/fonts/glyphicons-halflings-regular.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/assets/fonts/glyphicons-halflings-regular.svg -------------------------------------------------------------------------------- /assets/fonts/glyphicons-halflings-regular.ttf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/assets/fonts/glyphicons-halflings-regular.ttf -------------------------------------------------------------------------------- /assets/fonts/glyphicons-halflings-regular.woff: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/assets/fonts/glyphicons-halflings-regular.woff -------------------------------------------------------------------------------- /assets/javascripts/scale.fix.js: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/assets/javascripts/scale.fix.js -------------------------------------------------------------------------------- /assets/stylesheets/pygment_trac.css: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/assets/stylesheets/pygment_trac.css -------------------------------------------------------------------------------- /assets/stylesheets/styles.css: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/assets/stylesheets/styles.css -------------------------------------------------------------------------------- /guidelines/cdx-non-get-requests/index.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/guidelines/cdx-non-get-requests/index.md -------------------------------------------------------------------------------- /guidelines/warc-fields/index.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/guidelines/warc-fields/index.md -------------------------------------------------------------------------------- /guidelines/warc-implementation-guidelines/index.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/guidelines/warc-implementation-guidelines/index.md -------------------------------------------------------------------------------- /index.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/index.md -------------------------------------------------------------------------------- /primers/web-archive-formats/cdx.unsorted.out: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/primers/web-archive-formats/cdx.unsorted.out -------------------------------------------------------------------------------- /primers/web-archive-formats/hello-world.txt: -------------------------------------------------------------------------------- 1 | --- 2 | layout: plaintext 3 | --- 4 | Hello World 5 | -------------------------------------------------------------------------------- /primers/web-archive-formats/hello-world.warc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/primers/web-archive-formats/hello-world.warc -------------------------------------------------------------------------------- /primers/web-archive-formats/hello-world.warc.cdx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/primers/web-archive-formats/hello-world.warc.cdx -------------------------------------------------------------------------------- /primers/web-archive-formats/hello-world.warc.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/primers/web-archive-formats/hello-world.warc.gz -------------------------------------------------------------------------------- /primers/web-archive-formats/index.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/primers/web-archive-formats/index.md -------------------------------------------------------------------------------- /specifications/cdx-format/cdx-2006/index.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/specifications/cdx-format/cdx-2006/index.md -------------------------------------------------------------------------------- /specifications/cdx-format/cdx-2015/index.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/specifications/cdx-format/cdx-2015/index.md -------------------------------------------------------------------------------- /specifications/warc-deduplication/recording-arbitrary-duplicates-1.0.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/specifications/warc-deduplication/recording-arbitrary-duplicates-1.0.md -------------------------------------------------------------------------------- /specifications/warc-deduplication/samples/20130729-heritrix-original.warc.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/specifications/warc-deduplication/samples/20130729-heritrix-original.warc.gz -------------------------------------------------------------------------------- /specifications/warc-deduplication/samples/20130729-heritrix-revisit-with-http-headers.warc.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/specifications/warc-deduplication/samples/20130729-heritrix-revisit-with-http-headers.warc.gz -------------------------------------------------------------------------------- /specifications/warc-deduplication/samples/20141124-heritrix-server-not-modified.warc.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/specifications/warc-deduplication/samples/20141124-heritrix-server-not-modified.warc.gz -------------------------------------------------------------------------------- /specifications/warc-deduplication/samples/20141129-heritrix-original.warc.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/specifications/warc-deduplication/samples/20141129-heritrix-original.warc.gz -------------------------------------------------------------------------------- /specifications/warc-deduplication/samples/20141129-heritrix-revisit-with-http-headers-and-new-warc-headers.warc.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/specifications/warc-deduplication/samples/20141129-heritrix-revisit-with-http-headers-and-new-warc-headers.warc.gz -------------------------------------------------------------------------------- /specifications/warc-format/meetings/2015-05-01-IIPC-GA-WARC-Meeting-Minutes.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/specifications/warc-format/meetings/2015-05-01-IIPC-GA-WARC-Meeting-Minutes.md -------------------------------------------------------------------------------- /specifications/warc-format/warc-1.0/The_WARC_Format.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/specifications/warc-format/warc-1.0/The_WARC_Format.md -------------------------------------------------------------------------------- /specifications/warc-format/warc-1.0/WARC_ISO_28500_version1_latestdraft.doc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/specifications/warc-format/warc-1.0/WARC_ISO_28500_version1_latestdraft.doc -------------------------------------------------------------------------------- /specifications/warc-format/warc-1.0/WARC_ISO_28500_version1_latestdraft.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/specifications/warc-format/warc-1.0/WARC_ISO_28500_version1_latestdraft.pdf -------------------------------------------------------------------------------- /specifications/warc-format/warc-1.0/index.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/specifications/warc-format/warc-1.0/index.md -------------------------------------------------------------------------------- /specifications/warc-format/warc-1.1-annotated/index.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/specifications/warc-format/warc-1.1-annotated/index.md -------------------------------------------------------------------------------- /specifications/warc-format/warc-1.1/index.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/specifications/warc-format/warc-1.1/index.md -------------------------------------------------------------------------------- /specifications/warc-rendered-targets/warc-rendered-targets-1.0.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/specifications/warc-rendered-targets/warc-rendered-targets-1.0.md -------------------------------------------------------------------------------- /specifications/warc-zstd/index.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iipc/warc-specifications/HEAD/specifications/warc-zstd/index.md --------------------------------------------------------------------------------