Jsoup parsing and traversing an HTML document (ii)

About the font adjustments in the Eclipse Editor Rollup console:

1. Download the Jsoup jar package: Http://jsoup.org/download

2, Jsoup Development Handbook for English: http://jsoup.org/cookbook/

3,jsoup Jsoup Cookbook Chinese version: http://www.open-open.com/jsoup/

-                     - -                     - -                &N Bsp    - -                     - -    and nbsp                - -                &N Bsp    - -               -            & nbsp        - 

-                      - -                      - -                      - -                      - - - -                      - -                -                      -

Small instance:

1  Packagecn.cast.test;2 3 4 5 ImportOrg.jsoup.Jsoup;6 Importorg.jsoup.nodes.Document;7 Importorg.jsoup.nodes.Element;8 Importorg.jsoup.select.Elements;9 Ten  One Importjava.io.IOException; A  - ImportOrg.jsoup.Jsoup; - ImportOrg.jsoup.Jsoup; the Importorg.jsoup.nodes.Document; - Importorg.jsoup.nodes.Element; - Importorg.jsoup.select.Elements; -  +  -  Public classtest_1 { +  A      Public Static voidMain (string[] args) { at         //TODO auto-generated Method Stub - geturlandtitle (); - gettextmes (); -     } -      -      Public Static voidGeturlandtitle () in     { -String url= "http://finance.sina.com.cn/"; to         Try { +Document doc=jsoup.connect (URL). Timeout (10000). get ();//get all infomation from URL website -             //System.out.println (DOC);  theElements Listdiv = Doc.getelementsbyattributevalue ("Class", "fin_tabs0_c0"); *             //System.out.println (listdiv); $              for(Element div:listdiv) {Panax NotoginsengElements links = Div.getelementsbytag ("a"); -                 //System.out.println (links); the                   for(Element link:links) { +String linkhref = link.attr ("href"). Trim (); AString LinkText =link.text (). Trim (); theSystem.out.println (linkhref+ "\ T" +linkText); +                  }     -              } $}Catch(IOException e) { $             //TODO auto-generated Catch block - e.printstacktrace (); -         } the     } -     Wuyi      Public Static voidgettextmes () the     { -String url= "http://finance.sina.com.cn/hy/20140823/100220099682.shtml"; WuString textmes= ""; -         Try { AboutDocument doc=jsoup.connect (URL). Timeout (10000). get (); $Elements Listdiv = Doc.getelementsbyattributevalue ("Class", "Blkcontainersblkcon Bshare_pop"); -             //System.out.println (listdiv); -              for(Element div:listdiv) -             { AElements Textinfos=div.getelementsbytag ("P"); +                 //System.out.println (Textinfos); the                  for(Element Textinfo:textinfos) -                 { $String text=textinfo.text (). Trim (); theTextmes=textmes+text+ "\ n"; the                 } the             } the System.out.println (textmes); -}Catch(IOException e) { in             //TODO auto-generated Catch block the e.printstacktrace (); the         } About     } the}

test_1

Jsoup parsing and traversing an HTML document (ii)