de.tudarmstadt.ukp.wikipedia.api.Wikipedia.getPage()方法的使用及代码示例

x33g5p2x  于2022-02-03 转载在 其他  
字(11.4k)|赞(0)|评价(0)|浏览(105)

本文整理了Java中de.tudarmstadt.ukp.wikipedia.api.Wikipedia.getPage()方法的一些代码示例,展示了Wikipedia.getPage()的具体用法。这些代码示例主要来源于Github/Stackoverflow/Maven等平台,是从一些精选项目中提取出来的代码,具有较强的参考意义,能在一定程度帮忙到你。Wikipedia.getPage()方法的具体详情如下:
包路径:de.tudarmstadt.ukp.wikipedia.api.Wikipedia
类名称:Wikipedia
方法名:getPage

Wikipedia.getPage介绍

[英]Gets the page for a given pageId.
[中]获取给定pageId的页面。

代码示例

代码示例来源:origin: dkpro/dkpro-jwpl

public Page next() {
  Page page = null;
  try {
    page = this.wiki.getPage(pageIDs.get(iterPosition));
  } catch (WikiApiException e) {
    logger.error("Could not load page with id {}", pageIDs.get(iterPosition), e);
  }
  iterPosition++;
  return page;
}

代码示例来源:origin: dkpro/dkpro-jwpl

/**
 * Gets the discussion page for an article page with the given pageId.
 *
 * @param articlePageId The id of the page.
 * @return The page object for a given pageId.
 * @throws WikiApiException Thrown if errors occurred.
 */
public Page getDiscussionPage(int articlePageId) throws WikiApiException {
  //Retrieve discussion page with article title
  //TODO not the prettiest solution, but currently discussions are only marked in the title
  return getDiscussionPage(getPage(articlePageId));
}

代码示例来源:origin: dkpro/dkpro-jwpl

/**
 * Gets the discussion page for the page with the given title.
 * The page retrieval works as defined in {@link #getPage(String title)}
 *
 * @param title The title of the page for which the discussions should be retrieved.
 * @return The page object for the discussion page.
 * @throws WikiApiException If no page or redirect with this title exists or title could not be properly parsed.
 */
public Page getDiscussionPage(String title) throws WikiApiException  {
  return getDiscussionPage(getPage(title));
}

代码示例来源:origin: de.tudarmstadt.ukp.dkpro.lexsemresource/de.tudarmstadt.ukp.dkpro.lexsemresource.wikipedia-asl

public boolean containsLexeme(String lexeme) throws LexicalSemanticResourceException {
   lexeme = WikipediaArticleUtils.getCaseSensitiveLexeme(lexeme, isCaseSensitive);
    try {
    wiki.getPage(lexeme);
  } catch (WikiApiException e) {
    return false;
  }
  return true;
}

代码示例来源:origin: dkpro/dkpro-jwpl

/**
 * @return The set of articles that are categorized under this category.
 * @throws WikiApiException
 */
public Set<Page> getArticles() throws WikiApiException {
  Set<Integer> tmpSet = getArticleIds();
  Set<Page> pages = new HashSet<Page>();
  for (int pageID : tmpSet) {
    pages.add(this.wiki.getPage(pageID));
  }
  return pages;
}

代码示例来源:origin: dkpro/dkpro-jwpl

/**
 * Returns an iterable containing all archived discussion pages for
 * the page with the given title String. <br>
 * The page retrieval works as defined in {@link #getPage(String title)}.<br>
 * The most recent discussion page is NOT included here!
 * It can be obtained with {@link #getDiscussionPage(Page)}.
 *
 * @param title The title of the page for which the discussions should be retrieved.
 * @return The page object for the discussion page.
 * @throws WikiApiException If no page or redirect with this title exists or title could not be properly parsed.
 */
public Iterable<Page> getDiscussionArchives(String title) throws WikiApiException  {
  //Retrieve discussion archive pages with page title
  return getDiscussionArchives(getPage(title));
}

代码示例来源:origin: dkpro/dkpro-jwpl

/**
 * Returns an iterable containing all archived discussion pages for
 * the page with the given title String. <br>
 * The page retrieval works as defined in {@link #getPage(int)}. <br>
 * The most recent discussion page is NOT included here!
 * It can be obtained with {@link #getDiscussionPage(Page)}.
 *
 * @param articlePageId The id of the page for which to the the discussion archives
 * @return The page object for the discussion page.
 * @throws WikiApiException If no page or redirect with this title exists or title could not be properly parsed.
 */
public Iterable<Page> getDiscussionArchives(int articlePageId) throws WikiApiException {
  //Retrieve discussion archive pages with page id
  return getDiscussionArchives(getPage(articlePageId));
}

