public abstract class AbstractScraper extends java.lang.Object implements Scraper
Modifier and Type | Field and Description |
---|---|
protected static java.lang.String |
EMPTY_STRING |
static char |
lb |
static char |
rb |
static char |
sl |
static char |
sp |
private java.util.Set<java.lang.String> |
tags0 |
private java.util.Set<java.lang.String> |
tags1 |
Constructor and Description |
---|
AbstractScraper(java.util.Set<java.lang.String> tags0,
java.util.Set<java.lang.String> tags1)
create a scraper.
|
Modifier and Type | Method and Description |
---|---|
protected static java.lang.String |
cleanLine(java.lang.String s) |
void |
close() |
boolean |
isTag0(java.lang.String tag) |
boolean |
isTag1(java.lang.String tag) |
static void |
main(java.lang.String[] args) |
abstract void |
scrapeTag0(ContentScraper.Tag tag) |
abstract void |
scrapeTag1(ContentScraper.Tag tag) |
abstract void |
scrapeText(char[] text,
java.lang.String insideTag) |
static java.lang.String |
stripAllTags(char[] s) |
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
deregisterHtmlFilterEventListener, finish, registerHtmlFilterEventListener, scrapeComment
protected static final java.lang.String EMPTY_STRING
public static final char sp
public static final char lb
public static final char rb
public static final char sl
private java.util.Set<java.lang.String> tags0
private java.util.Set<java.lang.String> tags1
public AbstractScraper(java.util.Set<java.lang.String> tags0, java.util.Set<java.lang.String> tags1)
tags0
- tags1
- public abstract void scrapeText(char[] text, java.lang.String insideTag)
scrapeText
in interface Scraper
public abstract void scrapeTag0(ContentScraper.Tag tag)
scrapeTag0
in interface Scraper
public abstract void scrapeTag1(ContentScraper.Tag tag)
scrapeTag1
in interface Scraper
public static java.lang.String stripAllTags(char[] s)
protected static final java.lang.String cleanLine(java.lang.String s)
public static void main(java.lang.String[] args)