public class WebcrawlerConfig extends Object
Modifier and Type | Field and Description |
---|---|
static String |
_rcsid |
static String |
ATTR_ASPSESSIONREMOVAL
aspsessionremoval attribute
|
static String |
ATTR_BINREGEXP
The bin regular expression
|
static String |
ATTR_BVSESSIONREMOVAL
bvsessionremoval attribute
|
static String |
ATTR_DESCRIPTION
description attribute
|
static String |
ATTR_DOMAIN
Domain/realm part of credentials (if any)
|
static String |
ATTR_INSENSITIVE
Whether the match is case insensitive
|
static String |
ATTR_JAVASESSIONREMOVAL
javasessionremoval attribute
|
static String |
ATTR_MAP
Map attribute
|
static String |
ATTR_MATCH
Match attribute
|
static String |
ATTR_MATCHREGEXP
Form name or link target regexp for authentication page
|
static String |
ATTR_NAME
name attribute
|
static String |
ATTR_NAMEREGEXP
Authentication parameter name regexp
|
static String |
ATTR_OVERRIDETARGETURL
URL to fetch next in a sequence (an override)
|
static String |
ATTR_PASSWORD
Password part of credentials
|
static String |
ATTR_PHPSESSIONREMOVAL
phpsessionremoval attribute
|
static String |
ATTR_REGEXP
regexp attribute
|
static String |
ATTR_REORDER
reorder attribute
|
static String |
ATTR_TOKEN
token attribute
|
static String |
ATTR_TRUSTEVERYTHING
"Trust everything" attribute - replacing truststore if set to 'true'
|
static String |
ATTR_TRUSTSTORE
Trust store section of authentication record
|
static String |
ATTR_TYPE
Type of security
|
static String |
ATTR_URLREGEXP
Regexp for access control node
|
static String |
ATTR_USERNAME
Username part of credentials
|
static String |
ATTR_VALUE
The value attribute (used for maxconnections and maxkbpersecond)
|
static String |
ATTRVALUE_BASIC
Type value for basic authentication
|
static String |
ATTRVALUE_CONTENT
Authentication page type: Access
|
static String |
ATTRVALUE_FALSE
Value false
|
static String |
ATTRVALUE_FORM
Authentication page type: Form
|
static String |
ATTRVALUE_LINK
Authentication page type: Link
|
static String |
ATTRVALUE_NO
Value no
|
static String |
ATTRVALUE_NTLM
Type value for NTLM authentication
|
static String |
ATTRVALUE_REDIRECTION
Authentication page type: Redirection
|
static String |
ATTRVALUE_SESSION
Type value for session-based authentication
|
static String |
ATTRVALUE_TRUE
Value true
|
static String |
ATTRVALUE_YES
Value yes
|
static String |
NODE_ACCESS
Forced acl access token node.
|
static String |
NODE_ACCESSCREDENTIAL
Access control description node
|
static String |
NODE_AUTHPAGE
Authentication page description node
|
static String |
NODE_AUTHPARAMETER
Authentication parameter node
|
static String |
NODE_BINDESC
The bin description node
|
static String |
NODE_EXCLUDEHEADER
Exclude header node.
|
static String |
NODE_EXCLUDES
Exclude regexps node.
|
static String |
NODE_EXCLUDESCONTENTINDEX
Exclude any page containing specified regex in their body from index
|
static String |
NODE_EXCLUDESINDEX
Exclude regexps node.
|
static String |
NODE_INCLUDES
Include regexps node.
|
static String |
NODE_INCLUDESINDEX
Include regexps node.
|
static String |
NODE_LIMITTOSEEDS
Limit to seeds.
|
static String |
NODE_MAP
Map entry specification node.
|
static String |
NODE_MAXCONNECTIONS
The max connections node
|
static String |
NODE_MAXFETCHESPERMINUTE
The max fetch rate node
|
static String |
NODE_MAXKBPERSECOND
The bandwidth node
|
static String |
NODE_METADATA
Forced metadata.
