A handy parsing HTML tool--JSOUP__JS

http://www.open-open.com/jsoup/

Using the syntax like jquery, it's easy to use.

Java Sample code: http://www.open-open.com/jsoup/example-list-links.htm

Package org.jsoup.examples; Import Org.jsoup.Jsoup; Import Org.jsoup.helper.Validate; Import org.jsoup.nodes.Document; Import org.jsoup.nodes.Element; Import org.jsoup.select.Elements; Import java.io.IOException; /** * Example program to list links from a URL. */public class Listlinks {public static void main (string[] args) throws IOException {validate.istrue (ARGS.L Ength = = 1, "Usage:supply URL to fetch"); String URL = args[0]; Print ("Fetching%s ...", url); Document doc = jsoup.connect (URL). get (); Elements links = doc.select ("a[href]"); Elements media = doc.select ("[src]"); Elements imports = Doc.select ("link[href]"); Print ("\nmedia: (%d)", media.size ()); for (Element Src:media) {if (Src.tagname (). Equals ("img")) Print ("*%s: <%s>%sx%s" (% s) ", Src.tagname (), Src.attr (" Abs:src "), src.attr (" width "), src.attr (" height "), Trim (src.attr ("Alt"), 20)); else print ("*%s: <%s>", Src.tagname (), Src.attr ("abs:src")); Print ("\nimports: (%d)", imports.size ()); for (Element link:imports) {print ("*%s <%s> (%s)", Link.tagname (), Link.attr ("Abs:href"), Link.attr ( "rel")); Print ("\nlinks: (%d)", links.size ()); for (Element link:links) {print ("* A: <%s> (%s)", Link.attr ("Abs:href"), Trim (Link.text (), 35)); }} private static void print (String msg, Object ... args) {System.out.println (msg, args)); private static String trim (string s, int width) {if (S.length () > width) return s.substring (0, Width-1) + "."; else return s; } }