@techreport{kunze-warc-00, number = {draft-kunze-warc-00}, type = {Internet-Draft}, institution = {Internet Engineering Task Force}, publisher = {Internet Engineering Task Force}, note = {Work in Progress}, url = {https://datatracker.ietf.org/doc/draft-kunze-warc/00/}, author = {John A. Kunze and Gordon Mohr and Michael Stack}, title = {{The WARC File Format (Version 0.16)}}, pagetotal = 40, year = 2008, month = jul, day = 5, abstract = {The WARC (Web ARChive) format specifies a method for combining multiple digital resources into an aggregate archival file together with related information. Resources are dated, identified by URIs, and preceded by simple text headers. By convention, files of this format are named with the extension ".warc" and have the MIME type application/warc. The WARC file format is a revision and generalization of the ARC format used by the Internet Archive to store information blocks harvested by web crawlers. This document specifies version 0.16 of the WARC format.}, }