@inproceedings{barbaresi-2021-trafilatura,
title = "Trafilatura: {A} Web Scraping Library and Command-Line Tool for Text Discovery and Extraction",
author = "Barbaresi, Adrien",
editor = "Ji, Heng and
Park, Jong C. and
Xia, Rui",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstrations",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-demo.15/",
doi = "10.18653/v1/2021.acl-demo.15",
pages = "122--131",
abstract = "An essential operation in web corpus construction consists in retaining the desired content while discarding the rest. Another challenge finding one`s way through websites. This article introduces a text discovery and extraction tool published under open-source license. Its installation and use is straightforward, notably from Python and on the command-line. The software allows for main text, comments and metadata extraction, while also providing building blocks for web crawling tasks. A comparative evaluation on real-world data also shows its interest as well as the performance of other available solutions. The contributions of this paper are threefold: it references the software, features a benchmark, and provides a meaningful baseline for similar tasks. The tool performs significantly better than other open-source solutions in this evaluation and in external benchmarks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="barbaresi-2021-trafilatura">
<titleInfo>
<title>Trafilatura: A Web Scraping Library and Command-Line Tool for Text Discovery and Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adrien</namePart>
<namePart type="family">Barbaresi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jong</namePart>
<namePart type="given">C</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>An essential operation in web corpus construction consists in retaining the desired content while discarding the rest. Another challenge finding one‘s way through websites. This article introduces a text discovery and extraction tool published under open-source license. Its installation and use is straightforward, notably from Python and on the command-line. The software allows for main text, comments and metadata extraction, while also providing building blocks for web crawling tasks. A comparative evaluation on real-world data also shows its interest as well as the performance of other available solutions. The contributions of this paper are threefold: it references the software, features a benchmark, and provides a meaningful baseline for similar tasks. The tool performs significantly better than other open-source solutions in this evaluation and in external benchmarks.</abstract>
<identifier type="citekey">barbaresi-2021-trafilatura</identifier>
<identifier type="doi">10.18653/v1/2021.acl-demo.15</identifier>
<location>
<url>https://aclanthology.org/2021.acl-demo.15/</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>122</start>
<end>131</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Trafilatura: A Web Scraping Library and Command-Line Tool for Text Discovery and Extraction
%A Barbaresi, Adrien
%Y Ji, Heng
%Y Park, Jong C.
%Y Xia, Rui
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstrations
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F barbaresi-2021-trafilatura
%X An essential operation in web corpus construction consists in retaining the desired content while discarding the rest. Another challenge finding one‘s way through websites. This article introduces a text discovery and extraction tool published under open-source license. Its installation and use is straightforward, notably from Python and on the command-line. The software allows for main text, comments and metadata extraction, while also providing building blocks for web crawling tasks. A comparative evaluation on real-world data also shows its interest as well as the performance of other available solutions. The contributions of this paper are threefold: it references the software, features a benchmark, and provides a meaningful baseline for similar tasks. The tool performs significantly better than other open-source solutions in this evaluation and in external benchmarks.
%R 10.18653/v1/2021.acl-demo.15
%U https://aclanthology.org/2021.acl-demo.15/
%U https://doi.org/10.18653/v1/2021.acl-demo.15
%P 122-131
Markdown (Informal)
[Trafilatura: A Web Scraping Library and Command-Line Tool for Text Discovery and Extraction](https://aclanthology.org/2021.acl-demo.15/) (Barbaresi, ACL-IJCNLP 2021)
ACL