@inproceedings{7649919cca924650a00f742982f89538,
title = "Effective web data extraction with Ducky",
abstract = "The World Wide Web has become an invaluable source of data. However, extracting useful information from the vastness of the web can become a challenge as depending on the amount of data needed, manual extraction or creation of web scraping programs may be necessary. These processes can be tedious and complicated. To address these, Ducky, a web wrapper that extracts data from web sources and translates them into structured data based on a user-defined configuration, has been developed. Ducky is able to extract data flexibly from various structured web pages, remove noise from extracted data and integrate multiple pages from different sites. In addition, the current version of Ducky automatically extracts data from Wikipedia and trendy keywords of Google and Yahoo.",
keywords = "CSS selector, Data extraction, Web scraping, Web wrapper",
author = "Kei Kanaoka and Motomichi Toyama",
year = "2015",
month = jul,
day = "13",
doi = "10.1145/2790755.2790787",
language = "English",
series = "ACM International Conference Proceeding Series",
publisher = "Association for Computing Machinery",
number = "CONFCODENUMBER",
pages = "212--213",
editor = "Desai, {Bipin C.} and Motomichi Toyama",
booktitle = "ACM International Conference Proceeding Series",
edition = "CONFCODENUMBER",
note = "19th International Database Engineering and Applications Symposium, IDEAS 2015 ; Conference date: 13-07-2015 Through 15-07-2015",
}