[{"data":1,"prerenderedAt":35},["ShallowReactive",2],{"maker-jlink":3},[4],{"id":5,"name":6,"line":7,"ai":8,"cat":9,"year":10,"points":11,"comments":12,"rec":13,"s":14,"top":15,"kw":16,"maker":22,"domain":23,"tier":24,"attempts":25,"strip":26,"url":27,"mix":28,"praise":32,"objection":33,"sub":34},13729301,"PDFLayoutTextStripper","Converts PDF to text while keeping the layout",false,"data",2017,283,92,"curious",0.03,4,[17,18,19,20,21],"pdf to text","pdf layout","pdfbox","text extraction","java library","jlink","github.com","legend",0,"1000300000000055533033333310000013554531","https:\u002F\u002Fgithub.com\u002FJonathanLink\u002FPDFLayoutTextStripper",[29,30,25,31],8,16,6,"PDFBox is a solid base for PDF parsing","PDF text extraction is inherently hard and copy-paste from PDF often yields garbage","pdf text extraction",1794036750873]