%0 Journal Article %1 Laender2002 %A Laender, Alberto H. F. %A Ribeiro-Neto, Berthier A. %A da Silva, Altigran S. %A Teixeira, Juliana S. %C New York, NY, USA %D 2002 %I ACM Press %J SIGMOD Rec. %K db information_extraction survey %N 2 %P 84--93 %R http://dx.doi.org/10.1145/565117.565137 %T A brief survey of web data extraction tools %U http://dx.doi.org/10.1145/565117.565137 %V 31 %X In the last few years, several works in the literature have addressed the problem of data extraction from Web pages. The importance of this problem derives from the fact that, once extracted, the data can be handled in a way similar to instances of a traditional database. The approaches proposed in the literature to address the problem of Web data extraction use techniques borrowed from areas such as natural language processing, languages and grammars, machine learning, information retrieval, databases, and ontologies. As a consequence, they present very distinct features and capabilities which make a direct comparison difficult to be done. In this paper, we propose a taxonomy for characterizing Web data extraction fools, briefly survey major Web data extraction tools described in the literature, and provide a qualitative analysis of them. Hopefully, this work will stimulate other studies aimed at a more comprehensive analysis of data extraction approaches and tools for Web data.

@article{Laender2002, abstract = {In the last few years, several works in the literature have addressed the problem of data extraction from Web pages. The importance of this problem derives from the fact that, once extracted, the data can be handled in a way similar to instances of a traditional database. The approaches proposed in the literature to address the problem of Web data extraction use techniques borrowed from areas such as natural language processing, languages and grammars, machine learning, information retrieval, databases, and ontologies. As a consequence, they present very distinct features and capabilities which make a direct comparison difficult to be done. In this paper, we propose a taxonomy for characterizing Web data extraction fools, briefly survey major Web data extraction tools described in the literature, and provide a qualitative analysis of them. Hopefully, this work will stimulate other studies aimed at a more comprehensive analysis of data extraction approaches and tools for Web data.}, added-at = {2009-03-12T15:42:50.000+0100}, address = {New York, NY, USA}, author = {Laender, Alberto H. F. and Ribeiro-Neto, Berthier A. and da Silva, Altigran S. and Teixeira, Juliana S.}, biburl = {https://www.bibsonomy.org/bibtex/206a6d87797d4e98dcbe610d3214c33de/lillejul}, citeulike-article-id = {1111013}, doi = {http://dx.doi.org/10.1145/565117.565137}, interhash = {92cdfc3f27b81b09375ec9524eff07e0}, intrahash = {06a6d87797d4e98dcbe610d3214c33de}, issn = {0163-5808}, journal = {SIGMOD Rec.}, keywords = {db information_extraction survey}, month = {June}, number = 2, pages = {84--93}, posted-at = {2007-12-20 19:58:25}, priority = {4}, publisher = {ACM Press}, timestamp = {2009-04-22T10:29:38.000+0200}, title = {A brief survey of web data extraction tools}, url = {http://dx.doi.org/10.1145/565117.565137}, volume = 31, year = 2002 }