public class LinkExtractor
extends java.lang.Object
Modifier and Type | Field and Description |
---|---|
private java.util.regex.Pattern |
blackpattern |
private static char |
dquotes |
private static char |
lb |
private java.util.WeakHashMap<MultiProtocolURL,java.lang.Object> |
links |
private static java.lang.Object |
PRESENT |
private static char |
rb |
private static char |
space |
Constructor and Description |
---|
LinkExtractor(java.util.regex.Pattern blackpattern) |
Modifier and Type | Method and Description |
---|---|
private static int |
find(java.lang.String s,
java.lang.String m,
int start) |
MultiProtocolURL[] |
getLinks()
return the links in the text in the order as they appear
|
void |
scrape(java.lang.String text) |
private static final char lb
private static final char rb
private static final char dquotes
private static final char space
private static final java.lang.Object PRESENT
private java.util.WeakHashMap<MultiProtocolURL,java.lang.Object> links
private java.util.regex.Pattern blackpattern
public void scrape(java.lang.String text)
public MultiProtocolURL[] getLinks()
private static final int find(java.lang.String s, java.lang.String m, int start)