cn.edu.hfut.dmic.contentextractor

类 ContentExtractor

java.lang.Object

cn.edu.hfut.dmic.contentextractor.ContentExtractor

public class ContentExtractor
extends Object

ContentExtractor could extract content,title,time from news webpage

作者:

hu

字段概要

字段

限定符和类型	字段和说明
protected org.jsoup.nodes.Document	doc
protected HashMap<org.jsoup.nodes.Element,cn.edu.hfut.dmic.contentextractor.ContentExtractor.CountInfo>	infoMap
static org.slf4j.Logger	LOG

方法概要

限定符和类型	方法和说明
protected void	clean()
protected cn.edu.hfut.dmic.contentextractor.ContentExtractor.CountInfo	computeInfo(org.jsoup.nodes.Node node)
protected double	computeScore(org.jsoup.nodes.Element tag)
protected double	computeVar(ArrayList<Integer> data)
protected int	editDistance(String word1, String word2)
static String	getContentByDoc(org.jsoup.nodes.Document doc)
static String	getContentByHtml(String html)
static String	getContentByHtml(String html, String url)
static String	getContentByUrl(String url)
org.jsoup.nodes.Element	getContentElement()
static org.jsoup.nodes.Element	getContentElementByDoc(org.jsoup.nodes.Document doc)
static org.jsoup.nodes.Element	getContentElementByHtml(String html)
static org.jsoup.nodes.Element	getContentElementByHtml(String html, String url)
static org.jsoup.nodes.Element	getContentElementByUrl(String url)
protected String	getDate(org.jsoup.nodes.Element contentElement)
News	getNews()
static News	getNewsByDoc(org.jsoup.nodes.Document doc)
static News	getNewsByHtml(String html)
static News	getNewsByHtml(String html, String url)
static News	getNewsByUrl(String url)
protected String	getTime(org.jsoup.nodes.Element contentElement)
protected String	getTitle(org.jsoup.nodes.Element contentElement)
protected String	getTitleByEditDistance(org.jsoup.nodes.Element contentElement)
protected int	lcs(String x, String y)
static void	main(String[] args)
protected double	strSim(String a, String b)

从类继承的方法 java.lang.Object

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

字段详细资料

LOG

public static final org.slf4j.Logger LOG

doc

protected org.jsoup.nodes.Document doc

infoMap

protected HashMap<org.jsoup.nodes.Element,cn.edu.hfut.dmic.contentextractor.ContentExtractor.CountInfo> infoMap

方法详细资料

clean

protected void clean()

computeInfo

protected cn.edu.hfut.dmic.contentextractor.ContentExtractor.CountInfo computeInfo(org.jsoup.nodes.Node node)

computeScore

protected double computeScore(org.jsoup.nodes.Element tag)

computeVar

protected double computeVar(ArrayList<Integer> data)

getContentElement

public org.jsoup.nodes.Element getContentElement()
                                          throws Exception

抛出:

Exception

getNews

public News getNews()
             throws Exception

抛出:

Exception

getTime

protected String getTime(org.jsoup.nodes.Element contentElement)
                  throws Exception

抛出:

Exception

getDate

protected String getDate(org.jsoup.nodes.Element contentElement)
                  throws Exception

抛出:

Exception

strSim

protected double strSim(String a,
                        String b)

getTitle

protected String getTitle(org.jsoup.nodes.Element contentElement)
                   throws Exception

抛出:

Exception

getTitleByEditDistance

protected String getTitleByEditDistance(org.jsoup.nodes.Element contentElement)
                                 throws Exception

抛出:

Exception

lcs

protected int lcs(String x,
                  String y)

editDistance

protected int editDistance(String word1,
                           String word2)

getContentElementByDoc

public static org.jsoup.nodes.Element getContentElementByDoc(org.jsoup.nodes.Document doc)
                                                      throws Exception

抛出:

Exception

getContentElementByHtml

public static org.jsoup.nodes.Element getContentElementByHtml(String html)
                                                       throws Exception

抛出:

Exception

getContentElementByHtml

public static org.jsoup.nodes.Element getContentElementByHtml(String html,
                                                              String url)
                                                       throws Exception

抛出:

Exception

getContentElementByUrl

public static org.jsoup.nodes.Element getContentElementByUrl(String url)
                                                      throws Exception

抛出:

Exception

getContentByDoc

public static String getContentByDoc(org.jsoup.nodes.Document doc)
                              throws Exception

抛出:

Exception

getContentByHtml

public static String getContentByHtml(String html)
                               throws Exception

抛出:

Exception

getContentByHtml

public static String getContentByHtml(String html,
                                      String url)
                               throws Exception

抛出:

Exception

getContentByUrl

public static String getContentByUrl(String url)
                              throws Exception

抛出:

Exception

getNewsByDoc

public static News getNewsByDoc(org.jsoup.nodes.Document doc)
                         throws Exception

抛出:

Exception

getNewsByHtml

public static News getNewsByHtml(String html)
                          throws Exception

抛出:

Exception

getNewsByHtml

public static News getNewsByHtml(String html,
                                 String url)
                          throws Exception

抛出:

Exception

getNewsByUrl

public static News getNewsByUrl(String url)
                         throws Exception

抛出:

Exception

main

public static void main(String[] args)
                 throws Exception

抛出:

Exception