us.codecraft.webmagic.selector

Interface Selectable

All Known Implementing Classes:

AbstractSelectable, Html, HtmlNode, Json, PlainText

public interface Selectable

Selectable text.

Since:

0.1.0

Author:

code4crafter@gmail.com

Method Summary

Modifier and Type	Method and Description
Selectable	$(String selector) select list with css selector
Selectable	$(String selector, String attrName) select list with css selector
List<String>	all() multi string result
Selectable	css(String selector) select list with css selector
Selectable	css(String selector, String attrName) select list with css selector
String	get() single string result
Selectable	jsonPath(String jsonPath) extract by JSON Path expression
Selectable	links() select all links
boolean	match() if result exist for select
List<Selectable>	nodes() get all nodes
Selectable	regex(String regex) select list with regex, default group is group 1
Selectable	regex(String regex, int group) select list with regex
Selectable	replace(String regex, String replacement) replace with regex
Selectable	select(Selector selector) extract by custom selector
Selectable	selectList(Selector selector) extract by custom selector
Selectable	smartContent() select smart content with ReadAbility algorithm
String	toString() single string result
Selectable	xpath(String xpath) select list with xpath

Method Detail

xpath

Selectable xpath(String xpath)

select list with xpath

Parameters:

xpath - xpath

Returns:

new Selectable after extract

$

Selectable $(String selector)

select list with css selector

Parameters:

selector - css selector expression

Returns:

new Selectable after extract

$

Selectable $(String selector,
             String attrName)

select list with css selector

Parameters:

selector - css selector expression

attrName - attribute name of css selector

Returns:

new Selectable after extract

css

Selectable css(String selector)

select list with css selector

Parameters:

selector - css selector expression

Returns:

new Selectable after extract

css

Selectable css(String selector,
               String attrName)

select list with css selector

Parameters:

selector - css selector expression

attrName - attribute name of css selector

Returns:

new Selectable after extract

smartContent

Selectable smartContent()

select smart content with ReadAbility algorithm

Returns:

content

links

Selectable links()

select all links

Returns:

all links

regex

Selectable regex(String regex)

select list with regex, default group is group 1

Parameters:

regex - regex

Returns:

new Selectable after extract

regex

Selectable regex(String regex,
                 int group)

select list with regex

Parameters:

regex - regex

group - group

Returns:

new Selectable after extract

replace

Selectable replace(String regex,
                   String replacement)

replace with regex

Parameters:

regex - regex

replacement - replacement

Returns:

new Selectable after extract

toString

String toString()

single string result

Overrides:

toString in class Object

Returns:

single string result

get

String get()

single string result

Returns:

single string result

match

boolean match()

if result exist for select

Returns:

true if result exist

all

List<String> all()

multi string result

Returns:

multi string result

jsonPath

Selectable jsonPath(String jsonPath)

extract by JSON Path expression

Parameters:

jsonPath - jsonPath

Returns:

result

select

Selectable select(Selector selector)

extract by custom selector

Parameters:

selector - selector

Returns:

result

selectList

Selectable selectList(Selector selector)

extract by custom selector

Parameters:

selector - selector

Returns:

result

nodes

List<Selectable> nodes()

get all nodes

Returns:

result