|
static String |
NODE_SEEDS
The seeds node.
|
static String |
NODE_TRUST
Trust store description node
|
static String |
NODE_URLSPEC
Canonicalization rule.
|
static String |
PARAMETER_EMAIL
Email (a parameter)
|
static String |
PARAMETER_PROXYAUTHDOMAIN
Proxy auth domain (parameter)
|
static String |
PARAMETER_PROXYAUTHPASSWORD
Proxy auth password (parameter)
|
static String |
PARAMETER_PROXYAUTHUSERNAME
Proxy auth username (parameter)
|
static String |
PARAMETER_PROXYHOST
Proxy host name (parameter)
|
static String |
PARAMETER_PROXYPORT
Proxy port (parameter)
|
static String |
PARAMETER_ROBOTSUSAGE
Robots usage (a parameter)
|
Constructor and Description |
---|
WebcrawlerConfig() |
public static final String _rcsid
public static final String PARAMETER_ROBOTSUSAGE
public static final String PARAMETER_EMAIL
public static final String PARAMETER_PROXYHOST
public static final String PARAMETER_PROXYPORT
public static final String PARAMETER_PROXYAUTHDOMAIN
public static final String PARAMETER_PROXYAUTHUSERNAME
public static final String PARAMETER_PROXYAUTHPASSWORD
public static final String NODE_BINDESC
public static final String ATTR_BINREGEXP
public static final String ATTR_INSENSITIVE
public static final String NODE_MAXCONNECTIONS
public static final String NODE_MAXKBPERSECOND
public static final String NODE_MAXFETCHESPERMINUTE
public static final String ATTR_VALUE
public static final String NODE_ACCESSCREDENTIAL
public static final String ATTR_URLREGEXP
public static final String ATTR_TYPE
public static final String ATTRVALUE_BASIC
public static final String ATTRVALUE_NTLM
public static final String ATTRVALUE_SESSION
public static final String ATTR_DOMAIN
public static final String ATTR_USERNAME
public static final String ATTR_PASSWORD
public static final String NODE_AUTHPAGE
public static final String ATTRVALUE_FORM
public static final String ATTRVALUE_LINK
public static final String ATTRVALUE_REDIRECTION
public static final String ATTRVALUE_CONTENT
public static final String ATTR_MATCHREGEXP
public static final String ATTR_OVERRIDETARGETURL
public static final String NODE_AUTHPARAMETER
public static final String ATTR_NAMEREGEXP
public static final String NODE_TRUST
public static final String ATTR_TRUSTSTORE
public static final String ATTR_TRUSTEVERYTHING
public static final String NODE_MAP
public static final String NODE_SEEDS
public static final String NODE_INCLUDES
public static final String NODE_EXCLUDES
public static final String NODE_INCLUDESINDEX
public static final String NODE_EXCLUDESINDEX
public static final String NODE_EXCLUDESCONTENTINDEX
public static final String NODE_LIMITTOSEEDS
public static final String NODE_URLSPEC
public static final String NODE_METADATA
public static final String NODE_ACCESS
public static final String NODE_EXCLUDEHEADER
public static final String ATTR_REGEXP
public static final String ATTR_DESCRIPTION
public static final String ATTR_REORDER
public static final String ATTR_JAVASESSIONREMOVAL
public static final String ATTR_ASPSESSIONREMOVAL
public static final String ATTR_PHPSESSIONREMOVAL
public static final String ATTR_BVSESSIONREMOVAL
public static final String ATTR_NAME
public static final String ATTR_TOKEN
public static final String ATTRVALUE_YES
public static final String ATTRVALUE_NO
public static final String ATTRVALUE_FALSE
public static final String ATTRVALUE_TRUE
public static final String ATTR_MATCH
public static final String ATTR_MAP