代码示例来源:origin: dkpro/dkpro-jwpl

/**
 * Returns the names of all templates contained in the specified page.
 *
 * @param pageTitle
 *            the title of the page for which the templates should be
 *            retrieved
 * @return A List with the names of the templates contained in the specified
 *         page
 * @throws WikiApiException
 *             If there was any error retrieving the page object (most
 *             likely if the templates are corrupted)
 */
public List<String> getTemplateNamesFromPage(String pageTitle) throws WikiApiException{
  Page p=null;
  try{
    p = wiki.getPage(pageTitle);
  }catch (WikiApiException e) {
    return new ArrayList<String>();
  }
  return getTemplateNamesFromPage(p);
}

代码示例来源:origin: dkpro/dkpro-jwpl

/**
 * Returns the article page for a given discussion page.
 *
 * @param discussionPage
 *            the discussion page object
 * @return The page object of the article associated with the discussion. If
 *         the parameter already was an article, it is returned directly.
 * @throws WikiApiException Thrown if errors occurred.
 */
public Page getArticleForDiscussionPage(Page discussionPage) throws WikiApiException {
  if(discussionPage.isDiscussion()){
    String title = discussionPage.getTitle().getPlainTitle().replaceAll(WikiConstants.DISCUSSION_PREFIX, "");
    if(title.contains("/")){
      //If we have a discussion archive
      //TODO This does not support articles that contain slashes-
      //However, the rest of the API cannot cope with that as well, so this should not be any extra trouble
      title = title.split("/")[0];
    }
    return getPage(title);
  }else{
    return discussionPage;
  }
}

代码示例来源:origin: de.tudarmstadt.ukp.similarity.algorithms/de.tudarmstadt.ukp.similarity.algorithms.wikipedia-asl

/**
 * Resolves disambiguation pages into candidate pages and returns the best relatedness value out of all candidate pairs.
 * @param token1 The first token.
 * @param token2 The second token.
 * @return The relatedness value between the two pages that belong to the given tokens.
 * @throws WikiException
 */
protected double getRelatednessValue(String token1, String token2) throws WikiException {
  // Get the pages that belong to the tokens.
  // Encode the search string as a wikipedia title before searching.
  Page page1;
  Page page2;
  try {
    page1 = wiki.getPage(token1);
    page2 = wiki.getPage(token2);
  } catch (WikiPageNotFoundException e) {
    return NOT_IN_WIKIPEDIA;
  }
  // resolve disambiguation pages
  Set<Page> pageSet1 = getDisambiguationPageSet(page1);
  Set<Page> pageSet2 = getDisambiguationPageSet(page2);
  List<Double> relatednessValues = this.getRelatednessValues(pageSet1, pageSet2);
  return getBestRelatedness(relatednessValues);
}

代码示例来源:origin: dkpro/dkpro-similarity

/**
 * Resolves disambiguation pages into candidate pages and returns the best relatedness value out of all candidate pairs.
 * @param token1 The first token.
 * @param token2 The second token.
 * @return The relatedness value between the two pages that belong to the given tokens.
 * @throws WikiException
 */
protected double getRelatednessValue(String token1, String token2) throws WikiException {
  // Get the pages that belong to the tokens.
  // Encode the search string as a wikipedia title before searching.
  Page page1;
  Page page2;
  try {
    page1 = wiki.getPage(token1);
    page2 = wiki.getPage(token2);
  } catch (WikiPageNotFoundException e) {
    return NOT_IN_WIKIPEDIA;
  }
  // resolve disambiguation pages
  Set<Page> pageSet1 = getDisambiguationPageSet(page1);
  Set<Page> pageSet2 = getDisambiguationPageSet(page2);
  List<Double> relatednessValues = this.getRelatednessValues(pageSet1, pageSet2);
  return getBestRelatedness(relatednessValues);
}

代码示例来源:origin: de.tudarmstadt.ukp.dkpro.lexsemresource/de.tudarmstadt.ukp.dkpro.lexsemresource.wikipedia-asl

public static Page entityToPage(Wikipedia wiki, Entity entity, boolean isCaseSensitive) throws LexicalSemanticResourceException {
  String lexeme = getCaseSensitiveLexeme(entity.getFirstLexeme(), isCaseSensitive);
   try {
    return wiki.getPage(lexeme);
  } catch (WikiApiException e) {
    throw new LexicalSemanticResourceException(e);
  }
}

代码示例来源:origin: dkpro/dkpro-core

protected void addDocumentMetaData(JCas jcas, int pageId, int revisionId)
  throws WikiTitleParsingException, WikiApiException
{
  // fix for issue http://code.google.com/p/dkpro-core-asl/issues/detail?id=209
  String language = WikiUtils.jwplLanguage2dkproLanguage(dbconfig.getLanguage());
  DocumentMetaData metaData = DocumentMetaData.create(jcas);
  metaData.setDocumentTitle(wiki.getPage(pageId).getTitle().getWikiStyleTitle());
  metaData.setCollectionId(Integer.valueOf(pageId).toString());
  metaData.setDocumentId(Integer.valueOf(revisionId).toString());
  metaData.setLanguage(language);
}

