[{"_1":2,"_64":-5,"_65":-5},"loaderData",{"_3":4,"_33":34,"_62":-5,"_63":-5},"root",{"_5":-5,"_6":-5,"_7":8,"_20":-5,"_21":22,"_23":24,"_27":28},"user","shoppingCartId","shoppingCart",{"_9":10,"_11":12,"_13":14,"_15":16,"_17":18,"_19":12},"count",0,"free",true,"updatedAt","2026-01-03T06:14:08.626Z","paymentGateway","STRIPE","cartItems",[],"loading","toast","locale","en","constants",{"_25":26},"paypalClientId","AX53Cwz8jR6rVVzzZiZNWWXl0dGagi-GZrjG-S3Ua14E5nrKMn7DxDQ730O4R8LusLPp49ALn6aRVaEy","publishers",{"_29":30,"_31":32},"companies",[],"universities",[],"routes/_store+/_readers+/email_author.$slug/route",{"_35":36,"_61":-5},"book",{"_37":38,"_39":40,"_41":42,"_43":44,"_45":46,"_47":48},"id","Z2lkOi8vbGVhbnB1Yi9TdG9yZTo6Qm9va1Byb2R1Y3QvMTQ2NDE","title","XML processing and website scraping in Java","state","retired","contactAuthorMethod","email","aboutText","

This book is about XML and HTML processing in the Java world.

First I tell you how I got to this topic and how I learned about XMLBeam and JSoup.

This book is practical: I have a lot of sample code in it and you can use it as a tutorial for XMLBeam and JSoup. However the documentation of those two frameworks should be read too.

I talk in this book about XML converting on the Google App Engine (to PDF, RTF, DocX, HTML), create a website scraper with JSoup and XMLBeam to compare the performance of them both.

And at the end I show how you can customize the toString option of both frameworks.

","authors",[49],{"_37":50,"_51":52,"_5":53},"Z2lkOi8vbGVhbnB1Yi9TdG9yZTo6UHJvZHVjdEF1dGhvci8xNTI2Ng","name","Gábor László Hajba",{"_54":55},"avatar",{"_56":57,"_58":59,"_60":12},"url","https://d39qdlcrvnra4b.cloudfront.net/avatars/374589/medium/GHajba_PL_small.jpg?1688453610","styleName","medium","exists","currentUser","routes/_store+/_layout","routes/_store+/_readers+/_layout","actionData","errors"]

Email the Author