A robot-based procedure is described for traversing a collection of hyperlinked documents written in HTML and converting these to the XML-compliant and well-formed XHTML representation. Transcluded chemical content invoked using <embed> or <applet> HTML calls are converted to the XHTML recommended <object> form. Additional attributes such as title or derived chemical attributes such as a SMILES descriptor are added to improve the indexing of the resulting document collection. Conformance tests for the popular Web browsers are reported.
%0 Journal Article
%1 Gkoutos2001a
%A Gkoutos, Georgios V.
%A Kenway, Philip R.
%A Rzepa, Henry S.
%D 2001
%I American Chemical Society
%J Journal of Chemical Information and Computer Sciences
%K XHTML
%N 2
%P 253-258
%R doi: 10.1021/ci000396y
%T JChemTidy: A Tool for Converting Chemical Web Document Collections to an XHTML Representation
%V 41
%X A robot-based procedure is described for traversing a collection of hyperlinked documents written in HTML and converting these to the XML-compliant and well-formed XHTML representation. Transcluded chemical content invoked using <embed> or <applet> HTML calls are converted to the XHTML recommended <object> form. Additional attributes such as title or derived chemical attributes such as a SMILES descriptor are added to improve the indexing of the resulting document collection. Conformance tests for the popular Web browsers are reported.
@article{Gkoutos2001a,
abstract = {A robot-based procedure is described for traversing a collection of hyperlinked documents written in HTML and converting these to the XML-compliant and well-formed XHTML representation. Transcluded chemical content invoked using <embed> or <applet> HTML calls are converted to the XHTML recommended <object> form. Additional attributes such as title or derived chemical attributes such as a SMILES descriptor are added to improve the indexing of the resulting document collection. Conformance tests for the popular Web browsers are reported.},
added-at = {2011-12-21T01:05:11.000+0100},
author = {Gkoutos, Georgios V. and Kenway, Philip R. and Rzepa, Henry S.},
biburl = {https://www.bibsonomy.org/bibtex/2974539504860d8c43375602db27672e5/fairybasslet},
doi = {doi: 10.1021/ci000396y},
interhash = {0b8fd2931a628ff22ced75ef85ad781b},
intrahash = {974539504860d8c43375602db27672e5},
journal = {Journal of Chemical Information and Computer Sciences},
keywords = {XHTML},
number = 2,
pages = {253-258},
publisher = {American Chemical Society},
timestamp = {2019-03-11T21:06:37.000+0100},
title = {JChemTidy: A Tool for Converting Chemical Web Document Collections to an XHTML Representation},
volume = 41,
year = 2001
}