@electronic{code.google.com,
   title       = {boilerpipe - Project Hosting on Google Code}, 
   url         = {http://code.google.com/p/boilerpipe/},
   biburl      = {https://puma.uni-kassel.de/url/e66c472e3fa3a0af975c503d14a0f599/benz},
   keywords    = {boilerpipe extract free googlecode html java lib library software text_extraction text_processing tool webpage},
   added-at    = {2011-02-04T16:06:58.000+0100},
   description = {The boilerpipe library provides algorithms to detect and remove the surplus "clutter" (boilerplate, templates) around the main textual content of a web page.The library already provides specific strategies for common tasks (for example: news article extraction) and may also be easily extended for individual problem settings.Extracting content is very fast (milliseconds), just needs the input document (no global or site-level information required) and is usually quite accurate.Boilerpipe is a Java library written by Christian Kohlschütter. It is released under the Apache License 2.0. },
   interhash   = {e66c472e3fa3a0af975c503d14a0f599}, 
   intrahash   = {e66c472e3fa3a0af975c503d14a0f599}
}