The Invisible Web: Uncovering Information Sources Search Engines Can't See Export

@book{Sherman2001:InvisibleWeb, abstract = {{Enormous expanses of the Internet are unreachable with standard Web search engines. This book provides the key to finding these hidden resources by identifying how to uncover and use invisible Web resources. Mapping the invisible Web, when and how to use it, assessing the validity of the information, and the future of Web searching are topics covered in detail. Only 16 percent of Net-based information can be located using a general search engine. The other 84 percent is what is referred to as the invisible Web-made up of information stored in databases. Unlike pages on the visible Web, information in databases is generally inaccessible to the software spiders and crawlers that compile search engine indexes. As Web technology improves, more and more information is being stored in databases that feed into dynamically generated Web pages. The tips provided in this resource will ensure that those databases are exposed and Net-based research will be conducted in the most thorough and effective manner.}}, author = {Price, Gary and Sherman, Chris}, citeulike-article-id = {297327}, citeulike-linkout-0 = {http://www.amazon.ca/exec/obidos/redirect?tag=citeulike09-20&path=ASIN/091096551X}, citeulike-linkout-1 = {http://www.amazon.de/exec/obidos/redirect?tag=citeulike01-21&path=ASIN/091096551X}, citeulike-linkout-2 = {http://www.amazon.fr/exec/obidos/redirect?tag=citeulike06-21&path=ASIN/091096551X}, citeulike-linkout-3 = {http://www.amazon.jp/exec/obidos/ASIN/091096551X}, citeulike-linkout-4 = {http://www.amazon.co.uk/exec/obidos/ASIN/091096551X/citeulike00-21}, citeulike-linkout-5 = {http://www.amazon.com/exec/obidos/redirect?tag=citeulike07-20&path=ASIN/091096551X}, citeulike-linkout-6 = {http://www.worldcat.org/isbn/091096551X}, citeulike-linkout-7 = {http://books.google.com/books?vid=ISBN091096551X}, citeulike-linkout-8 = {http://www.amazon.com/gp/search?keywords=091096551X&index=books&linkCode=qs}, citeulike-linkout-9 = {http://www.librarything.com/isbn/091096551X}, comment = {p. 61 lists types of invisible web content: 1) disconnect pages 2) Page consisting primarily of images, audio, or video 3) Pages consisting primarily of PDF, PS, Flash, exe, compressed files (tar, zip) 4) Content in relational databases 5) Real-time content 6) Dynamically generated content Of course, this book is somewhat outdated. Google has crawled PDF and PS for some time and now crawls Flash.}, day = {01}, edition = {1}, howpublished = {Paperback}, isbn = {091096551X}, keywords = {deep-web}, month = {July}, posted-at = {2008-07-14 22:46:46}, priority = {2}, publisher = {Information Today, Inc.}, title = {The Invisible Web: Uncovering Information Sources Search Engines Can't See}, url = {http://www.amazon.com/exec/obidos/redirect?tag=citeulike07-20&path=ASIN/091096551X}, year = {2001} }

TY - BOOK ID - Sherman2001:InvisibleWeb L3 - citeulike-article-id:297327 N2 - {Enormous expanses of the Internet are unreachable with standard Web search engines. This book provides the key to finding these hidden resources by identifying how to uncover and use invisible Web resources. Mapping the invisible Web, when and how to use it, assessing the validity of the information, and the future of Web searching are topics covered in detail. Only 16 percent of Net-based information can be located using a general search engine. The other 84 percent is what is referred to as the invisible Web-made up of information stored in databases. Unlike pages on the visible Web, information in databases is generally inaccessible to the software spiders and crawlers that compile search engine indexes. As Web technology improves, more and more information is being stored in databases that feed into dynamically generated Web pages. The tips provided in this resource will ensure that those databases are exposed and Net-based research will be conducted in the most thorough and effective manner.} SN - 091096551X TI - The Invisible Web: Uncovering Information Sources Search Engines Can't See PB - Information Today, Inc. KW - deep-web N1 - p. 61 lists types of invisible web content: 1) disconnect pages 2) Page consisting primarily of images, audio, or video 3) Pages consisting primarily of PDF, PS, Flash, exe, compressed files (tar, zip) 4) Content in relational databases 5) Real-time content 6) Dynamically generated content Of course, this book is somewhat outdated. Google has crawled PDF and PS for some time and now crawls Flash. AU - Price, Gary AU - Sherman, Chris PY - 2001/07/01/ UR - http://www.amazon.ca/exec/obidos/redirect?tag=citeulike09-20&path=ASIN/091096551X ER -