DOM-based content extraction of HTML documents.

@inproceedings{gupta-2003-dombased, author = {Suhit Gupta and Gail E. Kaiser and David Neistadt and Peter Grimm}, editor = {Guszt\'{a}v Hencsey and Bebo White and Yih-Farn Robin Chen and L\'{a}szl\'{o} Kov\'{a}cs and Steve Lawrence}, title = {{DOM-based content extraction of HTML documents}}, booktitle = {{Proceedings of the Twelfth International World Wide Web Conference, WWW 2003, Budapest, Hungary, May 20-24, 2003}}, pages = {207--214}, publisher = {ACM}, year = {2003}, url = {https://doi.org/10.1145/775152.775182}, doi = {https://doi.org/10.1145/775152.775182} }