@inproceedings{d1226adfe5cd43abb8b4c351cf87fe0a,
title = "Universal web pages content parser",
abstract = "This article describes the universal web pages content parser - cross-platform application enhancing the process of data extraction from the web pages. In this implementation user friendly interface, possibility of significant automation and reusability of already created patterns had been the key elements. Moreover, the original approach to the issue of parsing the not well-formed HTML, stating the application's core, is precisely presented. Universal web pages content parser shows that the simplified web scrapping utility may be available to masses and not well-formed HTML sources may feed useful tree-like data structures as well as the well-formed ones.",
keywords = "HTML, XML, content parser, web",
author = "Piotr Pawlas and Adam Doma{\'n}ski and Joanna Doma{\'n}ska",
year = "2012",
doi = "10.1007/978-3-642-31217-5\_14",
language = "English",
isbn = "9783642312168",
series = "Communications in Computer and Information Science",
pages = "130--138",
booktitle = "Computer Networks - 19th International Conference, CN 2012, Proceedings",
note = "19th International Conference on Computer Networks, CN 2012 ; Conference date: 19-06-2012 Through 23-06-2012",
}