org.htmlparser.util

类 ParserUtils

java.lang.Object

org.htmlparser.util.ParserUtils

public class ParserUtils
extends java.lang.Object

构造器概要

构造器

构造器和说明
ParserUtils()

方法概要

限定符和类型	方法和说明
static Parser	createParserParsingAnInputString(java.lang.String input)
static Node[]	findTypeInNode(Node node, java.lang.Class type) Search given node and pick up any objects of given type.
static java.lang.String	removeChars(java.lang.String s, char occur)
static java.lang.String	removeEscapeCharacters(java.lang.String inputString)
static java.lang.String	removeTrailingBlanks(java.lang.String text)
static java.lang.String[]	splitButChars(java.lang.String input, java.lang.String charsDoNotBeRemoved)
static java.lang.String[]	splitButDigits(java.lang.String input, java.lang.String charsDoNotBeRemoved) Split the input string considering as string separator all the not numerical characters with the only exception of the characters specified in charsDoNotBeRemoved param.
static java.lang.String[]	splitChars(java.lang.String input, java.lang.String charsToBeRemoved)
static java.lang.String[]	splitSpaces(java.lang.String input, java.lang.String charsToBeRemoved)
static java.lang.String[]	splitTags(java.lang.String input, java.lang.Class nodeType)
static java.lang.String[]	splitTags(java.lang.String input, java.lang.Class nodeType, boolean recursive, boolean insideTag)
static java.lang.String[]	splitTags(java.lang.String input, NodeFilter filter)
static java.lang.String[]	splitTags(java.lang.String input, NodeFilter filter, boolean recursive, boolean insideTag)
static java.lang.String[]	splitTags(java.lang.String input, java.lang.String[] tags)
static java.lang.String[]	splitTags(java.lang.String input, java.lang.String[] tags, boolean recursive, boolean insideTag)
static java.lang.String	trimAllTags(java.lang.String input, boolean inside)
static java.lang.String	trimButChars(java.lang.String input, java.lang.String charsDoNotBeRemoved)
static java.lang.String	trimButCharsBeginEnd(java.lang.String input, java.lang.String charsDoNotBeRemoved)
static java.lang.String	trimButDigits(java.lang.String input, java.lang.String charsDoNotBeRemoved) Remove from the input string all the not numerical characters with the only exception of the characters specified in charsDoNotBeRemoved param.
static java.lang.String	trimButDigitsBeginEnd(java.lang.String input, java.lang.String charsDoNotBeRemoved) Remove from the beginning and the end of the input string all the not numerical characters with the only exception of the characters specified in charsDoNotBeRemoved param.
static java.lang.String	trimChars(java.lang.String input, java.lang.String charsToBeRemoved)
static java.lang.String	trimCharsBeginEnd(java.lang.String input, java.lang.String charsToBeRemoved)
static java.lang.String	trimSpaces(java.lang.String input, java.lang.String charsToBeRemoved)
static java.lang.String	trimSpacesBeginEnd(java.lang.String input, java.lang.String charsToBeRemoved)
static java.lang.String	trimTags(java.lang.String input, java.lang.Class nodeType)
static java.lang.String	trimTags(java.lang.String input, java.lang.Class nodeType, boolean recursive, boolean insideTag)
static java.lang.String	trimTags(java.lang.String input, NodeFilter filter)
static java.lang.String	trimTags(java.lang.String input, NodeFilter filter, boolean recursive, boolean insideTag)
static java.lang.String	trimTags(java.lang.String input, java.lang.String[] tags)
static java.lang.String	trimTags(java.lang.String input, java.lang.String[] tags, boolean recursive, boolean insideTag)

从类继承的方法 java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

构造器详细资料

ParserUtils

public ParserUtils()

方法详细资料

removeChars

public static java.lang.String removeChars(java.lang.String s,
                                           char occur)

removeEscapeCharacters

public static java.lang.String removeEscapeCharacters(java.lang.String inputString)

removeTrailingBlanks

public static java.lang.String removeTrailingBlanks(java.lang.String text)

findTypeInNode

public static Node[] findTypeInNode(Node node,
                                    java.lang.Class type)

Search given node and pick up any objects of given type.

参数:

node - The node to search.

type - The class to search for.

返回:

A node array with the matching nodes.

splitButDigits

public static java.lang.String[] splitButDigits(java.lang.String input,
                                                java.lang.String charsDoNotBeRemoved)

Split the input string considering as string separator all the not numerical characters with the only exception of the characters specified in charsDoNotBeRemoved param.
For example if you call splitButDigits("<DIV> +12.5, +3.4 </DIV>", "+."),
you obtain an array of strings {"+12.5", "+3.4"} as output (1,2,3,4 and 5 are digits and +,. are chars that do not be removed).

参数:

input - The string in input.

charsDoNotBeRemoved - The chars that do not be removed.

返回:

The array of strings as output.

trimButDigits

public static java.lang.String trimButDigits(java.lang.String input,
                                             java.lang.String charsDoNotBeRemoved)

Remove from the input string all the not numerical characters with the only exception of the characters specified in charsDoNotBeRemoved param.
For example if you call trimButDigits("<DIV> +12.5 </DIV>", "+."),
you obtain a string "+12.5" as output (1,2 and 5 are digits and +,. are chars that do not be removed).
For example if you call trimButDigits("<DIV> +1 2 . 5 </DIV>", "+."),
you obtain a string "+12.5" as output (the spaces between 1 and 2, 2 and ., . and 5 are removed).

参数:

input - The string in input.

charsDoNotBeRemoved - The chars that do not be removed.

