@inproceedings{HamborgMBG17,
	address = {Berlin},
	title = {news-please: {A} {Generic} {News} {Crawler} and {Extractor}},
	url = {paper=https://www.gipp.com/wp-content/papercite-data/pdf/hamborg2017.pdf code=https://github.com/fhamborg/news-please},
	doi = {10.18452/1447},
	abstract = {The amount of news published and read online has increased tremendously in recent years, making news data an interesting resource for many research dis-ciplines, such as the social sciences and linguistics. However, large scale col-lection of news data is cumbersome due to a lack of generic tools for crawling and extracting such data. We present news-please, a generic, multi-language, open-source crawler and extractor for news that works out-of-the-box for a large variety of news websites. Our system allows crawling arbitrary news websites and extracting the major elements of news articles on those websites, i.e., title, lead paragraph, main content, publication date, author, and main im-age. Compared to existing tools, news-please features full website extraction requiring only the root URL.},
	booktitle = {Proceedings of the 15th {International} {Symposium} of {Information} {Science}},
	author = {Hamborg, Felix and Meuschke, Norman and Breitinger, Corinna and Gipp, Bela},
	editor = {Gaede, Maria and Trkulja, Violeta and Petra, Vivien},
	month = mar,
	year = {2017},
	keywords = {News Analysis},
	pages = {218--223},
}

{"_id":"m8cpSiqhYRYgbf3t2","bibbaseid":"hamborg-meuschke-breitinger-gipp-newspleaseagenericnewscrawlerandextractor-2017","authorIDs":["3aamy24wTzcQoTPGY","7Crs4B84W7BbduMmq","97o4RCsEFAoSxEQqt","9dzP7gNRTLKvc9aPR","GYqCNzAZv2xc9nhmD","KLLNwF6yrTvRfDhAP","LKQ5pS2Y8Pc7FTkr7","TuCkHmKovwKzF3y8Z","ZDet9tokdva7KFSEH","ZJvJiH6kd887XEnz3","gBWY7RvNrDhhspCGi","nLJ4c698vfAyWRWTr","pCb6WupcebiMmhw8Y","qNrPNpAwKg5fp598G","s7Z2R2uTWDHRHN2bE","tFwG3DWb6fYeXs3sL","yiM4TojQ7StGdi2iD"],"author_short":["Hamborg, F.","Meuschke, N.","Breitinger, C.","Gipp, B."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","address":"Berlin","title":"news-please: A Generic News Crawler and Extractor","doi":"10.18452/1447","abstract":"The amount of news published and read online has increased tremendously in recent years, making news data an interesting resource for many research dis-ciplines, such as the social sciences and linguistics. However, large scale col-lection of news data is cumbersome due to a lack of generic tools for crawling and extracting such data. We present news-please, a generic, multi-language, open-source crawler and extractor for news that works out-of-the-box for a large variety of news websites. Our system allows crawling arbitrary news websites and extracting the major elements of news articles on those websites, i.e., title, lead paragraph, main content, publication date, author, and main im-age. Compared to existing tools, news-please features full website extraction requiring only the root URL.","booktitle":"Proceedings of the 15th International Symposium of Information Science","author":[{"propositions":[],"lastnames":["Hamborg"],"firstnames":["Felix"],"suffixes":[]},{"propositions":[],"lastnames":["Meuschke"],"firstnames":["Norman"],"suffixes":[]},{"propositions":[],"lastnames":["Breitinger"],"firstnames":["Corinna"],"suffixes":[]},{"propositions":[],"lastnames":["Gipp"],"firstnames":["Bela"],"suffixes":[]}],"editor":[{"propositions":[],"lastnames":["Gaede"],"firstnames":["Maria"],"suffixes":[]},{"propositions":[],"lastnames":["Trkulja"],"firstnames":["Violeta"],"suffixes":[]},{"propositions":[],"lastnames":["Petra"],"firstnames":["Vivien"],"suffixes":[]}],"month":"March","year":"2017","keywords":"News