Java Doc for htmlFilterContentScraper.java in » Search-Engine » yacy » de » anomic » htmlFilter » Java Source Code / Java DocumentationJava Source Code and Java Documentation
Java Source Code / Java Documentation
1.
6.0 JDK Core
2.
6.0 JDK Modules
3.
6.0 JDK Modules com.sun
4.
6.0 JDK Modules com.sun.java
5.
6.0 JDK Modules sun
6.
6.0 JDK Platform
7.
Ajax
8.
Apache Harmony Java SE
9.
Aspect oriented
10.
Authentication Authorization
11.
Blogger System
12.
Build
13.
Byte Code
14.
Cache
15.
Chart
16.
Chat
17.
Code Analyzer
18.
Collaboration
19.
Content Management System
20.
Database Client
21.
Database DBMS
22.
Database JDBC Connection Pool
23.
Database ORM
24.
Development
25.
EJB Server geronimo
26.
EJB Server GlassFish
27.
EJB Server JBoss 4.2.1
28.
EJB Server resin 3.1.5
29.
ERP CRM Financial
30.
ESB
31.
Forum
32.
GIS
33.
Graphic Library
34.
Groupware
35.
HTML Parser
36.
IDE
37.
IDE Eclipse
38.
IDE Netbeans
39.
Installer
40.
Internationalization Localization
41.
Inversion of Control
42.
Issue Tracking
43.
J2EE
44.
JBoss
45.
JMS
46.
JMX
47.
Library
48.
Mail Clients
49.
Net
50.
Parser
51.
PDF
52.
Portal
53.
Profiler
54.
Project Management
55.
Report
56.
RSS RDF
57.
Rule Engine
58.
Science
59.
Scripting
60.
Search Engine
61.
Security
62.
Sevlet Container
63.
Source Control
64.
Swing Library
65.
Template Engine
66.
Test Coverage
67.
Testing
68.
UML
69.
Web Crawler
70.
Web Framework
71.
Web Mail
72.
Web Server
73.
Web Services
74.
Web Services apache cxf 2.0.1
75.
Web Services AXIS2
76.
Wiki Engine
77.
Workflow Engines
78.
XML
79.
XML UI
Java
Java Tutorial
Java Open Source
Jar File Download
Java Articles
Java Products
Java by API
Photoshop Tutorials
Maya Tutorials
Flash Tutorials
3ds-Max Tutorials
Illustrator Tutorials
GIMP Tutorials
C# / C Sharp
C# / CSharp Tutorial
C# / CSharp Open Source
ASP.Net
ASP.NET Tutorial
JavaScript DHTML
JavaScript Tutorial
JavaScript Reference
HTML / CSS
HTML CSS Reference
C / ANSI-C
C Tutorial
C++
C++ Tutorial
Ruby
PHP
Python
Python Tutorial
Python Open Source
SQL Server / T-SQL
SQL Server / T-SQL Tutorial
Oracle PL / SQL
Oracle PL/SQL Tutorial
PostgreSQL
SQL / MySQL
MySQL Tutorial
VB.Net
VB.Net Tutorial
Flash / Flex / ActionScript
VBA / Excel / Access / Word
XML
XML Tutorial
Microsoft Office PowerPoint 2007 Tutorial
Microsoft Office Excel 2007 Tutorial
Microsoft Office Word 2007 Tutorial
Java Source Code / Java Documentation
»
Search Engine
»
yacy
»
de.anomic.htmlFilter
Source Cross Reference
Class Diagram
Java Document (Java Doc)
java.lang
.Object
de.anomic.htmlFilter
.htmlFilterAbstractScraper
de.anomic.htmlFilter
.htmlFilterContentScraper
htmlFilterContentScraper
public
class htmlFilterContentScraper extends
htmlFilterAbstractScraper
implements
htmlFilterScraper
(Code)
Field Summary
final
public
static
String
splitrex
Constructor Summary
public
htmlFilterContentScraper
(
yacyURL
root)
Method Summary
public
void
close
()
public
void
deregisterHtmlFilterEventListener
(
htmlFilterEventListener
listener)
void
fireScrapeTag0
(
String
tagname,
Properties
tagopts)
void
fireScrapeTag1
(
String
tagname,
Properties
tagopts, char[] text)
public
Map
<
yacyURL
,
String
>
getAnchors
()
public
String
getAuthor
()
public
String
[]
getContentLanguages
()
public
String
getContentType
()
public
String
getDescription
()
public
yacyURL
getFavicon
()
public
String
[]
getHeadlines
(int i)
public
TreeSet
<
htmlFilterImageEntry
>
getImages
()
public
String
[]
getKeywords
()
public
Map
<
String
,
String
>
getMetas
()
public
String
getRefreshPath
()
public
int
getRefreshSeconds
()
public
byte[]
getText
()
public
byte[]
getText
(
String
charSet)
public
String
getTitle
()
public
static
htmlFilterContentScraper
parseResource
(
yacyURL
location)
public
void
print
()
final
public
static boolean
punctuation
(char c)
public
void
registerHtmlFilterEventListener
(
htmlFilterEventListener
listener)
public
void
scrapeTag0
(
String
tagname,
Properties
tagopts)
public
void
scrapeTag1
(
String
tagname,
Properties
tagopts, char[] text)
public
void
scrapeText
(char[] newtext,
String
