%0 Conference Paper %1 oai:CiteSeerPSU:65077 %A Eichmann, David %D 1994 %I First World Wide Web Conference, Geneva, Switzerland %K searchengine www03 wwwbook wwwkap17 %T The RBSE Spider - Balancing Effective Search Against Web Load %X The design of a Web spider entails many things, including a concern for reasonable behavior, as well as more technical concerns. The RBSE Spider is a mechanism for exploring World Wide Web structure and indexing useful material thereby discovered. We relate our experience in constructing and operating this spider. 1 -- Introduction As the World Wide Web 3 increases in complexity and number of users, it will be increasingly difficult for users to find information. Recent statistics posted by Fletcher 6, McBryan 12 and others indicate that there are more than 100,000 artifacts now Web-accessible. Relying solely upon browsing of hyperlinks or hand-crafted indices to gain access to specific topics is intractable. This paper describes our experience with constructing a spider as part of our work on the Repository Based Software Engineering (RBSE) project. Web spiders are programs that traverse the Web, acting in some manner upon the information thereby uncovered. The RBSE spider disc... %Z David Eichmann (Repository Based Software Engineering Program; Research Institute for Computing and Information Systems; University of Houston -- Clear Lake);

@inproceedings{oai:CiteSeerPSU:65077, abstract = {The design of a Web spider entails many things, including a concern for reasonable behavior, as well as more technical concerns. The RBSE Spider is a mechanism for exploring World Wide Web structure and indexing useful material thereby discovered. We relate our experience in constructing and operating this spider. 1 -- Introduction As the World Wide Web [3] increases in complexity and number of users, it will be increasingly difficult for users to find information. Recent statistics posted by Fletcher [6], McBryan [12] and others indicate that there are more than 100,000 artifacts now Web-accessible. Relying solely upon browsing of hyperlinks or hand-crafted indices to gain access to specific topics is intractable. This paper describes our experience with constructing a spider as part of our work on the Repository Based Software Engineering (RBSE) project. Web spiders are programs that traverse the Web, acting in some manner upon the information thereby uncovered. The RBSE spider disc...}, added-at = {2008-12-05T15:39:31.000+0100}, annote = {David Eichmann (Repository Based Software Engineering Program; Research Institute for Computing and Information Systems; University of Houston -- Clear Lake);}, author = {Eichmann, David}, bibsource = {OAI-PMH server at cs1.ist.psu.edu}, biburl = {https://www.bibsonomy.org/bibtex/2bd313c5c60eec988cb5ff41b2e321463/lysander07}, interhash = {415fbb8fb5de341b73d793f712b5c2ab}, intrahash = {bd313c5c60eec988cb5ff41b2e321463}, keywords = {searchengine www03 wwwbook wwwkap17}, language = {en}, month = {April~20}, oai = {oai:CiteSeerPSU:65077}, publisher = {First World Wide Web Conference, Geneva, Switzerland}, rights = {unrestricted}, timestamp = {2009-01-27T15:24:50.000+0100}, title = {The {RBSE} Spider - Balancing Effective Search Against Web Load}, year = 1994 }