Analysis","pages":"218–223","bibtex":"@inproceedings{HamborgMBG17,\n\taddress = {Berlin},\n\ttitle = {news-please: {A} {Generic} {News} {Crawler} and {Extractor}},\n\turl = {paper=https://www.gipp.com/wp-content/papercite-data/pdf/hamborg2017.pdf code=https://github.com/fhamborg/news-please},\n\tdoi = {10.18452/1447},\n\tabstract = {The amount of news published and read online has increased tremendously in recent years, making news data an interesting resource for many research dis-ciplines, such as the social sciences and linguistics. However, large scale col-lection of news data is cumbersome due to a lack of generic tools for crawling and extracting such data. We present news-please, a generic, multi-language, open-source crawler and extractor for news that works out-of-the-box for a large variety of news websites. Our system allows crawling arbitrary news websites and extracting the major elements of news articles on those websites, i.e., title, lead paragraph, main content, publication date, author, and main im-age. Compared to existing tools, news-please features full website extraction requiring only the root URL.},\n\tbooktitle = {Proceedings of the 15th {International} {Symposium} of {Information} {Science}},\n\tauthor = {Hamborg, Felix and Meuschke, Norman and Breitinger, Corinna and Gipp, Bela},\n\teditor = {Gaede, Maria and Trkulja, Violeta and Petra, Vivien},\n\tmonth = mar,\n\tyear = {2017},\n\tkeywords = {News Analysis},\n\tpages = {218--223},\n}\n\n","author_short":["Hamborg, F.","Meuschke, N.","Breitinger, C.","Gipp, B."],"editor_short":["Gaede, M.","Trkulja, V.","Petra, V."],"urlpaper":"https://www.gipp.com/wp-content/papercite-data/pdf/hamborg2017.pdf","urlcode":"https://github.com/fhamborg/news-please","key":"HamborgMBG17","id":"HamborgMBG17","bibbaseid":"hamborg-meuschke-breitinger-gipp-newspleaseagenericnewscrawlerandextractor-2017","role":"author","urls":{"Paper":"https://www.gipp.com/wp-content/papercite-data/pdf/hamborg2017.pdf","Code":"https://github.com/fhamborg/news-please"},"keyword":["News Analysis"],"metadata":{"authorlinks":{"meuschke, n":"https://bibbase.org/show?bib=https%3A%2F%2Fapi.zotero.org%2Fgroups%2F2532143%2Fitems%3Fkey%3DDOjJ33bOgISaFjBIBr7jCV5S%26format%3Dbibtex%26limit%3D100"}},"downloads":0},"bibtype":"inproceedings","biburl":"https://api.zotero.org/groups/2532143/items?key=DOjJ33bOgISaFjBIBr7jCV5S&format=bibtex&limit=100","creationDate":"2020-04-15T13:02:33.686Z","downloads":0,"keywords":["news analysis"],"search_terms":["news","please","generic","news","crawler","extractor","hamborg","meuschke","breitinger","gipp"],"title":"news-please: A Generic News Crawler and Extractor","year":2017,"dataSources":["aEHCfX6B2taJt8dfa","9qTaLWxMN5hLpMP8m","xteq4cdC6ATE2G6Fg","JNgeyAG2vQ8k88oYh","FPjHiAkAja6XvmScK","RTGAqwGfLTSqYQMsS","Y7kZGjoN5Erk3Lo2J","yM7MefT3mRkY9m7i4","jnWJCpbQCoWvxj9kz","F32umBkhFrpeJbp7A","BWzEyLkMvdMGpHpr6","e3AdWzdxYmb85Fn5D","MtqPmSRuq4X8FJqNT","YCwvFifyPbazBYMQD","6oZMeYhGKA2Mp8xhF","gYMS6DBXsNosXKcRC","bQwdfx3o8Q3vnsqfH","SzFkcrpurPzNHEyqX","6KJgnNtYZiwwFkcGq","dHLtmS5G7GmooD755","EvZZTzAZvA3EsuMjm"]}