insideTag)
public
static
String
[]
urlComps
(
String
normalizedURL)
Field Detail
splitrex
final
public
static
String
splitrex
(Code)
Constructor Detail
htmlFilterContentScraper
public
htmlFilterContentScraper(
yacyURL
root)
(Code)
Method Detail
close
public
void close()
(Code)
deregisterHtmlFilterEventListener
public
void deregisterHtmlFilterEventListener(
htmlFilterEventListener
listener)
(Code)
fireScrapeTag0
void fireScrapeTag0(
String
tagname,
Properties
tagopts)
(Code)
fireScrapeTag1
void fireScrapeTag1(
String
tagname,
Properties
tagopts, char[] text)
(Code)
getAnchors
public
Map
<
yacyURL
,
String
> getAnchors()
(Code)
getAuthor
public
String
getAuthor()
(Code)
getContentLanguages
public
String
[] getContentLanguages()
(Code)
getContentType
public
String
getContentType()
(Code)
getDescription
public
String
getDescription()
(Code)
getFavicon
public
yacyURL
getFavicon()
(Code)
the URL to the favicon that belongs to the document
getHeadlines
public
String
[] getHeadlines(int i)
(Code)
getImages
public
TreeSet
<
htmlFilterImageEntry
> getImages()
(Code)
getKeywords
public
String
[] getKeywords()
(Code)
getMetas
public
Map
<
String
,
String
> getMetas()
(Code)
getRefreshPath
public
String
getRefreshPath()
(Code)
getRefreshSeconds
public
int getRefreshSeconds()
(Code)
getText
public
byte[] getText()
(Code)
getText
public
byte[] getText(
String
charSet)
(Code)
getTitle
public
String
getTitle()
(Code)
parseResource
public
static
htmlFilterContentScraper
parseResource(
yacyURL
location) throws
IOException
(Code)
print
public
void print()
(Code)
punctuation
final
public
static boolean punctuation(char c)
(Code)
registerHtmlFilterEventListener
public
void registerHtmlFilterEventListener(
htmlFilterEventListener
listener)
(Code)
scrapeTag0
public
void scrapeTag0(
String
tagname,
Properties
tagopts)
(Code)
scrapeTag1
public
void scrapeTag1(
String
tagname,
Properties
tagopts, char[] text)
(Code)
scrapeText
public
void scrapeText(char[] newtext,
String
insideTag)
(Code)
urlComps
public
static
String
[] urlComps(
String
normalizedURL)
(Code)
Fields inherited from
de.anomic.htmlFilter.htmlFilterAbstractScraper
final
public
static char lb
(Code)
(Java Doc)
final
public
static char rb
(Code)
(Java Doc)
final
public
static char sl
(Code)
(Java Doc)
Methods inherited from
de.anomic.htmlFilter.htmlFilterAbstractScraper
public
void close()
(Code)
(Java Doc)
public
static
serverCharBuffer
convertUmlaute(
serverCharBuffer
bb)
(Code)
(Java Doc)
public
void finalize()
(Code)
(Java Doc)
public
boolean isTag0(
String
tag)
(Code)
(Java Doc)
public
boolean isTag1(
String
tag)
(Code)
(Java Doc)
abstract
public
void scrapeTag0(
String
tagname,
Properties
tagopts)
(Code)
(Java Doc)
abstract
public
void scrapeTag1(
String
tagname,
Properties
tagopts, char[] text)
(Code)
(Java Doc)
abstract
public
void scrapeText(char[] text,
String
insideTag)
(Code)
(Java Doc)
public
static
serverCharBuffer
stripAll(
serverCharBuffer
bb)
(Code)
(Java Doc)
protected
static
serverCharBuffer
stripAllTags(
serverCharBuffer
bb)
(Code)
(Java Doc)
protected
static
serverCharBuffer
transscriptAll(
serverCharBuffer
bb)
(Code)
(Java Doc)
Methods inherited from
java.lang.Object
native
protected
Object
clone() throws
CloneNotSupportedException
(Code)
(Java Doc)
public
boolean equals(
Object
obj)
(Code)
(Java Doc)
protected
void finalize() throws
Throwable
(Code)
(Java Doc)
final native
public
Class
> getClass()
(Code)
(Java Doc)
native
public
int hashCode()
(Code)
(Java Doc)
final native
public
void notify()
(Code)
(Java Doc)
final native
public
void notifyAll()
(Code)
(Java Doc)
public
String
toString()
(Code)
(Java Doc)
final native
public
void wait(long timeout) throws
InterruptedException
(Code)
(Java Doc)
final
public
void wait(long timeout, int nanos) throws
InterruptedException
(Code)
(Java Doc)
final
public
void wait() throws
InterruptedException
(Code)
(Java Doc)
www.java2java.com
|
Contact Us
Copyright 2009 - 12 Demo Source and Support. All rights reserved.
All other trademarks are property of their respective owners.