%0 Conference Paper %1 sun08 %A Sun, Yang %A Councill, Isaac G. %A Giles, C. Lee %B Proceedings of the 8th International Conference on Web Engineering %C Yorktown Heights, NY %D 2008 %K imported %T BotSeer: An Automated Information System for Analyzing Web Robots %X Robots.txt files are vital to the web since they are supposed to regulate what search engines can and cannot crawl. We present BotSeer, a Web-based information system and search tool that provides resources and services for researching Web robots and trends in Robot Exclusion Protocol deployment and adherence. BotSeer currently indexes and analyzes 2.2 million robots.txt files obtained from 13.2 million websites, as well as a large Web server log of real-world robot behavior and related analyses. BotSeer provides three major services including robots.txt searching, robot bias analysis, and robot-generated log analysis. BotSeer serves as a resource for studying the regulation and behavior of Web robots as well as a tool to inform the creation of effective robots.txt files and crawler implementations.

@inproceedings{sun08, abstract = {Robots.txt files are vital to the web since they are supposed to regulate what search engines can and cannot crawl. We present BotSeer, a Web-based information system and search tool that provides resources and services for researching Web robots and trends in Robot Exclusion Protocol deployment and adherence. BotSeer currently indexes and analyzes 2.2 million robots.txt files obtained from 13.2 million websites, as well as a large Web server log of real-world robot behavior and related analyses. BotSeer provides three major services including robots.txt searching, robot bias analysis, and robot-generated log analysis. BotSeer serves as a resource for studying the regulation and behavior of Web robots as well as a tool to inform the creation of effective robots.txt files and crawler implementations.}, added-at = {2009-01-14T00:43:43.000+0100}, address = {Yorktown Heights, NY}, author = {Sun, Yang and Councill, Isaac G. and Giles, C. Lee}, biburl = {https://www.bibsonomy.org/bibtex/2db8b4fb6420e9b1b203929fb30297872/dret}, booktitle = {Proceedings of the 8th International Conference on Web Engineering}, crossref = {icwe2008}, description = {dret'd bibliography}, interhash = {d3fdd6084b4586863c237b716ef2e86c}, intrahash = {db8b4fb6420e9b1b203929fb30297872}, keywords = {imported}, month = {July}, timestamp = {2009-01-14T00:43:55.000+0100}, title = {BotSeer: An Automated Information System for Analyzing Web Robots}, uri = {http://botseer.ist.psu.edu/sun-botseer.pdf}, year = 2008 }