代码示例来源:origin: dkpro/dkpro-jwpl

Page page = wiki.getPage(title);
  System.out.println(page.getText());
} catch (WikiApiException e) {

代码示例来源:origin: dkpro/dkpro-jwpl

public static void main(String[] args) throws WikiApiException {

    // configure the database connection parameters
    DatabaseConfiguration dbConfig = new DatabaseConfiguration();
    dbConfig.setHost("SERVER_URL");
    dbConfig.setDatabase("DATABASE");
    dbConfig.setUser("USER");
    dbConfig.setPassword("PASSWORD");
    dbConfig.setLanguage(Language.german);

    // Create a new German wikipedia.
    Wikipedia wiki = new Wikipedia(dbConfig);

    // Get the page with title "Hello world".
    // May throw an exception, if the page does not exist.
    Page page = wiki.getPage("Hello world");
    System.out.println(page.getText());

  }
}

代码示例来源:origin: dkpro/dkpro-jwpl

public static void main(String[] args) throws WikiApiException {

    // configure the database connection parameters
    DatabaseConfiguration dbConfig = new DatabaseConfiguration();
    dbConfig.setHost("SERVER_URL");
    dbConfig.setDatabase("DATABASE");
    dbConfig.setUser("USER");
    dbConfig.setPassword("PASSWORD");
    dbConfig.setLanguage(Language.german);

    // Create a new German wikipedia.
    Wikipedia wiki = new Wikipedia(dbConfig);

    String title = "Hello world";
    if (wiki.existsPage(title)) {
      Page page = wiki.getPage(title);
      System.out.println(page.getText());
    }
    else {
      System.out.println("Page " + title + " does not exist");
    }
  }
}

代码示例来源:origin: dkpro/dkpro-jwpl

/**
 * @param args
 */
public static void main(String[] args)
{
  DatabaseConfiguration dbconf = new DatabaseConfiguration();
  dbconf.setDatabase("wiki_en_20120104_rev");
  dbconf.setUser("root");
  dbconf.setPassword("");
  dbconf.setHost("127.0.0.1:3307");
  dbconf.setLanguage(WikiConstants.Language.english);
  try {
    Wikipedia wiki = new Wikipedia(dbconf);
    Page p = wiki.getPage("Ari Sitas");
    List<ExtractedSection> sects = ParseUtils.getSections(p.getText(),p.getTitle().toString(),  -1);
    for(ExtractedSection sect:sects){
      System.out.println(sect.getBody());
    }
  }
  catch (Exception e) {
    // TODO handle exception
    e.printStackTrace();
  }
}

代码示例来源:origin: dkpro/dkpro-jwpl

Page p = wiki.getPage("Dog");

代码示例来源:origin: dkpro/dkpro-jwpl

public static void main(String[] args) throws WikiApiException {
  //db connection settings
  DatabaseConfiguration dbConfig = new DatabaseConfiguration();
  dbConfig.setDatabase("DATABASE");
  dbConfig.setHost("HOST");
  dbConfig.setUser("USER");
  dbConfig.setPassword("PASSWORD");
  dbConfig.setLanguage(Language.english);
  //initialize a wiki
  Wikipedia wiki = new Wikipedia(dbConfig);
  MediaWikiParserFactory pf = new MediaWikiParserFactory(Language.english);
  MediaWikiParser parser = pf.createParser();
  //get the page 'House_(disambiguation)'
  ParsedPage pp = parser.parse(wiki.getPage("House_(disambiguation)").getText());
  int i = 1;
  // print out all nested lists of the page
  for(NestedList nl : pp.getNestedLists()){
    System.out.println(i + ": \n" + outputNestedList(nl,0));
    i++;
  }
}

代码示例来源:origin: dkpro/dkpro-jwpl

public static void main(String[] args) throws WikiApiException {
    //db connection settings
    DatabaseConfiguration dbConfig = new DatabaseConfiguration();
    dbConfig.setDatabase("DATABASE");
    dbConfig.setHost("HOST");
    dbConfig.setUser("USER");
    dbConfig.setPassword("PASSWORD");
    dbConfig.setLanguage(Language.english);
    
    //initialize a wiki
    Wikipedia wiki = new Wikipedia(dbConfig);
    
    //get the page 'Dog'
    Page p = wiki.getPage("Dog");
    
    //get a ParsedPage object
    MediaWikiParserFactory pf = new MediaWikiParserFactory();
    MediaWikiParser parser = pf.createParser();
    ParsedPage pp = parser.parse(p.getText());
  
    //get the sections of the page
    List<Section> sections = pp.getSections();
    
    for(Section section : sections) {
      System.out.println(section.getTitle());
    }
  }
}

相关文章