返回:

The string as output.

trimButDigitsBeginEnd

public static java.lang.String trimButDigitsBeginEnd(java.lang.String input,
                                                     java.lang.String charsDoNotBeRemoved)

Remove from the beginning and the end of the input string all the not numerical characters with the only exception of the characters specified in charsDoNotBeRemoved param.
The removal process removes only chars at the beginning and at the end of the string.
For example if you call trimButDigitsBeginEnd("<DIV> +12.5 </DIV>", "+."),
you obtain a string "+12.5" as output (1,2 and 5 are digits and +,. are chars that do not be removed).
For example if you call trimButDigitsBeginEnd("<DIV> +1 2 . 5 </DIV>", "+."),
you obtain a string "+1 2 . 5" as output (the spacess inside the string are not removed).

参数:

input - - The string in input.

charsDoNotBeRemoved - - The chars that do not be removed.

返回:

The string as output.

splitSpaces

public static java.lang.String[] splitSpaces(java.lang.String input,
                                             java.lang.String charsToBeRemoved)

trimSpaces

public static java.lang.String trimSpaces(java.lang.String input,
                                          java.lang.String charsToBeRemoved)

trimSpacesBeginEnd

public static java.lang.String trimSpacesBeginEnd(java.lang.String input,
                                                  java.lang.String charsToBeRemoved)

splitButChars

public static java.lang.String[] splitButChars(java.lang.String input,
                                               java.lang.String charsDoNotBeRemoved)

trimButChars

public static java.lang.String trimButChars(java.lang.String input,
                                            java.lang.String charsDoNotBeRemoved)

trimButCharsBeginEnd

public static java.lang.String trimButCharsBeginEnd(java.lang.String input,
                                                    java.lang.String charsDoNotBeRemoved)

splitChars

public static java.lang.String[] splitChars(java.lang.String input,
                                            java.lang.String charsToBeRemoved)

trimChars

public static java.lang.String trimChars(java.lang.String input,
                                         java.lang.String charsToBeRemoved)

trimCharsBeginEnd

public static java.lang.String trimCharsBeginEnd(java.lang.String input,
                                                 java.lang.String charsToBeRemoved)

splitTags

public static java.lang.String[] splitTags(java.lang.String input,
                                           java.lang.String[] tags)
                                    throws ParserException,
                                           java.io.UnsupportedEncodingException

抛出:

ParserException

java.io.UnsupportedEncodingException

splitTags

public static java.lang.String[] splitTags(java.lang.String input,
                                           java.lang.String[] tags,
                                           boolean recursive,
                                           boolean insideTag)
                                    throws ParserException,
                                           java.io.UnsupportedEncodingException

抛出:

ParserException

java.io.UnsupportedEncodingException

splitTags

public static java.lang.String[] splitTags(java.lang.String input,
                                           java.lang.Class nodeType)
                                    throws ParserException,
                                           java.io.UnsupportedEncodingException

抛出:

ParserException

java.io.UnsupportedEncodingException

splitTags

public static java.lang.String[] splitTags(java.lang.String input,
                                           java.lang.Class nodeType,
                                           boolean recursive,
                                           boolean insideTag)
                                    throws ParserException,
                                           java.io.UnsupportedEncodingException

抛出:

ParserException

java.io.UnsupportedEncodingException

splitTags

public static java.lang.String[] splitTags(java.lang.String input,
                                           NodeFilter filter)
                                    throws ParserException,
                                           java.io.UnsupportedEncodingException

抛出:

ParserException

java.io.UnsupportedEncodingException

splitTags

public static java.lang.String[] splitTags(java.lang.String input,
                                           NodeFilter filter,
                                           boolean recursive,
                                           boolean insideTag)
                                    throws ParserException,
                                           java.io.UnsupportedEncodingException

抛出:

ParserException

java.io.UnsupportedEncodingException

trimAllTags

public static java.lang.String trimAllTags(java.lang.String input,
                                           boolean inside)

trimTags

public static java.lang.String trimTags(java.lang.String input,
                                        java.lang.String[] tags)
                                 throws ParserException,
                                        java.io.UnsupportedEncodingException

抛出:

ParserException

java.io.UnsupportedEncodingException

trimTags

public static java.lang.String trimTags(java.lang.String input,
                                        java.lang.String[] tags,
                                        boolean recursive,
                                        boolean insideTag)
                                 throws ParserException,
                                        java.io.UnsupportedEncodingException

抛出:

ParserException

java.io.UnsupportedEncodingException

trimTags

public static java.lang.String trimTags(java.lang.String input,
                                        java.lang.Class nodeType)
                                 throws ParserException,
                                        java.io.UnsupportedEncodingException

抛出:

ParserException

java.io.UnsupportedEncodingException

trimTags

public static java.lang.String trimTags(java.lang.String input,
                                        java.lang.Class nodeType,
                                        boolean recursive,
                                        boolean insideTag)
                                 throws ParserException,
                                        java.io.UnsupportedEncodingException

抛出:

ParserException

java.io.UnsupportedEncodingException

trimTags

public static java.lang.String trimTags(java.lang.String input,
                                        NodeFilter filter)
                                 throws ParserException,
                                        java.io.UnsupportedEncodingException

抛出:

ParserException

java.io.UnsupportedEncodingException

trimTags

public static java.lang.String trimTags(java.lang.String input,
                                        NodeFilter filter,
                                        boolean recursive,
                                        boolean insideTag)
                                 throws ParserException,
                                        java.io.UnsupportedEncodingException

抛出:

ParserException

java.io.UnsupportedEncodingException

createParserParsingAnInputString

public static Parser createParserParsingAnInputString(java.lang.String input)
                                               throws ParserException,
                                                      java.io.UnsupportedEncodingException

抛出:

ParserException

java.io.UnsupportedEncodingException